diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..6b148f3dd75e19c1fcfc81492f7900eecfb81bc6 --- /dev/null +++ b/README.md @@ -0,0 +1,55 @@ +--- +base_model: +- meta-llama/Llama-3.1-70B-Instruct +library_name: transformers +tags: +- mergekit +- merge + +--- +# llama-3.1-120b-instruct + +This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). +It's a recreation of [mlabonne/Meta-Llama-3-120B-Instruct](https://huggingface.co./mlabonne/Meta-Llama-3-120B-Instruct) but using Llama 3.1 70b instead of Llama 3, with the same configuration. + +## Merge Details +### Merge Method + +This model was merged using the passthrough merge method. + +### Models Merged + +The following models were included in the merge: +* [meta-llama/Llama-3.1-70B-Instruct](https://huggingface.co./meta-llama/Llama-3.1-70B-Instruct) + +### Configuration + +The following YAML configuration was used to produce this model: + +```yaml +slices: +- sources: + - layer_range: [0, 20] + model: meta-llama/Llama-3.1-70B-Instruct +- sources: + - layer_range: [10, 30] + model: meta-llama/Llama-3.1-70B-Instruct +- sources: + - layer_range: [20, 40] + model: meta-llama/Llama-3.1-70B-Instruct +- sources: + - layer_range: [30, 50] + model: meta-llama/Llama-3.1-70B-Instruct +- sources: + - layer_range: [40, 60] + model: meta-llama/Llama-3.1-70B-Instruct +- sources: + - layer_range: [50, 70] + model: meta-llama/Llama-3.1-70B-Instruct +- sources: + - layer_range: [60, 80] + model: meta-llama/Llama-3.1-70B-Instruct +merge_method: passthrough +dtype: float16 + +``` diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..1933b9dda569eba828841d0284b369ffeabc3056 --- /dev/null +++ b/config.json @@ -0,0 +1,40 @@ +{ + "_name_or_path": "meta-llama/Llama-3.1-70B-Instruct", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 8192, + "initializer_range": 0.02, + "intermediate_size": 28672, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 64, + "num_hidden_layers": 140, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.46.0", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/mergekit_config.yml b/mergekit_config.yml new file mode 100644 index 0000000000000000000000000000000000000000..6634bda5abab56c8707bd1e285ce46a66afd8cdb --- /dev/null +++ b/mergekit_config.yml @@ -0,0 +1,24 @@ +slices: +- sources: + - layer_range: [0, 20] + model: meta-llama/Llama-3.1-70B-Instruct +- sources: + - layer_range: [10, 30] + model: meta-llama/Llama-3.1-70B-Instruct +- sources: + - layer_range: [20, 40] + model: meta-llama/Llama-3.1-70B-Instruct +- sources: + - layer_range: [30, 50] + model: meta-llama/Llama-3.1-70B-Instruct +- sources: + - layer_range: [40, 60] + model: meta-llama/Llama-3.1-70B-Instruct +- sources: + - layer_range: [50, 70] + model: meta-llama/Llama-3.1-70B-Instruct +- sources: + - layer_range: [60, 80] + model: meta-llama/Llama-3.1-70B-Instruct +merge_method: passthrough +dtype: float16 diff --git a/model-00001-of-00050.safetensors b/model-00001-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1a636e758e56a072dabd74ecd0b28388642d10f1 --- /dev/null +++ b/model-00001-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d6b2b03306e00c0e70d58598d4911b587f7f7537c7e33137aed53858092bf8e +size 4672471496 diff --git a/model-00002-of-00050.safetensors b/model-00002-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..426be699f8cd9302656022f3758ad6187f9024e0 --- /dev/null +++ b/model-00002-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daf2022d1fc8804e5fd01c9dcc15a2ba9807c42d06cf5066de5505a6c5c1ca6d +size 4831922680 diff --git a/model-00003-of-00050.safetensors b/model-00003-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e301a1f949fe9eec8f525b93645f8145182245b7 --- /dev/null +++ b/model-00003-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bb14258180ae65798f4c1d09f55d793f81d8563e8831a1ea6b8ea4799848208 +size 4966190736 diff --git a/model-00004-of-00050.safetensors b/model-00004-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..59b81ae982022ff06ea0f3b6d85027a79c6c5b70 --- /dev/null +++ b/model-00004-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2264e94f6b4bffb614e6733922771b07b2537bf24f67ed5ff4fe0e7b11b5203 +size 4831906200 diff --git a/model-00005-of-00050.safetensors b/model-00005-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..641bd8904e78cb780eb81e32726f61edb3b728d7 --- /dev/null +++ b/model-00005-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:520e6206ce7e53029587bae3f2fd1bb7c6c3471635677750853186493da1f23f +size 4999711712 diff --git a/model-00006-of-00050.safetensors b/model-00006-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2e505fbaab0610f7d447b4c3af0bf8b00db698c4 --- /dev/null +++ b/model-00006-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2859ef4d85f9704d9cee7d8ff64e994b164cdaa5b56d0e110d12c9ca9522abad +size 4798385224 diff --git a/model-00007-of-00050.safetensors b/model-00007-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..56ac3e8a4c0c8c6ae18ca48410d127a723a2f78b --- /dev/null +++ b/model-00007-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:595043aa527c3c44346348e59ecf0aeb83d070ca8fa2be54e6a3551be0d76130 +size 4831906200 diff --git a/model-00008-of-00050.safetensors b/model-00008-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bceb520f09ccfda0b643e0536f4bc47c53a95f5a --- /dev/null +++ b/model-00008-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9f3551f16c072dba382dac464a5d906df452b2350e098adbf0f007265448e40 +size 4966190736 diff --git a/model-00009-of-00050.safetensors b/model-00009-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e5716e6d00dc5623b2a79191b703b8e546d3a5ab --- /dev/null +++ b/model-00009-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a49fba98efd43aa2b1ad873f12a9d9046e61b8c9606b26e54daacefb596fb0d +size 4664167384 diff --git a/model-00010-of-00050.safetensors b/model-00010-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..00aa97a45a5779439868da2dcb846e88b9e31a46 --- /dev/null +++ b/model-00010-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34884dbc8c6dcf962212f69c74f872c5797f89833fddb70b120b497ce4c3bcc3 +size 4831906200 diff --git a/model-00011-of-00050.safetensors b/model-00011-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8ab011f6b3bc852a0055074df2ae5c662e0d6e14 --- /dev/null +++ b/model-00011-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35252e9be0ce4f80e3c2d6ff8d2701be1572903d99269d87112f08aa6f3a4ff7 +size 4999711712 diff --git a/model-00012-of-00050.safetensors b/model-00012-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..121c31aa57f584de7ead8f49aa8ba03fb19c38e4 --- /dev/null +++ b/model-00012-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d30389aaf95e80ae5b1c93bcf62d499a18ce68da09ccaf1ca0a67582bff7261 +size 4798385224 diff --git a/model-00013-of-00050.safetensors b/model-00013-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3de1b9e9aa7e88e655ce753c672e41e935151ff7 --- /dev/null +++ b/model-00013-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd2e6aaa1024646476eb7c97ca032bcea82b0559b1ea7683e88b862decaa9fd3 +size 4831906200 diff --git a/model-00014-of-00050.safetensors b/model-00014-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d90836c53cfdc1d979e769f37f6d7d3990464fc4 --- /dev/null +++ b/model-00014-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d4e77a1583a7bdfc25680bc08372b58cb87c885f0264036f6c4082b5dd54af2 +size 4966190736 diff --git a/model-00015-of-00050.safetensors b/model-00015-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..96da12b22564930d48c7af67eb7b8259ed9273e2 --- /dev/null +++ b/model-00015-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76416e5634cadbaa71222241610194bc69f38c70334183b0456181421ac1efd9 +size 4831906200 diff --git a/model-00016-of-00050.safetensors b/model-00016-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8a890d4dbeb20d8ad8bac4c57da52ee408f4a6fd --- /dev/null +++ b/model-00016-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff44e489e7cc25b0f45fc91ec702df1108ed9844bbf1fe8090965b20445ba60a +size 4966174232 diff --git a/model-00017-of-00050.safetensors b/model-00017-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bc4d8ca8b325cb4113842a024c9e8230af42fb90 --- /dev/null +++ b/model-00017-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5568d1a7d9287079145ed0878780056904c1ba64c0fa7cd3a5aae6f502272681 +size 4966140544 diff --git a/model-00018-of-00050.safetensors b/model-00018-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b743618ae0e9f0bf443954e5b372ecd5479f75aa --- /dev/null +++ b/model-00018-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebdeccc43575e6a538ddae18085ea6879ff429654d07290e377de5276a7fe471 +size 4999711704 diff --git a/model-00019-of-00050.safetensors b/model-00019-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..311853fd12a89a0212582ecca69177c1b4d6d988 --- /dev/null +++ b/model-00019-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:345b97b98f0fad656d8062288dc1e6db353c60f478114d07ae394908ff84d432 +size 4999711712 diff --git a/model-00020-of-00050.safetensors b/model-00020-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eef06ec93aeac9c5a90c6a0081f72c886215b190 --- /dev/null +++ b/model-00020-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a16747f24d34d3e19b263f41a92e94e6bde4f0a7ec778e95dbfc4fa041b6ebae +size 4798385224 diff --git a/model-00021-of-00050.safetensors b/model-00021-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fa00e254300c2ca229a92e395586474b71382b96 --- /dev/null +++ b/model-00021-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4fdbdad88200c43381bfe67f589c3c70e0d59c4e0eb2b9c7ede06238f82c363 +size 4831906200 diff --git a/model-00022-of-00050.safetensors b/model-00022-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..73c1dce8300b4e1e0ab521dfabf5d5197f9f4268 --- /dev/null +++ b/model-00022-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32c8e0dfa125ecfffb762fdcda09a64097125c6987887b79517f7ba806c37a82 +size 4966190736 diff --git a/model-00023-of-00050.safetensors b/model-00023-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dcf5ca6641be7609e2181f271899c486577bcd92 --- /dev/null +++ b/model-00023-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4da4c885e4a3b4dcd0c659619be30ae37a65856aa566b6be9117ae66e4fcf32 +size 4831906200 diff --git a/model-00024-of-00050.safetensors b/model-00024-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e004f6f73037e30be25ee9a6ca8300c89ac66cf4 --- /dev/null +++ b/model-00024-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f1b0dfd73ab6865f400ec295fde62f00ff6c3ef045d922d2c34391fedb5d2b2 +size 4664167376 diff --git a/model-00025-of-00050.safetensors b/model-00025-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..43ad04ee0f50b0cf15362656472870cc798d2cb1 --- /dev/null +++ b/model-00025-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57e1c679cd658852974773b35a7f7ae14beda6096528d29e62d8a40b0f9264a1 +size 4999711712 diff --git a/model-00026-of-00050.safetensors b/model-00026-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4123d2e69dec96668f4a399f0d85daa8c4184912 --- /dev/null +++ b/model-00026-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3240e649c292d905f0698ca896f1dfac4844a9e48c0d2474a3dfe9d0d2412bbe +size 4798385224 diff --git a/model-00027-of-00050.safetensors b/model-00027-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4f86f8e8ca478be828df1e1be759edb87688e1ee --- /dev/null +++ b/model-00027-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff438d7da66ed3049d08ed6c501e011dbfbbf1f57085903f42ed4d875dbbda3e +size 4831906200 diff --git a/model-00028-of-00050.safetensors b/model-00028-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ff62066033afa5bfb2fd1e6655ea1851d6c73cef --- /dev/null +++ b/model-00028-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ac89613cd93016b780dbff0290bbbc614e9f7610e42f238e37420661631bae2 +size 4966190736 diff --git a/model-00029-of-00050.safetensors b/model-00029-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..93927f29114901fc77d0cf7001fac451592b4ce2 --- /dev/null +++ b/model-00029-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0dbd77d2ee348362ac012aba2eef2a0fd54b256ffb40ccf9e6d6d9146cab0d2 +size 4831906200 diff --git a/model-00030-of-00050.safetensors b/model-00030-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8c31793613be24c827b0206d48e51ba5080a15a0 --- /dev/null +++ b/model-00030-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:715f6e63ffca34def2a8e271c7fa6d30345fd99147c86991f7d9249b95849803 +size 4966190736 diff --git a/model-00031-of-00050.safetensors b/model-00031-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..98887f7289983e736b63832473258fbbbb6b784f --- /dev/null +++ b/model-00031-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:168bab91302186fc04b8e87ae389f5ee6e63cb220cfb273b1b2873c90fcab20b +size 4982901368 diff --git a/model-00032-of-00050.safetensors b/model-00032-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e032e406047c04889b1cf1ff843ad1db7a649fa4 --- /dev/null +++ b/model-00032-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3db5ed93d9902bef4b3c5014433ff8258f3aa2f5a5619b42dedb8814f4474a8 +size 4982934368 diff --git a/model-00033-of-00050.safetensors b/model-00033-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..be5c22f45a611bea18b23ea2126b0d541f667a78 --- /dev/null +++ b/model-00033-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f548efaa6c8fc1ad7e54e010e88d166f2a0555062cfe8bd7ea4d972d277c3301 +size 4999711720 diff --git a/model-00034-of-00050.safetensors b/model-00034-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..88984c3e4f7ec7c37e5a3377455792491d812c79 --- /dev/null +++ b/model-00034-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62475c0bac2a8fd6f7ec6bdf8eb9655857c88f06183384beca3297031c5b5366 +size 4798385240 diff --git a/model-00035-of-00050.safetensors b/model-00035-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ab62454267028ae2ec0a8f81eaa2f0c9e613e40a --- /dev/null +++ b/model-00035-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4b73824be4668f7487d5eb249445dd30450e05e083dced0687b8734078bfb91 +size 4831906208 diff --git a/model-00036-of-00050.safetensors b/model-00036-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c2ee8a245004f1383fecab00f340f2021f8b8ea8 --- /dev/null +++ b/model-00036-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fef95f1be960bf78af29cf1aeb5dad16fdb62813ebf2b75ced025c0d46ea8f1 +size 4966190744 diff --git a/model-00037-of-00050.safetensors b/model-00037-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a58dfb6f54906ad9a1963d0236ea4ce75d223a3c --- /dev/null +++ b/model-00037-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72a9a30521d09c8f5e417621b08e89d266075382743c047d418951b9594eeb82 +size 4831906208 diff --git a/model-00038-of-00050.safetensors b/model-00038-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d5e34024175992277c2b756d9ef1937a41765354 --- /dev/null +++ b/model-00038-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56b3568aafcb4a3d302619ca3f2f8ad6b32dada5c637a666c1aa577b04e58fe1 +size 4966174256 diff --git a/model-00039-of-00050.safetensors b/model-00039-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..201d7861e0484ea87e5275634cc228a1b984ab01 --- /dev/null +++ b/model-00039-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a81a33c36ee2a2553537fea5714b020061a5b1e5f0201a6c4e622adef8d484a8 +size 4966140544 diff --git a/model-00040-of-00050.safetensors b/model-00040-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1f177e2aff42fb96a2a12cbe19be3705c13f40c1 --- /dev/null +++ b/model-00040-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b86c3ebdee6c199c413afed34e453399bec1befde451f9568933e166d56e3a54 +size 4999711728 diff --git a/model-00041-of-00050.safetensors b/model-00041-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6bf7c8a3fd5e55ea5d53e43fe12e0379864f4ddc --- /dev/null +++ b/model-00041-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe048112581f18ab2b711f986330edcc00f4f90ce5ca870e187aab437b1a689c +size 4999711744 diff --git a/model-00042-of-00050.safetensors b/model-00042-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8f1c430f31f918a32b8096cef770e7f6e7c653cc --- /dev/null +++ b/model-00042-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a907a87e173ab30cb6d7856626e210f23f01eac564bd4696d274abf9dac60f8e +size 4798385256 diff --git a/model-00043-of-00050.safetensors b/model-00043-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d71ec9ced3a2b0e769f6706f0571af2a9fc7a387 --- /dev/null +++ b/model-00043-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ec7ccb8b8564bab41b16cb34808c73d331c5759a640d0102cd5416fe25d66f8 +size 4831906216 diff --git a/model-00044-of-00050.safetensors b/model-00044-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b635537682cfc731879b2f0062bb5c5212aefa59 --- /dev/null +++ b/model-00044-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2eadae2b8bf98f2c17505931c54bbaab78530eadf17ffff588ab125992b2b2b3 +size 4966190768 diff --git a/model-00045-of-00050.safetensors b/model-00045-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f8344f6f8735ce144fde35e402096781221afc8a --- /dev/null +++ b/model-00045-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d132c7cb3612a6ade0c2e3406d1bbb18d277df83a00ee4023249899ac86db6c +size 4831906224 diff --git a/model-00046-of-00050.safetensors b/model-00046-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e2716cc0b2c28c6066b2bbead949804d361cf205 --- /dev/null +++ b/model-00046-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:685b0145bd48929b1dacdae3e7c807541ec003e81bd10c55152806939d1b28ea +size 4966174256 diff --git a/model-00047-of-00050.safetensors b/model-00047-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..997ec84f8ad15aa067f3c69f0d57bcc14abc2ea8 --- /dev/null +++ b/model-00047-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae6ad4c459fbb1f7ea870a9ffa037f0b740833efb5e6868830552eac770437b7 +size 4982917904 diff --git a/model-00048-of-00050.safetensors b/model-00048-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..123c338d536e179b49f0366b2a48d86543b2007b --- /dev/null +++ b/model-00048-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd2ffe35b77fa8f8c292f144034b5948b482186fafc7cf2c22af4e99fc938897 +size 4999711736 diff --git a/model-00049-of-00050.safetensors b/model-00049-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..810c4b7bc32c124cd49ddcaa437650a58ae41081 --- /dev/null +++ b/model-00049-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe6c231c39d2bd668683a0045613aaf5b5e28b2acb35a47278262674747e3b1d +size 4647373576 diff --git a/model-00050-of-00050.safetensors b/model-00050-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..988257651f1cf59071f35a993434b8ac7368cf2b --- /dev/null +++ b/model-00050-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89ff1df4ebe509fe6f2eac64dc012c6f192fdb4d5e362ea614013f1479efd3c5 +size 4194405184 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..4046f472067e9b2571aa13cfe09807fad9460e40 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1 @@ +{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 243785940992}, "weight_map": {"lm_head.weight": "model-00001-of-00050.safetensors", "model.embed_tokens.weight": "model-00001-of-00050.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00050.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00050.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00050.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00050.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00050.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00050.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00050.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00050.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00050.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00050.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00050.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00050.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00050.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00050.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00050.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00050.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00050.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00050.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00050.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00050.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00050.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00050.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00050.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00050.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00050.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00050.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00050.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00050.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00050.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00050.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00050.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00050.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00050.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00050.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00050.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00050.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00050.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00050.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00050.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00050.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00050.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00050.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00050.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00050.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00050.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00050.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00050.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00050.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00050.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00050.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00050.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00050.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00050.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00050.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00050.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00050.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00050.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00050.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00050.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00050.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00050.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00050.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00050.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00050.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00050.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00050.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00050.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00050.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00050.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00050.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00050.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00050.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00050.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00050.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00050.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00050.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00050.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00050.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00050.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00050.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00050.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00050.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00050.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00050.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00050.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00050.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00050.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00050.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00050.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00050.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00050.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00050.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00006-of-00050.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00050.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00050.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00050.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00050.