Upload folder using huggingface_hub (#1)

- 3660f2830bf7e88ea4a27e5f94fb6aa37c79dd3954e66b3c26580eb11edc5d89 (61b1fcf31938ad94f4a197e9cefad7d49e62879a)
- 0516a454629365c2b1d2f424771008b575b168478ffe8d99c00e53fed6032d05 (2ff9de148d3dfc8536aeca663e1f4611694380b5)
- 0724f03653419af215fe384d2e55fd76a1ad86055fc4eebc992febaff3933510 (ccf251c3fd7331ec2c4b9fd836903b6b38ed05d5)
- b4a8ac7c2412ff59933dc1410edf446cfd1135db06b6e984118b511d88659382 (97294bb0d8c47808ba3eda3aa20ed1455519b2bf)
- 2da01e28cd84a6a1333c07457096fbe02574ef9c285a479ac66de76c3940c471 (94dc912adae7d91aa11df2e7ad0069c81cd6bc13)
- 3686bdbc2d5dc59c140c19b9db1be5b40380d09f5ac3032c09dcde9b314eb328 (d7813b87ce2900c8dfc5c84683fe62b326ca68b8)
- e95b3629a82558f529707ed08ee7861337e29dbaaf4d3c537a738afaa9173c52 (2a80ec52b5839fbcebcc6c5271401a5c6afa1838)
- 7d05689b545eca8eeededba29058edc75f7c0654bc497af2263b45c768fb40d8 (6b87427ba48318333d76d6b3264494ea7de23da5)
- 55669b8e620f6b01f40ad64aa6d6ccb0a6725cc7bf4103494b235a36ac8d752c (22f54cd5ad301e80f33d8621288a6292d9f3bcd6)
- 466792c8029c42a5a9d8da29a503b531321ecef752ec1b35bce3ee409da95c2b (a8e7f104117eea524ae7e966a77488e26672fd7a)
- 671b5a6f9e8ecdb2bb1c5a3ff9041747018646d4543850b3de71d349f261ad02 (73a6827236f2998444d841fdad5b2f532a589ed6)
- f6d81b4719c375f1e4e2c9ca3dea92166b885e5f423417060508527e10538677 (0ed9d3e7a3ded5d1942559cf60b7db60cf7c942a)
- 6ff78eb5f9a1a60806e700446933796fd120e5bba4d4f3952bc0c0a43e73d4a4 (097cd221a7b46847aec00e44359d8867d2827b32)
- 26f8db907e258ed0de3b2c99d6b8bac3898834fc9475bf0453a983b6a6bd596e (9e627c09f67e38305aefeca05215746696a04bd5)
- 88271fb51b3c08880b14ae8115c66771600e0dbdc50fb70e545fc8b5bcb1359c (e66b79f09fe3b3e4afb82e428aac0055ff482529)
- 77592b83e253a18bbeaae019d877902482470f9c613032efa61952e9e8b157bf (da4d1d11cc8878d788116a68cdd856148cb0e1bb)
- 092486c263fb738ac9ea1f77e0a6f173c066dfff5343e2af78229e44006766f4 (48fe9be5dc559ecf1071db343c4bb9d51efffc1b)
- 18cbde7be68ff9e9d7fbfdf9262b06a48bdb1001f18ad93f9ef7571027e79b05 (fc622e2c594b960496164d1c8432b923988865a5)
- 6d31f4f28a7c8b554ef69c6313976b19e92c73ee73c5b825c7918e31f6deb10d (f572b2a9afbf3c3a0b0846a72be84726416a848f)
- 844b7b561a70d62f6e06011469732cb8f89d26c1f45e9d790c304e7e29352b73 (9ebbe9ee6664019a80075907433b3638969487ca)
- 96f1038ced7f055c819a932e44187c5d5b06bcaa533a933d2c93cd3667df32b9 (327693c49601030076e71440bcc0a71e18bb9107)


Co-authored-by: Jay Rainton <[email protected]>

.gitattributes

@@ -32,3 +32,4 @@ 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

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/nvmedata/jue/bloom_ock_new",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 14336,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 112,
+  "n_layer": 70,
+  "pad_token_id": 3,
+  "pretraining_tp": 4,
+  "return_dict": false,
+  "slow_but_exact": false,
+  "transformers_version": "4.25.0",
+  "use_cache": false,
+  "vocab_size": 250880
+}

pytorch_model-01-of-20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76d48bfbd522da6287d48356847b61f27fcd71505513dacf5111df7d8870d6a1
+size 17059103878

pytorch_model-02-of-20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f881bf8fa9695bd162221b0ae604395de016c353cd3204fd26616e790b885646
+size 18087257857

pytorch_model-03-of-20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d35adb75eaa5f88826a9402c948e4fc6032f8e83ec8641dbda5cf2bc2060757e
+size 18087229915

pytorch_model-04-of-20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88baa6adb19e1e893eb1af3a9c1e10b6a4ba29eebd8019664df47519eee22bf1
+size 18087171231

pytorch_model-05-of-20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8330113dae1a8fa4b1dc082ca2dab387ee16a2b9208f10d62dcc554d22c1d45b
+size 18087257857

