Upload folder using huggingface_hub

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "nontoxic-bagel-34b-v0.2",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "max_position_embeddings": 200000,
+  "model_type": "mixtral",
+  "num_attention_heads": 56,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
+  "num_local_experts": 4,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 64000
+}

.ipynb_checkpoints/mergekit_moe_config-checkpoint.yml

@@ -0,0 +1,18 @@
+
+base_model: nontoxic-bagel-34b-v0.2
+gate_mode: hidden
+dtype: bfloat16
+
+experts:
+  - source_model: bagel-dpo-34b-v0.2
+    positive_prompts: ["question answering", "Q:", science", "biology", "chemistry", "physics"]
+    negative_prompts: ["math", "reason", "mathematics", "solve", "count", "code", "python", "javascript", "programming", "algorithm"]
+
+  - source_model: Nous-Hermes-2-Yi-34B
+    positive_prompts: ["chat", "math", "reason", "mathematics", "solve", "count", "python", "javascript", "programming", "algorithm", "tell me", "assistant"]
+
+  - source_model: SUS-Chat-34B
+    positive_prompts: ["math", "reason", "mathematics", "solve", "count", "assistant"]
+
+  - source_model: yi-34B-v3
+    positive_prompts: [""]

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "nontoxic-bagel-34b-v0.2",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "max_position_embeddings": 200000,
+  "model_type": "mixtral",
+  "num_attention_heads": 56,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
+  "num_local_experts": 4,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 64000
+}

mergekit_moe_config.yml

@@ -0,0 +1,18 @@
+
+base_model: nontoxic-bagel-34b-v0.2
+gate_mode: hidden
+dtype: bfloat16
+
+experts:
+  - source_model: bagel-dpo-34b-v0.2
+    positive_prompts: ["question answering", "Q:", science", "biology", "chemistry", "physics"]
+    negative_prompts: ["math", "reason", "mathematics", "solve", "count", "code", "python", "javascript", "programming", "algorithm"]
+
+  - source_model: Nous-Hermes-2-Yi-34B
+    positive_prompts: ["chat", "math", "reason", "mathematics", "solve", "count", "python", "javascript", "programming", "algorithm", "tell me", "assistant"]
+
+  - source_model: SUS-Chat-34B
+    positive_prompts: ["math", "reason", "mathematics", "solve", "count", "assistant"]
+
+  - source_model: yi-34B-v3
+    positive_prompts: [""]

model-00001-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaa9d00033996b756150f9c94c8ce07e2d3717988956c765f6f07c8afc504872
+size 9763127624

model-00002-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16b0d2bcea7e1d36268a0453e9dd99b07ee174462b74f8ff2323f6f404077479
+size 9982448024

model-00003-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9b528160a13be018f32dfea791a8533b025eb2b54473be7bea3fa3331e2f435
+size 9982448040

model-00004-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08b01799f17aad1ab62aea902f84b39954e9973bfc2957e16469df4c36602ba0
+size 9982448040

model-00005-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af78c9c3cc6e33476854cfe980129476adbf5dc769bf650eca1e19417fc041c5
+size 9982448040

model-00006-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13940eae1ec5197b1077b15c0baaf691fa18fcb7c0fa68012feda0257c1e4710
+size 9982448040

model-00007-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd931a3e4cf73acf7458cf6d80d398910bbc932c41a983d37a4ae35d5ee3fdab
+size 9982448040

model-00008-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76175126f5ef1084e4c46aee56b8fd7eca3b166de0f47e2d60fafddafde922ed
+size 9982448008

model-00009-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26033028eda21de3530937ec320761769fa124c3bc2574545173c82e203cd18f
+size 9982448024

model-00010-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc1af9e34a9c0e74e92bfff400265e245edb7cb3a785c06e2ad7477e884eb3ed
+size 9982448040

model-00011-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad7b42051d28a9f3049947a676d444f5135950a9273131e0faae0bb66b39c54d
+size 9982448040

model-00012-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02080c392745c33a40c21b23ef0eaf29486682d69faed4f5fdb7ee899eb05a03
+size 9982448040

model-00013-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d62bfd1b151cc3d906c865a57c4ec724b1612fd7fcdd3364c5b129cb55c62896
+size 9982448040

model-00014-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:123d2b498f0de4c6674779cefb8ec9dad6de7b58114c15c2e5c67fa773c53200
+size 9982448040

model-00015-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acaf978c2b119e2d12136468b8df1a397103b025b0da4d1dfff53342482574c8
+size 9982448016

model-00016-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45c9178cc23a6ce2cb2ec453376f589246b654510e51d2f5c289b2bff43debcd
+size 9982448016

model-00017-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c0dd2f84474709feb2caf38c5ae39cdfeb32203293173374adc52d77cbb0df5
+size 9982448040

model-00018-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dc169eb7e737358066b2c1f7c40cdac9d0a7bb9a55f027ba611f8fcbcff47cf
+size 9982448040

model-00019-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d6a8407ad4bce8549b7fe7913999f9dff5f2ca00bc9862a91c3195baf2dd2c7
+size 9982448040

model-00020-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3da88fbb80d32b9fbda90f98c2075423710123115ca86769b482574533e076f
+size 9982448040

model-00021-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c26e0663eb6cbb05f5219f7484bddd0f15b5c63506892132c3badc78049ff03c
+size 9982448040

model-00022-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c54fe9f3d77770d91def3060b424be6b5b5a73c0f0416d35d3a1759dfd8a090
+size 9997999880

model-00023-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6042a65cb594d9bb887953aba24a8101b04237d90277be47795e3928bbd9ae6b
+size 7916023384

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{%- for idx in range(0, messages|length) -%}\n{%- if messages[idx]['role'] == 'user' -%}\n{%- if idx > 1 -%}\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\n{%- else -%}\n{{- messages[idx]['content'] + ' [/INST]' -}}\n{%- endif -%}\n{% elif messages[idx]['role'] == 'system' %}\n{{- '[INST] <<SYS>>\\n' + messages[idx]['content'] + '\\n<</SYS>>\\n\\n' -}}\n{%- elif messages[idx]['role'] == 'assistant' -%}\n{{- ' '  + messages[idx]['content'] + ' ' + eos_token -}}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 200000,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}