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00007-of-00050.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00050.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00050.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00050.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00050.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00050.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00050.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00050.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00050.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00050.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00050.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00050.safetensors", "model.layers.17.input_layernorm.weight": "model-00007-of-00050.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00050.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00050.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00050.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00050.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00050.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00008-of-00050.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00050.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00050.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00050.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00050.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00050.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00050.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00050.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00050.safetensors", "model.layers.28.input_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00008-of-00050.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00008-of-00050.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00050.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00050.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00008-of-00050.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00008-of-00050.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00050.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00050.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00050.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00050.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00050.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00050.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00050.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00050.safetensors", "model.layers.29.input_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.19.input_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00008-of-00050.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00009-of-00050.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00050.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00050.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00009-of-00050.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00009-of-00050.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00050.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00050.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00050.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00050.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00050.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00050.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00050.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00050.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00050.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.input_layernorm.weight": "model-00009-of-00050.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00009-of-00050.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00009-of-00050.safetensors", "model.layers.40.input_layernorm.weight": "model-00009-of-00050.safetensors", "model.layers.30.input_layernorm.weight": "model-00009-of-00050.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00010-of-00050.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00010-of-00050.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00050.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00050.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00010-of-00050.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00010-of-00050.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00050.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00050.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00010-of-00050.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00050.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00010-of-00050.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00050.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00010-of-00050.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00050.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00010-of-00050.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00050.safetensors", "model.layers.41.input_layernorm.weight": "model-00010-of-00050.safetensors", "model.layers.31.input_layernorm.weight": "model-00010-of-00050.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00010-of-00050.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00010-of-00050.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00050.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00050.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00011-of-00050.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00050.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00011-of-00050.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00050.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00011-of-00050.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00050.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00011-of-00050.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00050.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00011-of-00050.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00050.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00011-of-00050.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00050.safetensors", "model.layers.42.input_layernorm.weight": "model-00011-of-00050.safetensors", "model.layers.32.input_layernorm.weight": "model-00011-of-00050.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00011-of-00050.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00011-of-00050.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00011-of-00050.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00050.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00011-of-00050.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00011-of-00050.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00011-of-00050.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00050.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00011-of-00050.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00050.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00011-of-00050.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00050.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00012-of-00050.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00050.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00012-of-00050.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00050.safetensors", "model.layers.43.input_layernorm.weight": "model-00012-of-00050.safetensors", "model.layers.33.input_layernorm.weight": "model-00012-of-00050.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00012-of-00050.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00012-of-00050.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00012-of-00050.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00012-of-00050.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00012-of-00050.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00012-of-00050.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00012-of-00050.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00050.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00012-of-00050.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00050.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00012-of-00050.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00050.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00012-of-00050.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00050.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00012-of-00050.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00050.safetensors", "model.layers.44.input_layernorm.weight": "model-00012-of-00050.safetensors", "model.layers.34.input_layernorm.weight": "model-00012-of-00050.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00012-of-00050.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00012-of-00050.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00013-of-00050.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00013-of-00050.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00013-of-00050.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00013-of-00050.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00013-of-00050.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00013-of-00050.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00013-of-00050.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00050.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00013-of-00050.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00050.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00013-of-00050.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00050.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00013-of-00050.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00050.safetensors", "model.layers.45.input_layernorm.weight": "model-00013-of-00050.safetensors", "model.layers.35.input_layernorm.weight": "model-00013-of-00050.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00013-of-00050.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00013-of-00050.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00013-of-00050.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00013-of-00050.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00013-of-00050.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00014-of-00050.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00014-of-00050.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00014-of-00050.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00014-of-00050.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00050.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00014-of-00050.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00014-of-00050.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00014-of-00050.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00014-of-00050.safetensors", "model.layers.46.input_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.36.input_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00014-of-00050.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00014-of-00050.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00014-of-00050.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00050.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00014-of-00050.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00014-of-00050.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00014-of-00050.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00014-of-00050.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00014-of-00050.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00014-of-00050.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00014-of-00050.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00014-of-00050.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00014-of-00050.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00014-of-00050.safetensors", "model.layers.47.input_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.37.input_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00014-of-00050.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00015-of-00050.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00015-of-00050.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00015-of-00050.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00015-of-00050.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00015-of-00050.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00015-of-00050.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00015-of-00050.