pytorch_model-06-of-20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f0f81b5d43c5d3818bd843b4343f3ad426bed98f53ff2464ea26829bc14c0d7
+size 18087229915

pytorch_model-07-of-20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81ee053dceb08c7aaaf47c31f9b13850ef7c4b1b2260c4f9627a6a78437db3b4
+size 18087171231

pytorch_model-08-of-20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:519e86b1c86525a7b719e7506b8400f4994636f1878373b4c6902cab45363bd4
+size 18087257857

pytorch_model-09-of-20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1bda6f18262c1a60d737c12631775f9b6d5b5c3d3705ba9487544c8abec7824
+size 18087229915

pytorch_model-10-of-20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:245834cb60e4ae4bf851e970e638e1f13b13490f82c57a317be0b37c0dc6799c
+size 18087171231

pytorch_model-11-of-20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bee51a0995b14b28cd8a177417473b9aff3d11a567a8aa1e7e3cc5aaf621ff2
+size 18087257857

pytorch_model-12-of-20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6659dc72b0f58135639162db8c3a28439a225b5004b7a1cd9395b1ee8d66bba3
+size 18087229915

pytorch_model-13-of-20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5060f70314fe5308bb2f050b31febb163dee27128b1b03a5ecf64f4f371ab42
+size 18087171231

pytorch_model-14-of-20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f0258eeddc7162fc03559d52fd91147af585d0b91b8440111e38d1b62403954
+size 18087257857

pytorch_model-15-of-20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7da433cbd0f8c121046738217ff47360a3375e26d20d523eb6500b53b126acef
+size 18087229915

pytorch_model-16-of-20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c19ba6089d55f6e3cf16e7915550d685c24cf572951be1e40b72ad0b6480d8d
+size 18087171231

pytorch_model-17-of-20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a72ac6f3f09b354f2633e30a751c3ad37498d2d029ad703a404e92660fc6855
+size 18087257857

pytorch_model-18-of-20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b2b2c1e86421fb426b3c38828e12da478264f27840d4035d56b79edbb7a3ee7
+size 18087229915

pytorch_model-19-of-20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f61999db5132bcdee1cae12faa1b1593a0adcf129ce528dc12109c6720d9e8d
+size 18087171231

pytorch_model-20-of-20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fb20df3af92660c248ec54533e1a8c8697bb8eb8e611afac2009f57db91e45b
+size 17058987750