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00015-of-00050.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00015-of-00050.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00015-of-00050.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00015-of-00050.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00015-of-00050.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00015-of-00050.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00015-of-00050.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00015-of-00050.safetensors", "model.layers.48.input_layernorm.weight": "model-00015-of-00050.safetensors", "model.layers.38.input_layernorm.weight": "model-00015-of-00050.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00015-of-00050.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00015-of-00050.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00015-of-00050.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00015-of-00050.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00016-of-00050.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00016-of-00050.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00016-of-00050.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00016-of-00050.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00016-of-00050.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00016-of-00050.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00016-of-00050.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00016-of-00050.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00016-of-00050.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00016-of-00050.safetensors", "model.layers.49.input_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.39.input_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00016-of-00050.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00016-of-00050.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00016-of-00050.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00016-of-00050.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00016-of-00050.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00016-of-00050.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00016-of-00050.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00016-of-00050.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00016-of-00050.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00016-of-00050.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00016-of-00050.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00016-of-00050.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00016-of-00050.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00016-of-00050.safetensors", "model.layers.3.input_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00017-of-00050.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00017-of-00050.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00017-of-00050.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00017-of-00050.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00017-of-00050.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00017-of-00050.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00017-of-00050.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00017-of-00050.safetensors", "model.layers.60.input_layernorm.weight": "model-00017-of-00050.safetensors", "model.layers.50.input_layernorm.weight": "model-00017-of-00050.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00017-of-00050.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00017-of-00050.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00017-of-00050.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00017-of-00050.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00017-of-00050.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00017-of-00050.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00017-of-00050.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00017-of-00050.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00017-of-00050.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00017-of-00050.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00017-of-00050.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00017-of-00050.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00017-of-00050.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00018-of-00050.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00018-of-00050.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00018-of-00050.safetensors", "model.layers.61.input_layernorm.weight": "model-00018-of-00050.safetensors", "model.layers.51.input_layernorm.weight": "model-00018-of-00050.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00018-of-00050.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00018-of-00050.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00018-of-00050.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00018-of-00050.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00018-of-00050.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00018-of-00050.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00018-of-00050.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00018-of-00050.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00018-of-00050.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00018-of-00050.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00018-of-00050.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00018-of-00050.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00018-of-00050.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00018-of-00050.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00018-of-00050.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00018-of-00050.safetensors", "model.layers.62.input_layernorm.weight": "model-00018-of-00050.safetensors", "model.layers.52.input_layernorm.weight": "model-00018-of-00050.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00018-of-00050.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00018-of-00050.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00018-of-00050.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00019-of-00050.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00019-of-00050.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00019-of-00050.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00019-of-00050.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00019-of-00050.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00019-of-00050.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00019-of-00050.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00019-of-00050.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00019-of-00050.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00019-of-00050.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00019-of-00050.safetensors", "model.layers.63.input_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.53.input_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00019-of-00050.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00019-of-00050.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00019-of-00050.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00019-of-00050.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00019-of-00050.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00019-of-00050.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00019-of-00050.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00019-of-00050.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00019-of-00050.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00050.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00020-of-00050.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00050.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00020-of-00050.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.input_layernorm.weight": "model-00020-of-00050.safetensors", "model.layers.54.input_layernorm.weight": "model-00020-of-00050.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00020-of-00050.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00020-of-00050.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00020-of-00050.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00020-of-00050.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00020-of-00050.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00020-of-00050.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00020-of-00050.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00020-of-00050.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00020-of-00050.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00050.safetensors", "model.layers.65.input_layernorm.weight": "model-00020-of-00050.safetensors", "model.layers.55.input_layernorm.weight": "model-00020-of-00050.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00020-of-00050.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00020-of-00050.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00021-of-00050.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00021-of-00050.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00021-of-00050.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00021-of-00050.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00021-of-00050.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00021-of-00050.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00021-of-00050.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00021-of-00050.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00021-of-00050.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00021-of-00050.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00021-of-00050.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00021-of-00050.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00021-of-00050.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00021-of-00050.safetensors", "model.layers.66.input_layernorm.weight": "model-00021-of-00050.safetensors", "model.layers.56.input_layernorm.weight": "model-00021-of-00050.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00021-of-00050.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00021-of-00050.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00021-of-00050.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00050.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00021-of-00050.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00022-of-00050.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00022-of-00050.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00022-of-00050.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00022-of-00050.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00022-of-00050.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00022-of-00050.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00022-of-00050.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00022-of-00050.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.input_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.57.input_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00022-of-00050.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00022-of-00050.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00022-of-00050.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00022-of-00050.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00022-of-00050.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00022-of-00050.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00022-of-00050.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00022-of-00050.safetensors", "model.layers.68.input_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.58.input_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00022-of-00050.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00023-of-00050.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00023-of-00050.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00023-of-00050.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00023-of-00050.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00023-of-00050.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00023-of-00050.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00023-of-00050.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00023-of-00050.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00023-of-00050.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00023-of-00050.