pytorch_model.bin.index.json

@@ -0,0 +1 @@
+{"metadata": {}, "weight_map": {"transformer.word_embeddings.weight": "pytorch_model-01-of-20.bin", "transformer.word_embeddings_layernorm.weight": "pytorch_model-01-of-20.bin", "transformer.word_embeddings_layernorm.bias": "pytorch_model-01-of-20.bin", "transformer.h.0.input_layernorm.weight": "pytorch_model-01-of-20.bin", "transformer.h.0.input_layernorm.bias": "pytorch_model-01-of-20.bin", "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-01-of-20.bin", "transformer.h.0.self_attention.query_key_value.bias": "pytorch_model-01-of-20.bin", "transformer.h.0.self_attention.dense.weight": "pytorch_model-01-of-20.bin", "transformer.h.0.self_attention.dense.bias": "pytorch_model-01-of-20.bin", "transformer.h.0.post_attention_layernorm.weight": "pytorch_model-01-of-20.bin", "transformer.h.0.post_attention_layernorm.bias": "pytorch_model-01-of-20.bin", "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-01-of-20.bin", "transformer.h.0.mlp.dense_h_to_4h.bias": "pytorch_model-01-of-20.bin", "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-01-of-20.bin", "transformer.h.0.mlp.dense_4h_to_h.bias": "pytorch_model-01-of-20.bin", "transformer.h.1.input_layernorm.weight": "pytorch_model-01-of-20.bin", "transformer.h.1.input_layernorm.bias": "pytorch_model-01-of-20.bin", "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-01-of-20.bin", "transformer.h.1.self_attention.query_key_value.bias": "pytorch_model-01-of-20.bin", "transformer.h.1.self_attention.dense.weight": "pytorch_model-01-of-20.bin", "transformer.h.1.self_attention.dense.bias": "pytorch_model-01-of-20.bin", "transformer.h.1.post_attention_layernorm.weight": "pytorch_model-01-of-20.bin", "transformer.h.1.post_attention_layernorm.bias": "pytorch_model-01-of-20.bin", "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-01-of-20.bin", "transformer.h.1.mlp.dense_h_to_4h.bias": "pytorch_model-01-of-20.bin", "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-01-of-20.bin", "transformer.h.1.mlp.dense_4h_to_h.bias": "pytorch_model-01-of-20.bin", "transformer.h.2.input_layernorm.weight": "pytorch_model-01-of-20.bin", "transformer.h.2.input_layernorm.bias": "pytorch_model-01-of-20.bin", "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-02-of-20.bin", "transformer.h.2.self_attention.query_key_value.bias": "pytorch_model-02-of-20.bin", "transformer.h.2.self_attention.dense.weight": "pytorch_model-02-of-20.bin", "transformer.h.2.self_attention.dense.bias": "pytorch_model-02-of-20.bin", "transformer.h.2.post_attention_layernorm.weight": "pytorch_model-02-of-20.bin", "transformer.h.2.post_attention_layernorm.bias": "pytorch_model-02-of-20.bin", "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-02-of-20.bin", "transformer.h.2.mlp.dense_h_to_4h.bias": "pytorch_model-02-of-20.bin", "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-02-of-20.bin", "transformer.h.2.mlp.dense_4h_to_h.bias": "pytorch_model-02-of-20.bin", "transformer.h.3.input_layernorm.weight": "pytorch_model-02-of-20.bin", "transformer.h.3.input_layernorm.bias": "pytorch_model-02-of-20.bin", "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-02-of-20.bin", "transformer.h.3.self_attention.query_key_value.bias": "pytorch_model-02-of-20.bin", "transformer.h.3.self_attention.dense.weight": "pytorch_model-02-of-20.bin", "transformer.h.3.self_attention.dense.bias": "pytorch_model-02-of-20.bin", "transformer.h.3.post_attention_layernorm.weight": "pytorch_model-02-of-20.bin", "transformer.h.3.post_attention_layernorm.bias": "pytorch_model-02-of-20.bin", "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-02-of-20.bin", "transformer.h.3.mlp.dense_h_to_4h.bias": "pytorch_model-02-of-20.bin", "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-02-of-20.bin", "transformer.h.3.mlp.dense_4h_to_h.bias": "pytorch_model-02-of-20.bin", "transformer.h.4.input_layernorm.weight": "pytorch_model-02-of-20.bin", "transformer.h.4.input_layernorm.bias": "pytorch_model-02-of-20.bin", "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-02-of-20.bin", "transformer.h.4.self_attention.query_key_value.bias": "pytorch_model-02-of-20.bin", "transformer.h.4.self_attention.dense.weight": "pytorch_model-02-of-20.bin", "transformer.h.4.self_attention.dense.bias": "pytorch_model-02-of-20.bin", "transformer.h.4.post_attention_layernorm.weight": "pytorch_model-02-of-20.bin", "transformer.h.4.post_attention_layernorm.bias": "pytorch_model-02-of-20.bin", "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-02-of-20.bin", "transformer.h.4.mlp.dense_h_to_4h.bias": "pytorch_model-02-of-20.bin", "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-02-of-20.bin", "transformer.h.4.mlp.dense_4h_to_h.bias": "pytorch_model-02-of-20.bin", "transformer.h.5.input_layernorm.weight": "pytorch_model-02-of-20.bin", "transformer.h.5.input_layernorm.bias": "pytorch_model-02-of-20.bin", "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-02-of-20.bin", "transformer.h.5.self_attention.query_key_value.bias": "pytorch_model-02-of-20.bin", "transformer.h.5.self_attention.dense.weight": "pytorch_model-02-of-20.bin", "transformer.h.5.self_attention.dense.bias": "pytorch_model-02-of-20.bin", "transformer.h.5.post_attention_layernorm.weight": "pytorch_model-02-of-20.bin", "transformer.h.5.post_attention_layernorm.bias": "pytorch_model-02-of-20.bin", "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-02-of-20.bin", "transformer.h.5.mlp.dense_h_to_4h.bias": "pytorch_model-02-of-20.bin", "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-03-of-20.bin", "transformer.h.5.mlp.dense_4h_to_h.bias": "pytorch_model-03-of-20.bin", "transformer.h.6.input_layernorm.weight": "pytorch_model-03-of-20.bin", "transformer.h.6.input_layernorm.bias": "pytorch_model-03-of-20.bin", "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-03-of-20.bin", "transformer.h.6.self_attention.query_key_value.bias": "pytorch_model-03-of-20.bin", "transformer.h.6.self_attention.dense.weight": "pytorch_model-03-of-20.bin", "transformer.h.6.self_attention.dense.bias": "pytorch_model-03-of-20.bin", "transformer.h.6.post_attention_layernorm.weight": "pytorch_model-03-of-20.bin", "transformer.h.6.post_attention_layernorm.bias": "pytorch_model-03-of-20.bin", "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-03-of-20.bin", "transformer.h.6.mlp.dense_h_to_4h.bias": "pytorch_model-03-of-20.bin", "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-03-of-20.bin", "transformer.h.6.mlp.dense_4h_to_h.bias": "pytorch_model-03-of-20.bin", "transformer.h.7.input_layernorm.weight": "pytorch_model-03-of-20.bin", "transformer.h.7.input_layernorm.bias": "pytorch_model-03-of-20.bin", "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-03-of-20.bin", "transformer.h.7.self_attention.query_key_value.bias": "pytorch_model-03-of-20.bin", "transformer.h.7.self_attention.dense.weight": "pytorch_model-03-of-20.bin", "transformer.h.7.self_attention.dense.bias": "pytorch_model-03-of-20.bin", "transformer.h.7.post_attention_layernorm.weight": "pytorch_model-03-of-20.bin", "transformer.h.7.post_attention_layernorm.bias": "pytorch_model-03-of-20.bin", "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-03-of-20.bin", "transformer.h.7.mlp.dense_h_to_4h.bias": "pytorch_model-03-of-20.bin", "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-03-of-20.bin", "transformer.h.7.mlp.dense_4h_to_h.bias": "pytorch_model-03-of-20.bin", "transformer.h.8.input_layernorm.weight": "pytorch_model-03-of-20.bin", "transformer.h.8.input_layernorm.bias": "pytorch_model-03-of-20.bin", "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-03-of-20.bin", "transformer.h.8.self_attention.query_key_value.bias": "pytorch_model-03-of-20.bin", "transformer.h.8.self_attention.dense.weight": "pytorch_model-03-of-20.bin", "transformer.h.8.self_attention.dense.bias": "pytorch_model-03-of-20.bin", "transformer.h.8.post_attention_layernorm.weight": "pytorch_model-03-of-20.bin", "transformer.h.8.post_attention_layernorm.bias": "pytorch_model-03-of-20.bin", "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-03-of-20.bin", "transformer.h.8.mlp.dense_h_to_4h.bias": "pytorch_model-03-of-20.bin", "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-03-of-20.bin", "transformer.h.8.mlp.dense_4h_to_h.bias": "pytorch_model-03-of-20.bin", "transformer.h.9.input_layernorm.weight": "pytorch_model-03-of-20.bin", "transformer.h.9.input_layernorm.bias": "pytorch_model-03-of-20.bin", "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-03-of-20.bin", "transformer.h.9.self_attention.query_key_value.bias": "pytorch_model-03-of-20.bin", "transformer.h.9.self_attention.dense.weight": "pytorch_model-03-of-20.bin", "transformer.h.9.self_attention.dense.bias": "pytorch_model-03-of-20.bin", "transformer.h.9.post_attention_layernorm.weight": "pytorch_model-03-of-20.bin", "transformer.h.9.post_attention_layernorm.bias": "pytorch_model-03-of-20.bin", "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-04-of-20.bin", "transformer.h.9.mlp.dense_h_to_4h.bias": "pytorch_model-04-of-20.bin", "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-04-of-20.bin", "transformer.h.9.mlp.dense_4h_to_h.bias": "pytorch_model-04-of-20.bin", "transformer.h.10.input_layernorm.weight": "pytorch_model-04-of-20.bin", "transformer.h.10.input_layernorm.bias": "pytorch_model-04-of-20.bin", "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-04-of-20.bin", "transformer.h.10.self_attention.query_key_value.bias": "pytorch_model-04-of-20.bin", "transformer.h.10.self_attention.dense.weight": "pytorch_model-04-of-20.bin", "transformer.h.10.self_attention.dense.bias": "pytorch_model-04-of-20.bin", "transformer.h.10.post_attention_layernorm.weight": "pytorch_model-04-of-20.bin", "transformer.h.10.post_attention_layernorm.bias": "pytorch_model-04-of-20.bin", "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-04-of-20.bin", "transformer.h.10.mlp.dense_h_to_4h.bias": "pytorch_model-04-of-20.bin", "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-04-of-20.bin", "transformer.h.10.mlp.dense_4h_to_h.bias": "pytorch_model-04-of-20.bin", "transformer.h.11.input_layernorm.weight": "pytorch_model-04-of-20.bin", "transformer.h.11.input_layernorm.bias": "pytorch_model-04-of-20.bin", "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-04-of-20.bin", "transformer.h.11.self_attention.query_key_value.bias": "pytorch_model-04-of-20.bin", "transformer.h.11.self_attention.dense.weight": "pytorch_model-04-of-20.bin", "transformer.h.11.self_attention.dense.bias": "pytorch_model-04-of-20.bin", "transformer.h.11.post_attention_layernorm.weight": "pytorch_model-04-of-20.bin", "transformer.h.11.post_attention_layernorm.bias": "pytorch_model-04-of-20.bin", "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-04-of-20.bin", "transformer.h.11.mlp.dense_h_to_4h.bias": "pytorch_model-04-of-20.bin", "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-04-of-20.bin", "transformer.h.11.mlp.dense_4h_to_h.bias": "pytorch_model-04-of-20.bin", "transformer.h.12.input_layernorm.weight": "pytorch_model-04-of-20.bin", "transformer.h.12.input_layernorm.bias": "pytorch_model-04-of-20.bin", "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-04-of-20.bin", "transformer.h.12.self_attention.query_key_value.bias": "pytorch_model-04-of-20.bin", "transformer.h.12.self_attention.dense.weight": "pytorch_model-04-of-20.bin", "transformer.h.12.self_attention.dense.bias": "pytorch_model-04-of-20.bin", "transformer.h.12.post_attention_layernorm.weight": "pytorch_model-04-of-20.bin", "transformer.h.12.post_attention_layernorm.bias": "pytorch_model-04-of-20.bin", "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-04-of-20.bin", "transformer.h.12.mlp.dense_h_to_4h.bias": "pytorch_model-04-of-20.bin", "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-04-of-20.bin", "transformer.h.12.mlp.dense_4h_to_h.bias": "pytorch_model-04-of-20.bin", "transformer.h.13.input_layernorm.weight": "pytorch_model-04-of-20.bin", "transformer.h.13.input_layernorm.bias": "pytorch_model-04-of-20.bin", "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-05-of-20.bin", "transformer.h.13.self_attention.query_key_value.bias": "pytorch_model-05-of-20.bin", "transformer.h.13.self_attention.dense.weight": "pytorch_model-05-of-20.bin", "transformer.h.13.self_attention.dense.bias": "pytorch_model-05-of-20.bin", "transformer.h.13.post_attention_layernorm.weight": "pytorch_model-05-of-20.bin", "transformer.h.13.post_attention_layernorm.bias": "pytorch_model-05-of-20.bin", "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-05-of-20.bin", "transformer.h.13.mlp.dense_h_to_4h.bias": "pytorch_model-05-of-20.bin", "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-05-of-20.bin", "transformer.h.13.mlp.dense_4h_to_h.bias": "pytorch_model-05-of-20.bin", "transformer.h.14.input_layernorm.weight": "pytorch_model-05-of-20.bin", "transformer.h.14.input_layernorm.bias": "pytorch_model-05-of-20.bin", "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-05-of-20.bin", "transformer.h.14.self_attention.query_key_value.bias": "pytorch_model-05-of-20.bin", "transformer.h.14.self_attention.dense.weight": "pytorch_model-05-of-20.bin", "transformer.h.14.self_attention.dense.bias": "pytorch_model-05-of-20.bin", "transformer.h.14.post_attention_layernorm.weight": "pytorch_model-05-of-20.bin", "transformer.h.14.post_attention_layernorm.bias": "pytorch_model-05-of-20.bin", "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-05-of-20.bin", "transformer.h.14.mlp.dense_h_to_4h.bias": "pytorch_model-05-of-20.bin", "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-05-of-20.bin", "transformer.h.14.mlp.dense_4h_to_h.bias": "pytorch_model-05-of-20.bin", "transformer.h.15.input_layernorm.weight": "pytorch_model-05-of-20.bin", "transformer.h.15.input_layernorm.bias": "pytorch_model-05-of-20.bin", "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-05-of-20.bin", "transformer.h.15.self_attention.query_key_value.bias": "pytorch_model-05-of-20.bin", "transformer.h.15.self_attention.dense.weight": "pytorch_model-05-of-20.bin", "transformer.h.15.self_attention.dense.bias": "pytorch_model-05-of-20.bin", "transformer.h.15.post_attention_layernorm.weight": "pytorch_model-05-of-20.bin", "transformer.h.15.post_attention_layernorm.bias": "pytorch_model-05-of-20.bin", "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-05-of-20.bin", "transformer.h.15.mlp.dense_h_to_4h.bias": "pytorch_model-05-of-20.bin", "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-05-of-20.bin", "transformer.h.15.mlp.dense_4h_to_h.bias": "pytorch_model-05-of-20.bin", "transformer.h.16.input_layernorm.weight": "pytorch_model-05-of-20.bin", "transformer.h.16.input_layernorm.bias": "pytorch_model-05-of-20.bin", "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-05-of-20.bin", "transformer.h.16.self_attention.query_key_value.bias": "pytorch_model-05-of-20.bin", "transformer.h.16.self_attention.dense.weight": "pytorch_model-05-of-20.bin", "transformer.h.16.self_attention.dense.bias": "pytorch_model-05-of-20.bin", "transformer.h.16.post_attention_layernorm.weight": "pytorch_model-05-of-20.bin", "transformer.h.16.post_attention_layernorm.bias": "pytorch_model-05-of-20.bin", "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-05-of