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00023-of-00050.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00023-of-00050.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00023-of-00050.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00023-of-00050.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00023-of-00050.safetensors", "model.layers.69.input_layernorm.weight": "model-00023-of-00050.safetensors", "model.layers.59.input_layernorm.weight": "model-00023-of-00050.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00023-of-00050.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00023-of-00050.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00023-of-00050.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00023-of-00050.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00024-of-00050.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00024-of-00050.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00024-of-00050.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00024-of-00050.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00024-of-00050.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00024-of-00050.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00024-of-00050.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00024-of-00050.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00024-of-00050.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00024-of-00050.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00024-of-00050.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00024-of-00050.safetensors", "model.layers.4.input_layernorm.weight": "model-00024-of-00050.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00024-of-00050.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00024-of-00050.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00024-of-00050.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00024-of-00050.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00024-of-00050.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00024-of-00050.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00024-of-00050.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00024-of-00050.safetensors", "model.layers.80.input_layernorm.weight": "model-00024-of-00050.safetensors", "model.layers.70.input_layernorm.weight": "model-00024-of-00050.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00024-of-00050.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00024-of-00050.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00024-of-00050.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00025-of-00050.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00025-of-00050.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00025-of-00050.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00025-of-00050.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00025-of-00050.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00025-of-00050.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00025-of-00050.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00025-of-00050.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00025-of-00050.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00025-of-00050.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00025-of-00050.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00025-of-00050.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00025-of-00050.safetensors", "model.layers.81.input_layernorm.weight": "model-00025-of-00050.safetensors", "model.layers.71.input_layernorm.weight": "model-00025-of-00050.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00025-of-00050.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00025-of-00050.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00025-of-00050.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00025-of-00050.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00025-of-00050.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00025-of-00050.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00025-of-00050.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00025-of-00050.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00025-of-00050.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00025-of-00050.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00025-of-00050.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00026-of-00050.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00026-of-00050.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00026-of-00050.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00026-of-00050.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00026-of-00050.safetensors", "model.layers.82.input_layernorm.weight": "model-00026-of-00050.safetensors", "model.layers.72.input_layernorm.weight": "model-00026-of-00050.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00026-of-00050.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00026-of-00050.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00026-of-00050.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00026-of-00050.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00026-of-00050.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00026-of-00050.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00026-of-00050.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00026-of-00050.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00026-of-00050.safetensors", "model.layers.83.input_layernorm.weight": "model-00026-of-00050.safetensors", "model.layers.73.input_layernorm.weight": "model-00026-of-00050.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00026-of-00050.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00026-of-00050.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00027-of-00050.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00050.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00027-of-00050.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00027-of-00050.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00027-of-00050.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00027-of-00050.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00027-of-00050.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00027-of-00050.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00027-of-00050.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00027-of-00050.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00027-of-00050.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00027-of-00050.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00027-of-00050.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00027-of-00050.safetensors", "model.layers.84.input_layernorm.weight": "model-00027-of-00050.safetensors", "model.layers.74.input_layernorm.weight": "model-00027-of-00050.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00027-of-00050.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00027-of-00050.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00027-of-00050.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00027-of-00050.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00027-of-00050.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00028-of-00050.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00028-of-00050.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00028-of-00050.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00028-of-00050.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00028-of-00050.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00028-of-00050.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00028-of-00050.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00028-of-00050.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00028-of-00050.safetensors", "model.layers.85.input_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.75.input_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00028-of-00050.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00050.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00028-of-00050.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00050.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00050.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00050.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00050.safetensors", "model.layers.86.input_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.76.input_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00028-of-00050.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00029-of-00050.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00029-of-00050.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00029-of-00050.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00029-of-00050.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00029-of-00050.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00029-of-00050.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00029-of-00050.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00029-of-00050.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00029-of-00050.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00029-of-00050.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00029-of-00050.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00029-of-00050.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00029-of-00050.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00029-of-00050.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00029-of-00050.safetensors", "model.layers.87.input_layernorm.weight": "model-00029-of-00050.safetensors", "model.layers.77.input_layernorm.weight": "model-00029-of-00050.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00029-of-00050.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00029-of-00050.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00029-of-00050.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00029-of-00050.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00030-of-00050.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00030-of-00050.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00030-of-00050.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00030-of-00050.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00030-of-00050.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00030-of-00050.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00030-of-00050.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00030-of-00050.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00030-of-00050.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00030-of-00050.safetensors", "model.layers.88.input_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.78.input_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00030-of-00050.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00030-of-00050.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00030-of-00050.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00030-of-00050.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00030-of-00050.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00030-of-00050.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00030-of-00050.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00030-of-00050.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00030-of-00050.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00030-of-00050.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00030-of-00050.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00030-of-00050.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00030-of-00050.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00030-of-00050.safetensors", "model.layers.89.input_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.79.input_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00031-of-00050.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00031-of-00050.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00031-of-00050.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00031-of-00050.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00031-of-00050.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00031-of-00050.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00031-of-00050.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00031-of-00050.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00031-of-00050.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00031-of-00050.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00031-of-00050.