-20.bin", "transformer.h.16.mlp.dense_h_to_4h.bias": "pytorch_model-05-of-20.bin", "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-06-of-20.bin", "transformer.h.16.mlp.dense_4h_to_h.bias": "pytorch_model-06-of-20.bin", "transformer.h.17.input_layernorm.weight": "pytorch_model-06-of-20.bin", "transformer.h.17.input_layernorm.bias": "pytorch_model-06-of-20.bin", "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-06-of-20.bin", "transformer.h.17.self_attention.query_key_value.bias": "pytorch_model-06-of-20.bin", "transformer.h.17.self_attention.dense.weight": "pytorch_model-06-of-20.bin", "transformer.h.17.self_attention.dense.bias": "pytorch_model-06-of-20.bin", "transformer.h.17.post_attention_layernorm.weight": "pytorch_model-06-of-20.bin", "transformer.h.17.post_attention_layernorm.bias": "pytorch_model-06-of-20.bin", "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-06-of-20.bin", "transformer.h.17.mlp.dense_h_to_4h.bias": "pytorch_model-06-of-20.bin", "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-06-of-20.bin", "transformer.h.17.mlp.dense_4h_to_h.bias": "pytorch_model-06-of-20.bin", "transformer.h.18.input_layernorm.weight": "pytorch_model-06-of-20.bin", "transformer.h.18.input_layernorm.bias": "pytorch_model-06-of-20.bin", "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-06-of-20.bin", "transformer.h.18.self_attention.query_key_value.bias": "pytorch_model-06-of-20.bin", "transformer.h.18.self_attention.dense.weight": "pytorch_model-06-of-20.bin", "transformer.h.18.self_attention.dense.bias": "pytorch_model-06-of-20.bin", "transformer.h.18.post_attention_layernorm.weight": "pytorch_model-06-of-20.bin", "transformer.h.18.post_attention_layernorm.bias": "pytorch_model-06-of-20.bin", "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-06-of-20.bin", "transformer.h.18.mlp.dense_h_to_4h.bias": "pytorch_model-06-of-20.bin", "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-06-of-20.bin", "transformer.h.18.mlp.dense_4h_to_h.bias": "pytorch_model-06-of-20.bin", "transformer.h.19.input_layernorm.weight": "pytorch_model-06-of-20.bin", "transformer.h.19.input_layernorm.bias": "pytorch_model-06-of-20.bin", "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-06-of-20.bin", "transformer.h.19.self_attention.query_key_value.bias": "pytorch_model-06-of-20.bin", "transformer.h.19.self_attention.dense.weight": "pytorch_model-06-of-20.bin", "transformer.h.19.self_attention.dense.bias": "pytorch_model-06-of-20.bin", "transformer.h.19.post_attention_layernorm.weight": "pytorch_model-06-of-20.bin", "transformer.h.19.post_attention_layernorm.bias": "pytorch_model-06-of-20.bin", "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-06-of-20.bin", "transformer.h.19.mlp.dense_h_to_4h.bias": "pytorch_model-06-of-20.bin", "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-06-of-20.bin", "transformer.h.19.mlp.dense_4h_to_h.bias": "pytorch_model-06-of-20.bin", "transformer.h.20.input_layernorm.weight": "pytorch_model-06-of-20.bin", "transformer.h.20.input_layernorm.bias": "pytorch_model-06-of-20.bin", "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-06-of-20.bin", "transformer.h.20.self_attention.query_key_value.bias": "pytorch_model-06-of-20.bin", "transformer.h.20.self_attention.dense.weight": "pytorch_model-06-of-20.bin", "transformer.h.20.self_attention.dense.bias": "pytorch_model-06-of-20.bin", "transformer.h.20.post_attention_layernorm.weight": "pytorch_model-06-of-20.bin", "transformer.h.20.post_attention_layernorm.bias": "pytorch_model-06-of-20.bin", "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-07-of-20.bin", "transformer.h.20.mlp.dense_h_to_4h.bias": "pytorch_model-07-of-20.bin", "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-07-of-20.bin", "transformer.h.20.mlp.dense_4h_to_h.bias": "pytorch_model-07-of-20.bin", "transformer.h.21.input_layernorm.weight": "pytorch_model-07-of-20.bin", "transformer.h.21.input_layernorm.bias": "pytorch_model-07-of-20.bin", "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-07-of-20.bin", "transformer.h.21.self_attention.query_key_value.bias": "pytorch_model-07-of-20.bin", "transformer.h.21.self_attention.dense.weight": "pytorch_model-07-of-20.bin", "transformer.h.21.self_attention.dense.bias": "pytorch_model-07-of-20.bin", "transformer.h.21.post_attention_layernorm.weight": "pytorch_model-07-of-20.bin", "transformer.h.21.post_attention_layernorm.bias": "pytorch_model-07-of-20.bin", "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-07-of-20.bin", "transformer.h.21.mlp.dense_h_to_4h.bias": "pytorch_model-07-of-20.bin", "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-07-of-20.bin", "transformer.h.21.mlp.dense_4h_to_h.bias": "pytorch_model-07-of-20.bin", "transformer.h.22.input_layernorm.weight": "pytorch_model-07-of-20.bin", "transformer.h.22.input_layernorm.bias": "pytorch_model-07-of-20.bin", "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-07-of-20.bin", "transformer.h.22.self_attention.query_key_value.bias": "pytorch_model-07-of-20.bin", "transformer.h.22.self_attention.dense.weight": "pytorch_model-07-of-20.bin", "transformer.h.22.self_attention.dense.bias": "pytorch_model-07-of-20.bin", "transformer.h.22.post_attention_layernorm.weight": "pytorch_model-07-of-20.bin", "transformer.h.22.post_attention_layernorm.bias": "pytorch_model-07-of-20.bin", "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-07-of-20.bin", "transformer.h.22.mlp.dense_h_to_4h.bias": "pytorch_model-07-of-20.bin", "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-07-of-20.bin", "transformer.h.22.mlp.dense_4h_to_h.bias": "pytorch_model-07-of-20.bin", "transformer.h.23.input_layernorm.weight": "pytorch_model-07-of-20.bin", "transformer.h.23.input_layernorm.bias": "pytorch_model-07-of-20.bin", "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-07-of-20.bin", "transformer.h.23.self_attention.query_key_value.bias": "pytorch_model-07-of-20.bin", "transformer.h.23.self_attention.dense.weight": "pytorch_model-07-of-20.bin", "transformer.h.23.self_attention.dense.bias": "pytorch_model-07-of-20.bin", "transformer.h.23.post_attention_layernorm.weight": "pytorch_model-07-of-20.bin", "transformer.h.23.post_attention_layernorm.bias": "pytorch_model-07-of-20.bin", "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-07-of-20.bin", "transformer.h.23.mlp.dense_h_to_4h.bias": "pytorch_model-07-of-20.bin", "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-07-of-20.bin", "transformer.h.23.mlp.dense_4h_to_h.bias": "pytorch_model-07-of-20.bin", "transformer.h.24.input_layernorm.weight": "pytorch_model-07-of-20.bin", "transformer.h.24.input_layernorm.bias": "pytorch_model-07-of-20.bin", "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-08-of-20.bin", "transformer.h.24.self_attention.query_key_value.bias": "pytorch_model-08-of-20.bin", "transformer.h.24.self_attention.dense.weight": "pytorch_model-08-of-20.bin", "transformer.h.24.self_attention.dense.bias": "pytorch_model-08-of-20.bin", "transformer.h.24.post_attention_layernorm.weight": "pytorch_model-08-of-20.bin", "transformer.h.24.post_attention_layernorm.bias": "pytorch_model-08-of-20.bin", "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-08-of-20.bin", "transformer.h.24.mlp.dense_h_to_4h.bias": "pytorch_model-08-of-20.bin", "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-08-of-20.bin", "transformer.h.24.mlp.dense_4h_to_h.bias": "pytorch_model-08-of-20.bin", "transformer.h.25.input_layernorm.weight": "pytorch_model-08-of-20.bin", "transformer.h.25.input_layernorm.bias": "pytorch_model-08-of-20.bin", "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-08-of-20.bin", "transformer.h.25.self_attention.query_key_value.bias": "pytorch_model-08-of-20.bin", "transformer.h.25.self_attention.dense.weight": "pytorch_model-08-of-20.bin", "transformer.h.25.self_attention.dense.bias": "pytorch_model-08-of-20.bin", "transformer.h.25.post_attention_layernorm.weight": "pytorch_model-08-of-20.bin", "transformer.h.25.post_attention_layernorm.bias": "pytorch_model-08-of-20.bin", "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-08-of-20.bin", "transformer.h.25.mlp.dense_h_to_4h.bias": "pytorch_model-08-of-20.bin", "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-08-of-20.bin", "transformer.h.25.mlp.dense_4h_to_h.bias": "pytorch_model-08-of-20.bin", "transformer.h.26.input_layernorm.weight": "pytorch_model-08-of-20.bin", "transformer.h.26.input_layernorm.bias": "pytorch_model-08-of-20.bin", "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-08-of-20.bin", "transformer.h.26.self_attention.query_key_value.bias": "pytorch_model-08-of-20.bin", "transformer.h.26.self_attention.dense.weight": "pytorch_model-08-of-20.bin", "transformer.h.26.self_attention.dense.bias": "pytorch_model-08-of-20.bin", "transformer.h.26.post_attention_layernorm.weight": "pytorch_model-08-of-20.bin", "transformer.h.26.post_attention_layernorm.bias": "pytorch_model-08-of-20.bin", "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-08-of-20.bin", "transformer.h.26.mlp.dense_h_to_4h.bias": "pytorch_model-08-of-20.bin", "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-08-of-20.bin", "transformer.h.26.mlp.dense_4h_to_h.bias": "pytorch_model-08-of-20.bin", "transformer.h.27.input_layernorm.weight": "pytorch_model-08-of-20.bin", "transformer.h.27.input_layernorm.bias": "pytorch_model-08-of-20.bin", "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-08-of-20.bin", "transformer.h.27.self_attention.query_key_value.bias": "pytorch_model-08-of-20.bin", "transformer.h.27.self_attention.dense.weight": "pytorch_model-08-of-20.bin", "transformer.h.27.self_attention.dense.bias": "pytorch_model-08-of-20.bin", "transformer.h.27.post_attention_layernorm.weight": "pytorch_model-08-of-20.bin", "transformer.h.27.post_attention_layernorm.bias": "pytorch_model-08-of-20.bin", "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-08-of-20.bin", "transformer.h.27.mlp.dense_h_to_4h.bias": "pytorch_model-08-of-20.bin", "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-09-of-20.bin", "transformer.h.27.mlp.dense_4h_to_h.bias": "pytorch_model-09-of-20.bin", "transformer.h.28.input_layernorm.weight": "pytorch_model-09-