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00031-of-00050.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00031-of-00050.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00031-of-00050.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00031-of-00050.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00031-of-00050.safetensors", "model.layers.5.input_layernorm.weight": "model-00031-of-00050.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00031-of-00050.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00031-of-00050.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00031-of-00050.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00031-of-00050.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00031-of-00050.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00031-of-00050.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00032-of-00050.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00032-of-00050.safetensors", "model.layers.100.input_layernorm.weight": "model-00032-of-00050.safetensors", "model.layers.90.input_layernorm.weight": "model-00032-of-00050.safetensors", "model.layers.100.mlp.down_proj.weight": "model-00032-of-00050.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00032-of-00050.safetensors", "model.layers.100.mlp.gate_proj.weight": "model-00032-of-00050.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00032-of-00050.safetensors", "model.layers.100.mlp.up_proj.weight": "model-00032-of-00050.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00032-of-00050.safetensors", "model.layers.100.post_attention_layernorm.weight": "model-00032-of-00050.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00032-of-00050.safetensors", "model.layers.100.self_attn.k_proj.weight": "model-00032-of-00050.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00032-of-00050.safetensors", "model.layers.100.self_attn.o_proj.weight": "model-00032-of-00050.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00032-of-00050.safetensors", "model.layers.100.self_attn.q_proj.weight": "model-00032-of-00050.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00032-of-00050.safetensors", "model.layers.100.self_attn.v_proj.weight": "model-00032-of-00050.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00032-of-00050.safetensors", "model.layers.101.input_layernorm.weight": "model-00032-of-00050.safetensors", "model.layers.91.input_layernorm.weight": "model-00032-of-00050.safetensors", "model.layers.101.mlp.down_proj.weight": "model-00032-of-00050.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00032-of-00050.safetensors", "model.layers.101.mlp.gate_proj.weight": "model-00032-of-00050.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00033-of-00050.safetensors", "model.layers.101.mlp.up_proj.weight": "model-00033-of-00050.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00033-of-00050.safetensors", "model.layers.101.post_attention_layernorm.weight": "model-00033-of-00050.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00033-of-00050.safetensors", "model.layers.101.self_attn.k_proj.weight": "model-00033-of-00050.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00033-of-00050.safetensors", "model.layers.101.self_attn.o_proj.weight": "model-00033-of-00050.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00033-of-00050.safetensors", "model.layers.101.self_attn.q_proj.weight": "model-00033-of-00050.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00033-of-00050.safetensors", "model.layers.101.self_attn.v_proj.weight": "model-00033-of-00050.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00033-of-00050.safetensors", "model.layers.102.input_layernorm.weight": "model-00033-of-00050.safetensors", "model.layers.92.input_layernorm.weight": "model-00033-of-00050.safetensors", "model.layers.102.mlp.down_proj.weight": "model-00033-of-00050.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00033-of-00050.safetensors", "model.layers.102.mlp.gate_proj.weight": "model-00033-of-00050.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00033-of-00050.safetensors", "model.layers.102.mlp.up_proj.weight": "model-00033-of-00050.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00033-of-00050.safetensors", "model.layers.102.post_attention_layernorm.weight": "model-00033-of-00050.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00033-of-00050.safetensors", "model.layers.102.self_attn.k_proj.weight": "model-00033-of-00050.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00033-of-00050.safetensors", "model.layers.102.self_attn.o_proj.weight": "model-00033-of-00050.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00034-of-00050.safetensors", "model.layers.102.self_attn.q_proj.weight": "model-00034-of-00050.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00034-of-00050.safetensors", "model.layers.102.self_attn.v_proj.weight": "model-00034-of-00050.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00034-of-00050.safetensors", "model.layers.103.input_layernorm.weight": "model-00034-of-00050.safetensors", "model.layers.93.input_layernorm.weight": "model-00034-of-00050.safetensors", "model.layers.103.mlp.down_proj.weight": "model-00034-of-00050.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00034-of-00050.safetensors", "model.layers.103.mlp.gate_proj.weight": "model-00034-of-00050.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00034-of-00050.safetensors", "model.layers.103.mlp.up_proj.weight": "model-00034-of-00050.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00034-of-00050.safetensors", "model.layers.103.post_attention_layernorm.weight": "model-00034-of-00050.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00034-of-00050.safetensors", "model.layers.103.self_attn.k_proj.weight": "model-00034-of-00050.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00034-of-00050.safetensors", "model.layers.103.self_attn.o_proj.weight": "model-00034-of-00050.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00034-of-00050.safetensors", "model.layers.103.self_attn.q_proj.weight": "model-00034-of-00050.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00034-of-00050.safetensors", "model.layers.103.self_attn.v_proj.weight": "model-00034-of-00050.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00034-of-00050.safetensors", "model.layers.104.input_layernorm.weight": "model-00034-of-00050.safetensors", "model.layers.94.input_layernorm.weight": "model-00034-of-00050.safetensors", "model.layers.104.mlp.down_proj.weight": "model-00034-of-00050.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00034-of-00050.safetensors", "model.layers.104.mlp.gate_proj.weight": "model-00035-of-00050.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00035-of-00050.safetensors", "model.layers.104.mlp.up_proj.weight": "model-00035-of-00050.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00035-of-00050.safetensors", "model.layers.104.post_attention_layernorm.weight": "model-00035-of-00050.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00035-of-00050.safetensors", "model.layers.104.self_attn.k_proj.weight": "model-00035-of-00050.safetensors", "model.layers.94.self_attn.k_proj.weight": "model-00035-of-00050.safetensors", "model.layers.104.self_attn.o_proj.weight": "model-00035-of-00050.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00035-of-00050.safetensors", "model.layers.104.self_attn.q_proj.weight": "model-00035-of-00050.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00035-of-00050.safetensors", "model.layers.104.self_attn.v_proj.weight": "model-00035-of-00050.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00035-of-00050.safetensors", "model.layers.105.input_layernorm.weight": "model-00035-of-00050.safetensors", "model.layers.95.input_layernorm.weight": "model-00035-of-00050.safetensors", "model.layers.105.mlp.down_proj.weight": "model-00035-of-00050.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00035-of-00050.safetensors", "model.layers.105.mlp.gate_proj.weight": "model-00035-of-00050.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00035-of-00050.safetensors", "model.layers.105.mlp.up_proj.weight": "model-00035-of-00050.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00036-of-00050.safetensors", "model.layers.105.post_attention_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.105.self_attn.k_proj.weight": "model-00036-of-00050.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00036-of-00050.safetensors", "model.layers.105.self_attn.o_proj.weight": "model-00036-of-00050.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00036-of-00050.safetensors", "model.layers.105.self_attn.q_proj.weight": "model-00036-of-00050.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00036-of-00050.safetensors", "model.layers.105.self_attn.v_proj.weight": "model-00036-of-00050.safetensors", "model.layers.95.self_attn.v_proj.weight": "model-00036-of-00050.safetensors", "model.layers.106.input_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.96.input_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.106.mlp.down_proj.weight": "model-00036-of-00050.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00036-of-00050.safetensors", "model.layers.106.mlp.gate_proj.weight": "model-00036-of-00050.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00036-of-00050.safetensors", "model.layers.106.mlp.up_proj.weight": "model-00036-of-00050.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00036-of-00050.safetensors", "model.layers.106.post_attention_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.106.self_attn.k_proj.weight": "model-00036-of-00050.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00036-of-00050.safetensors", "model.layers.106.self_attn.o_proj.weight": "model-00036-of-00050.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00036-of-00050.safetensors", "model.layers.106.self_attn.q_proj.weight": "model-00036-of-00050.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00036-of-00050.safetensors", "model.layers.106.self_attn.v_proj.weight": "model-00036-of-00050.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00036-of-00050.safetensors", "model.layers.107.input_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.97.input_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.107.mlp.down_proj.weight": "model-00036-of-00050.safetensors", "model.layers.97.mlp.down_proj.weight": "model-00037-of-00050.safetensors", "model.layers.107.mlp.gate_proj.weight": "model-00037-of-00050.safetensors", "model.layers.97.mlp.gate_proj.weight": "model-00037-of-00050.safetensors", "model.layers.107.mlp.up_proj.weight": "model-00037-of-00050.safetensors", "model.layers.97.mlp.up_proj.weight": "model-00037-of-00050.safetensors", "model.layers.107.post_attention_layernorm.weight": "model-00037-of-00050.safetensors", "model.layers.97.post_attention_layernorm.weight": "model-00037-of-00050.safetensors", "model.layers.107.self_attn.k_proj.weight": "model-00037-of-00050.safetensors", "model.layers.97.self_attn.k_proj.weight": "model-00037-of-00050.safetensors", "model.layers.107.self_attn.o_proj.weight": "model-00037-of-00050.safetensors", "model.layers.97.self_attn.o_proj.weight": "model-00037-of-00050.safetensors", "model.layers.107.self_attn.q_proj.weight": "model-00037-of-00050.safetensors", "model.layers.97.self_attn.q_proj.weight": "model-00037-of-00050.safetensors", "model.layers.107.self_attn.v_proj.weight": "model-00037-of-00050.safetensors", "model.layers.97.self_attn.v_proj.weight": "model-00037-of-00050.safetensors", "model.layers.108.input_layernorm.weight": "model-00037-of-00050.safetensors", "model.layers.98.input_layernorm.weight": "model-00037-of-00050.safetensors", "model.layers.108.mlp.down_proj.weight": "model-00037-of-00050.safetensors", "model.layers.98.mlp.down_proj.weight": "model-00037-of-00050.safetensors", "model.layers.108.mlp.gate_proj.weight": "model-00037-of-00050.safetensors", "model.layers.98.mlp.gate_proj.weight": "model-00037-of-00050.safetensors", "model.layers.108.mlp.up_proj.weight": "model-00038-of-00050.safetensors", "model.layers.98.mlp.up_proj.weight": "model-00038-of-00050.safetensors", "model.layers.108.post_attention_layernorm.weight": "model-00038-of-00050.safetensors", "model.layers.98.post_attention_layernorm.weight": "model-00038-of-00050.safetensors", "model.layers.108.self_attn.k_proj.weight": "model-00038-of-00050.safetensors", "model.layers.98.self_attn.k_proj.weight": "model-00038-of-00050.safetensors", "model.layers.108.self_attn.o_proj.weight": "model-00038-of-00050.safetensors", "model.layers.98.self_attn.o_proj.weight": "model-00038-of-00050.safetensors", "model.layers.108.self_attn.q_proj.weight": "model-00038-of-00050.safetensors", "model.layers.98.self_attn.q_proj.weight": "model-00038-of-00050.safetensors", "model.layers.108.self_attn.v_proj.weight": "model-00038-of-00050.safetensors", "model.layers.98.self_attn.v_proj.weight": "model-00038-of-00050.safetensors", "model.layers.109.input_layernorm.weight": "model-00038-of-00050.safetensors", "model.layers.99.input_layernorm.weight": "model-00038-of-00050.safetensors", "model.layers.109.mlp.down_proj.weight": "model-00038-of-00050.safetensors", "model.layers.99.mlp.down_proj.weight": "model-00038-of-00050.safetensors", "model.layers.109.mlp.gate_proj.weight": "model-00038-of-00050.safetensors", "model.layers.99.mlp.gate_proj.weight": "model-00038-of-00050.safetensors", "model.layers.109.mlp.up_proj.weight": "model-00038-of-00050.safetensors", "model.layers.99.mlp.up_proj.weight": "model-00038-of-00050.safetensors", "model.layers.109.post_attention_layernorm.weight": "model-00038-of-00050.safetensors", "model.layers.99.post_attention_layernorm.weight": "model-00038-of-00050.safetensors", "model.layers.109.self_attn.k_proj.weight": "model-00038-of-00050.safetensors", "model.layers.99.self_attn.k_proj.weight": "model-00038-of-00050.safetensors", "model.layers.109.self_attn.o_proj.weight": "model-00038-of-00050.safetensors", "model.layers.99.self_attn.o_proj.weight": "model-00038-of-00050.safetensors", "model.layers.109.self_attn.q_proj.weight": "model-00038-of-00050.safetensors", "model.layers.99.self_attn.q_proj.weight": "model-00038-of-00050.safetensors", "model.layers.109.self_attn.v_proj.weight": "model-00038-of-00050.safetensors", "model.layers.99.self_attn.v_proj.weight": "model-00038-of-00050.safetensors", "model.layers.6.input_layernorm.weight": "model-00038-of-00050.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00039-of-00050.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00039-of-00050.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00039-of-00050.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00039-of-00050.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00039-of-00050.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00039-of-00050.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00039-of-00050.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00039-of-00050.safetensors", "model.layers.120.input_layernorm.weight": "model-00039-of-00050.safetensors", "model.layers.110.input_layernorm.weight": "model-00039-of-00050.safetensors", "model.layers.120.mlp.down_proj.weight": "model-00039-of-00050.safetensors", "model.layers.110.mlp.down_proj.weight": "model-00039-of-00050.safetensors", "model.layers.120.mlp.gate_proj.weight": "model-00039-of-00050.safetensors", "model.layers.110.mlp.gate_proj.weight": "model-00039-of-00050.safetensors", "model.layers.120.mlp.up_proj.weight": "model-00039-of-00050.safetensors", "model.layers.110.mlp.up_proj.weight": "model-00039-of-00050.safetensors", "model.layers.120.post_attention_layernorm.weight": "model-00039-of-00050.safetensors", "model.layers.110.post_attention_layernorm.weight": "model-00039-of-00050.safetensors", "model.layers.120.self_attn.k_proj.weight": "model-00039-of-00050.safetensors", "model.layers.110.self_attn.k_proj.weight": "model-00039-of-00050.safetensors", "model.layers.120.self_attn.o_proj.weight": "model-00039-of-00050.safetensors", "model.layers.110.self_attn.o_proj.weight": "model-00039-of-00050.safetensors", "model.layers.120.self_attn.q_proj.weight": "model-00039-of-00050.safetensors", "model.layers.110.self_attn.q_proj.weight": "model-00040-of-00050.safetensors", "model.layers.120.self_attn.v_proj.weight": "model-00040-of-00050.safetensors", "model.layers.110.self_attn.v_proj.weight": "model-00040-of-00050.safetensors", "model.layers.121.input_layernorm.weight": "model-00040-of-00050.safetensors", "model.layers.111.input_layernorm.weight": "model-00040-of-00050.safetensors", "model.layers.121.mlp.down_proj.weight": "model-00040-of-00050.safetensors", "model.layers.111.mlp.down_proj.weight": "model-00040-of-00050.safetensors", "model.layers.121.mlp.gate_proj.weight": "model-00040-of-00050.safetensors", "model.layers.111.mlp.gate_proj.weight": "model-00040-of-00050.safetensors", "model.layers.121.mlp.up_proj.weight": "model-00040-of-00050.safetensors", "model.layers.111.mlp.up_proj.weight": "model-00040-of-00050.safetensors", "model.layers.121.post_attention_layernorm.weight": "model-00040-of-00050.safetensors", "model.layers.111.post_attention_layernorm.weight": "model-00040-of-00050.safetensors", "model.layers.121.self_attn.k_proj.weight": "model-00040-of-00050.safetensors", "model.layers.111.self_attn.k_proj.weight": "model-00040-of-00050.safetensors", "model.layers.121.self_attn.o_proj.weight": "model-00040-of-00050.safetensors", "model.layers.111.self_attn.o_proj.weight": "model-00040-of-00050.safetensors", "model.layers.121.self_attn.q_proj.weight": "model-00040-of-00050.safetensors", "model.layers.111.self_attn.q_proj.weight": "model-00040-of-00050.safetensors", "model.layers.121.self_attn.v_proj.weight": "model-00040-of-00050.safetensors", "model.layers.111.self_attn.v_proj.weight": "model-00040-of-00050.safetensors", "model.layers.122.input_layernorm.weight": "model-00040-of-00050.safetensors", "model.layers.112.input_layernorm.weight": "model-00040-of-00050.safetensors", "model.layers.122.mlp.down_proj.weight": "model-00040-of-00050.safetensors", "model.layers.112.mlp.down_proj.weight": "model-00040-of-00050.safetensors", "model.layers.122.mlp.gate_proj.weight": "model-00040-of-00050.safetensors", "model.layers.112.mlp.gate_proj.weight": "model-00041-of-00050.safetensors", "model.layers.122.mlp.up_proj.weight": "model-00041-of-00050.safetensors", "model.layers.112.mlp.up_proj.weight": "model-00041-of-00050.safetensors", "model.layers.122.post_attention_layernorm.weight": "model-00041-of-00050.safetensors", "model.layers.112.post_attention_layernorm.weight": "model-00041-of-00050.safetensors", "model.layers.122.self_attn.k_proj.weight": "model-00041-of-00050.safetensors", "model.layers.112.self_attn.k_proj.weight": "model-00041-of-00050.safetensors", "model.layers.122.self_attn.o_proj.weight": "model-00041-of-00050.safetensors", "model.layers.112.self_attn.o_proj.weight": "model-00041-of-00050.safetensors", "model.layers.122.self_attn.q_proj.weight": "model-00041-of-00050.safetensors", "model.layers.112.self_attn.q_proj.weight": "model-00041-of-00050.safetensors", "model.layers.122.self_attn.v_proj.weight": "model-00041-of-00050.safetensors", "model.layers.112.self_attn.v_proj.weight": "model-00041-of-00050.safetensors", "model.layers.123.input_layernorm.weight": "model-00041-of-00050.safetensors", "model.layers.113.input_layernorm.weight": "model-00041-of-00050.safetensors", "model.layers.123.mlp.down_proj.weight": "model-00041-of-00050.safetensors", "model.layers.113.mlp.down_proj.weight": "model-00041-of-00050.safetensors", "model.layers.123.mlp.gate_proj.weight": "model-00041-of-00050.safetensors", "model.layers.113.mlp.gate_proj.weight": "model-00041-of-00050.safetensors", "model.layers.123.mlp.up_proj.weight": "model-00041-of-00050.safetensors", "model.layers.113.mlp.up_proj.weight": "model-00041-of-00050.safetensors", "model.layers.123.post_attention_layernorm.weight": "model-00041-of-00050.safetensors", "model.layers.113.post_attention_layernorm.weight": "model-00041-of-00050.safetensors", "model.layers.123.self_attn.k_proj.weight": "model-00041-of-00050.safetensors", "model.layers.113.self_attn.k_proj.weight": "model-00041-of-00050.safetensors", "model.layers.123.self_attn.o_proj.weight": "model-00041-of-00050.safetensors", "model.layers.113.self_attn.o_proj.weight": "model-00042-of-00050.safetensors", "model.layers.123.self_attn.q_proj.weight": "model-00042-of-00050.safetensors", "model.layers.113.self_attn.q_proj.weight": "model-00042-of-00050.safetensors", "model.layers.123.self_attn.v_proj.weight": "model-00042-of-00050.safetensors", "model.layers.113.self_attn.v_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.input_layernorm.weight": "model-00042-of-00050.safetensors", "model.layers.114.input_layernorm.weight": "model-00042-of-00050.safetensors", "model.layers.124.mlp.down_proj.weight": "model-00042-of-00050.safetensors", "model.layers.114.mlp.down_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.mlp.gate_proj.weight": "model-00042-of-00050.safetensors", "model.layers.114.mlp.gate_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.mlp.up_proj.weight": "model-00042-of-00050.safetensors", "model.layers.114.mlp.up_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.post_attention_layernorm.weight": "model-00042-of-00050.safetensors", "model.layers.114.post_attention_layernorm.weight": "model-00042-of-00050.safetensors", "model.layers.124.self_attn.k_proj.weight": "model-00042-of-00050.safetensors", "model.layers.114.self_attn.k_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.self_attn.o_proj.weight": "model-00042-of-00050.safetensors", "model.layers.114.self_attn.o_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.self_attn.q_proj.weight": "model-00042-of-00050.safetensors", "model.layers.114.self_attn.q_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.self_attn.v_proj.weight": "model-00042-of-00050.safetensors", "model.layers.114.self_attn.v_proj.weight": "model-00042-of-00050.safetensors", "model.layers.125.input_layernorm.weight": "model-00042-of-00050.safetensors", "model.layers.115.input_layernorm.weight": "model-00042-of-00050.safetensors", "model.layers.125.mlp.down_proj.weight": "model-00042-of-00050.safetensors", "model.layers.115.mlp.down_proj.weight": "model-00042-of-00050.safetensors", "model.layers.125.mlp.gate_proj.weight": "model-00043-of-00050.safetensors", "model.layers.115.mlp.gate_proj.weight": "model-00043-of-00050.safetensors", "model.layers.125.mlp.up_proj.weight": "model-00043-of-00050.safetensors", "model.layers.115.mlp.up_proj.weight": "model-00043-of-00050.safetensors", "model.layers.125.post_attention_layernorm.weight": "model-00043-of-00050.safetensors", "model.layers.115.post_attention_layernorm.weight": "model-00043-of-00050.safetensors", "model.layers.125.self_attn.k_proj.weight": "model-00043-of-00050.safetensors", "model.layers.115.self_attn.k_proj.weight": "model-00043-of-00050.safetensors", "model.layers.125.self_attn.o_proj.weight": "model-00043-of-00050.safetensors", "model.layers.115.self_attn.o_proj.weight": "model-00043-of-00050.safetensors", "model.layers.125.self_attn.q_proj.weight": "model-00043-of-00050.safetensors", "model.layers.115.self_attn.q_proj.weight": "model-00043-of-00050.safetensors", "model.layers.125.self_attn.v_proj.weight": "model-00043-of-00050.safetensors", "model.layers.115.self_attn.v_proj.weight": "model-00043-of-00050.safetensors", "model.layers.126.input_layernorm.weight": "model-00043-of-00050.safetensors", "model.layers.116.input_layernorm.weight": "model-00043-of-00050.safetensors", "model.layers.126.mlp.down_proj.weight": "model-00043-of-00050.safetensors", "model.layers.116.mlp.down_proj.weight": "model-00043-of-00050.safetensors", "model.layers.126.mlp.gate_proj.weight": "model-00043-of-00050.safetensors", "model.layers.116.mlp.gate_proj.weight": "model-00043-of-00050.safetensors", "model.layers.126.mlp.up_proj.weight": "model-00043-of-00050.safetensors", "model.layers.116.mlp.up_proj.weight": "model-00044-of-00050.safetensors", "model.layers.126.post_attention_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.116.post_attention_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.126.self_attn.k_proj.weight": "model-00044-of-00050.safetensors", "model.layers.116.self_attn.k_proj.weight": "model-00044-of-00050.safetensors", "model.layers.126.self_attn.o_proj.weight": "model-00044-of-00050.safetensors", "model.layers.116.self_attn.o_proj.weight": "model-00044-of-00050.safetensors", "model.layers.126.self_attn.q_proj.weight": "model-00044-of-00050.safetensors", "model.layers.116.self_attn.q_proj.weight": "model-00044-of-00050.safetensors", "model.layers.126.self_attn.v_proj.weight": "model-00044-of-00050.safetensors", "model.layers.116.self_attn.v_proj.weight": "model-00044-of-00050.safetensors", "model.layers.127.input_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.117.input_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.127.mlp.down_proj.weight": "model-00044-of-00050.safetensors", "model.layers.117.mlp.down_proj.weight": "model-00044-of-00050.safetensors", "model.layers.127.mlp.gate_proj.weight": "model-00044-of-00050.safetensors", "model.layers.117.mlp.gate_proj.weight": "model-00044-of-00050.safetensors", "model.layers.127.mlp.up_proj.weight": "model-00044-of-00050.safetensors", "model.layers.117.mlp.up_proj.weight": "model-00044-of-00050.safetensors", "model.layers.127.post_attention_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.117.post_attention_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.127.self_attn.k_proj.weight": "model-00044-of-00050.safetensors", "model.layers.117.self_attn.k_proj.weight": "model-00044-of-00050.safetensors", "model.layers.127.self_attn.o_proj.weight": "model-00044-of-00050.safetensors", "model.layers.117.self_attn.o_proj.weight": "model-00044-of-00050.safetensors", "model.layers.127.self_attn.q_proj.weight": "model-00044-of-00050.safetensors", "model.layers.117.self_attn.q_proj.weight": "model-00044-of-00050.safetensors", "model.layers.127.self_attn.v_proj.weight": "model-00044-of-00050.safetensors", "model.layers.117.self_attn.v_proj.weight": "model-00044-of-00050.safetensors", "model.layers.128.input_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.118.input_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.128.mlp.down_proj.weight": "model-00044-of-00050.safetensors", "model.layers.118.mlp.down_proj.weight": "model-00045-of-00050.safetensors", "model.layers.128.mlp.gate_proj.weight": "model-00045-of-00050.safetensors", "model.layers.118.mlp.gate_proj.weight": "model-00045-of-00050.safetensors", "model.layers.128.mlp.up_proj.weight": "model-00045-of-00050.safetensors", "model.layers.118.mlp.up_proj.weight": "model-00045-of-00050.safetensors", "model.layers.128.post_attention_layernorm.weight": "model-00045-of-00050.safetensors", "model.layers.118.post_attention_layernorm.weight": "model-00045-of-00050.safetensors", "model.layers.128.self_attn.k_proj.weight": "model-00045-of-00050.safetensors", "model.layers.118.self_attn.k_proj.weight": "model-00045-of-00050.safetensors", "model.layers.128.self_attn.o_proj.weight": "model-00045-of-00050.safetensors", "model.layers.118.self_attn.o_proj.weight": "model-00045-of-00050.safetensors", "model.layers.128.self_attn.q_proj.weight": "model-00045-of-00050.safetensors", "model.layers.118.self_attn.q_proj.weight": "model-00045-of-00050.safetensors", "model.layers.128.self_attn.v_proj.weight": "model-00045-of-00050.safetensors", "model.layers.118.self_attn.v_proj.weight": "model-00045-of-00050.safetensors", "model.layers.129.input_layernorm.weight": "model-00045-of-00050.safetensors", "model.layers.119.input_layernorm.weight": "model-00045-of-00050.safetensors", "model.layers.129.mlp.down_proj.weight": "model-00045-of-00050.safetensors", "model.layers.119.mlp.down_proj.weight": "model-00045-of-00050.safetensors", "model.layers.129.mlp.gate_proj.weight": "model-00045-of-00050.safetensors", "model.layers.119.mlp.gate_proj.weight": "model-00045-of-00050.safetensors", "model.layers.129.mlp.up_proj.weight": "model-00046-of-00050.safetensors", "model.layers.119.mlp.up_proj.weight": "model-00046-of-00050.safetensors", "model.layers.129.post_attention_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.119.post_attention_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.129.self_attn.k_proj.weight": "model-00046-of-00050.safetensors", "model.layers.119.self_attn.k_proj.weight": "model-00046-of-00050.safetensors", "model.layers.129.self_attn.o_proj.weight": "model-00046-of-00050.safetensors", "model.layers.119.self_attn.o_proj.weight": "model-00046-of-00050.safetensors", "model.layers.129.self_attn.q_proj.weight": "model-00046-of-00050.safetensors", "model.layers.119.self_attn.q_proj.weight": "model-00046-of-00050.safetensors", "model.layers.129.self_attn.v_proj.weight": "model-00046-of-00050.safetensors", "model.layers.119.self_attn.v_proj.weight": "model-00046-of-00050.safetensors", "model.layers.7.input_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00046-of-00050.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00046-of-00050.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00046-of-00050.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00046-of-00050.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00046-of-00050.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00046-of-00050.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.input_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.130.mlp.down_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.mlp.gate_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.mlp.up_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.post_attention_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.130.self_attn.k_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.self_attn.o_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.self_attn.q_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.self_attn.v_proj.weight": "model-00046-of-00050.safetensors", "model.layers.131.input_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.131.mlp.down_proj.weight": "model-00047-of-00050.safetensors", "model.layers.131.mlp.gate_proj.weight": "model-00047-of-00050.safetensors", "model.layers.131.mlp.up_proj.weight": "model-00047-of-00050.safetensors", "model.layers.131.post_attention_layernorm.weight": "model-00047-of-00050.safetensors", "model.layers.131.self_attn.k_proj.weight": "model-00047-of-00050.safetensors", "model.layers.131.self_attn.o_proj.weight": "model-00047-of-00050.safetensors", "model.layers.131.self_attn.q_proj.weight": "model-00047-of-00050.safetensors", "model.layers.131.self_attn.v_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.input_layernorm.weight": "model-00047-of-00050.safetensors", "model.layers.132.mlp.down_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.mlp.gate_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.mlp.up_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.post_attention_layernorm.weight": "model-00047-of-00050.safetensors", "model.layers.132.self_attn.k_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.self_attn.o_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.self_attn.q_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.self_attn.v_proj.weight": "model-00047-of-00050.safetensors", "model.layers.133.input_layernorm.weight": "model-00047-of-00050.safetensors", "model.layers.133.mlp.down_proj.weight": "model-00047-of-00050.safetensors", "model.layers.133.mlp.gate_proj.weight": "model-00047-of-00050.safetensors", "model.layers.133.mlp.up_proj.weight": "model-00047-of-00050.safetensors", "model.layers.133.post_attention_layernorm.weight": "model-00047-of-00050.safetensors", "model.layers.133.self_attn.k_proj.weight": "model-00047-of-00050.safetensors", "model.layers.133.self_attn.o_proj.weight": "model-00047-of-00050.safetensors", "model.layers.133.self_attn.q_proj.weight": "model-00048-of-00050.safetensors", "model.layers.133.self_attn.v_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.input_layernorm.weight": "model-00048-of-00050.safetensors", "model.layers.134.mlp.down_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.mlp.gate_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.mlp.up_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.post_attention_layernorm.weight": "model-00048-of-00050.safetensors", "model.layers.134.self_attn.k_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.self_attn.o_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.self_attn.q_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.self_attn.v_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.input_layernorm.weight": "model-00048-of-00050.safetensors", "model.layers.135.mlp.down_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.mlp.gate_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.mlp.up_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.post_attention_layernorm.weight": "model-00048-of-00050.safetensors", "model.layers.135.self_attn.k_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.self_attn.o_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.self_attn.q_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.self_attn.v_proj.weight": "model-00048-of-00050.safetensors", "model.layers.136.input_layernorm.weight": "model-00048-of-00050.safetensors", "model.layers.136.mlp.down_proj.weight": "model-00048-of-00050.safetensors", "model.layers.136.mlp.gate_proj.weight": "model-00048-of-00050.safetensors", "model.layers.136.mlp.up_proj.weight": "model-00048-of-00050.safetensors", "model.layers.136.post_attention_layernorm.weight": "model-00048-of-00050.safetensors", "model.layers.136.self_attn.k_proj.weight": "model-00048-of-00050.safetensors", "model.layers.136.self_attn.o_proj.weight": "model-00049-of-00050.safetensors", "model.layers.136.self_attn.q_proj.weight": "model-00049-of-00050.safetensors", "model.layers.136.self_attn.v_proj.weight": "model-00049-of-00050.safetensors", "model.layers.137.input_layernorm.weight": "model-00049-of-00050.safetensors", "model.layers.137.mlp.down_proj.weight": "model-00049-of-00050.safetensors", "model.layers.137.mlp.gate_proj.weight": "model-00049-of-00050.safetensors", "model.layers.137.mlp.up_proj.weight": "model-00049-of-00050.safetensors", "model.layers.137.post_attention_layernorm.weight": "model-00049-of-00050.safetensors", "model.layers.137.self_attn.k_proj.weight": "model-00049-of-00050.safetensors", "model.layers.137.self_attn.o_proj.weight": "model-00049-of-00050.safetensors", "model.layers.137.self_attn.q_proj.weight": "model-00049-of-00050.safetensors", "model.layers.137.self_attn.v_proj.weight": "model-00049-of-00050.safetensors", "model.layers.138.input_layernorm.weight": "model-00049-of-00050.safetensors", "model.layers.138.mlp.down_proj.weight": "model-00049-of-00050.safetensors", "model.layers.138.mlp.gate_proj.weight": "model-00049-of-00050.safetensors", "model.layers.138.mlp.up_proj.weight": "model-00049-of-00050.safetensors", "model.layers.138.post_attention_layernorm.weight": "model-00049-of-00050.safetensors", "model.layers.138.self_attn.k_proj.weight": "model-00049-of-00050.safetensors", "model.layers.138.self_attn.o_proj.weight": "model-00049-of-00050.safetensors", "model.layers.138.self_attn.q_proj.weight": "model-00049-of-00050.safetensors", "model.layers.138.self_attn.v_proj.weight": "model-00049-of-00050.safetensors", "model.layers.139.input_layernorm.weight": "model-00049-of-00050.safetensors", "model.layers.139.mlp.down_proj.weight": "model-00049-of-00050.safetensors", "model.layers.139.mlp.gate_proj.weight": "model-00049-of-00050.safetensors", "model.layers.139.mlp.up_proj.weight": "model-00050-of-00050.safetensors", "model.layers.139.post_attention_layernorm.weight": "model-00050-of-00050.safetensors", "model.layers.139.self_attn.k_proj.weight": "model-00050-of-00050.safetensors", "model.layers.139.self_attn.o_proj.weight": "model-00050-of-00050.safetensors", "model.layers.139.self_attn.q_proj.weight": "model-00050-of-00050.safetensors", "model.layers.139.self_attn.v_proj.weight": "model-00050-of-00050.safetensors", "model.layers.8.input_layernorm.weight": "model-00050-of-00050.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00050-of-00050.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00050-of-00050.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00050-of-00050.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00050-of-00050.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00050-of-00050.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00050-of-00050.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00050-of-00050.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.input_layernorm.weight": "model-00050-of-00050.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00050-of-00050.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00050-of-00050.safetensors", "model.norm.weight": "model-00050-of-00050.safetensors"}} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..02ee80b6196926a5ad790a004d9efd6ab1ba6542 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,16 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..db88166e2bc4c799fd5d1ae643b75e84d03ee70e --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2062 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "tokenizer_class": "PreTrainedTokenizerFast" +}