of-20.bin", "transformer.h.28.input_layernorm.bias": "pytorch_model-09-of-20.bin", "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-09-of-20.bin", "transformer.h.28.self_attention.query_key_value.bias": "pytorch_model-09-of-20.bin", "transformer.h.28.self_attention.dense.weight": "pytorch_model-09-of-20.bin", "transformer.h.28.self_attention.dense.bias": "pytorch_model-09-of-20.bin", "transformer.h.28.post_attention_layernorm.weight": "pytorch_model-09-of-20.bin", "transformer.h.28.post_attention_layernorm.bias": "pytorch_model-09-of-20.bin", "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-09-of-20.bin", "transformer.h.28.mlp.dense_h_to_4h.bias": "pytorch_model-09-of-20.bin", "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-09-of-20.bin", "transformer.h.28.mlp.dense_4h_to_h.bias": "pytorch_model-09-of-20.bin", "transformer.h.29.input_layernorm.weight": "pytorch_model-09-of-20.bin", "transformer.h.29.input_layernorm.bias": "pytorch_model-09-of-20.bin", "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-09-of-20.bin", "transformer.h.29.self_attention.query_key_value.bias": "pytorch_model-09-of-20.bin", "transformer.h.29.self_attention.dense.weight": "pytorch_model-09-of-20.bin", "transformer.h.29.self_attention.dense.bias": "pytorch_model-09-of-20.bin", "transformer.h.29.post_attention_layernorm.weight": "pytorch_model-09-of-20.bin", "transformer.h.29.post_attention_layernorm.bias": "pytorch_model-09-of-20.bin", "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-09-of-20.bin", "transformer.h.29.mlp.dense_h_to_4h.bias": "pytorch_model-09-of-20.bin", "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-09-of-20.bin", "transformer.h.29.mlp.dense_4h_to_h.bias": "pytorch_model-09-of-20.bin", "transformer.h.30.input_layernorm.weight": "pytorch_model-09-of-20.bin", "transformer.h.30.input_layernorm.bias": "pytorch_model-09-of-20.bin", "transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-09-of-20.bin", "transformer.h.30.self_attention.query_key_value.bias": "pytorch_model-09-of-20.bin", "transformer.h.30.self_attention.dense.weight": "pytorch_model-09-of-20.bin", "transformer.h.30.self_attention.dense.bias": "pytorch_model-09-of-20.bin", "transformer.h.30.post_attention_layernorm.weight": "pytorch_model-09-of-20.bin", "transformer.h.30.post_attention_layernorm.bias": "pytorch_model-09-of-20.bin", "transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-09-of-20.bin", "transformer.h.30.mlp.dense_h_to_4h.bias": "pytorch_model-09-of-20.bin", "transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-09-of-20.bin", "transformer.h.30.mlp.dense_4h_to_h.bias": "pytorch_model-09-of-20.bin", "transformer.h.31.input_layernorm.weight": "pytorch_model-09-of-20.bin", "transformer.h.31.input_layernorm.bias": "pytorch_model-09-of-20.bin", "transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-09-of-20.bin", "transformer.h.31.self_attention.query_key_value.bias": "pytorch_model-09-of-20.bin", "transformer.h.31.self_attention.dense.weight": "pytorch_model-09-of-20.bin", "transformer.h.31.self_attention.dense.bias": "pytorch_model-09-of-20.bin", "transformer.h.31.post_attention_layernorm.weight": "pytorch_model-09-of-20.bin", "transformer.h.31.post_attention_layernorm.bias": "pytorch_model-09-of-20.bin", "transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-10-of-20.bin", "transformer.h.31.mlp.dense_h_to_4h.bias": "pytorch_model-10-of-20.bin", "transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-10-of-20.bin", "transformer.h.31.mlp.dense_4h_to_h.bias": "pytorch_model-10-of-20.bin", "transformer.h.32.input_layernorm.weight": "pytorch_model-10-of-20.bin", "transformer.h.32.input_layernorm.bias": "pytorch_model-10-of-20.bin", "transformer.h.32.self_attention.query_key_value.weight": "pytorch_model-10-of-20.bin", "transformer.h.32.self_attention.query_key_value.bias": "pytorch_model-10-of-20.bin", "transformer.h.32.self_attention.dense.weight": "pytorch_model-10-of-20.bin", "transformer.h.32.self_attention.dense.bias": "pytorch_model-10-of-20.bin", "transformer.h.32.post_attention_layernorm.weight": "pytorch_model-10-of-20.bin", "transformer.h.32.post_attention_layernorm.bias": "pytorch_model-10-of-20.bin", "transformer.h.32.mlp.dense_h_to_4h.weight": "pytorch_model-10-of-20.bin", "transformer.h.32.mlp.dense_h_to_4h.bias": "pytorch_model-10-of-20.bin", "transformer.h.32.mlp.dense_4h_to_h.weight": "pytorch_model-10-of-20.bin", "transformer.h.32.mlp.dense_4h_to_h.bias": "pytorch_model-10-of-20.bin", "transformer.h.33.input_layernorm.weight": "pytorch_model-10-of-20.bin", "transformer.h.33.input_layernorm.bias": "pytorch_model-10-of-20.bin", "transformer.h.33.self_attention.query_key_value.weight": "pytorch_model-10-of-20.bin", "transformer.h.33.self_attention.query_key_value.bias": "pytorch_model-10-of-20.bin", "transformer.h.33.self_attention.dense.weight": "pytorch_model-10-of-20.bin", "transformer.h.33.self_attention.dense.bias": "pytorch_model-10-of-20.bin", "transformer.h.33.post_attention_layernorm.weight": "pytorch_model-10-of-20.bin", "transformer.h.33.post_attention_layernorm.bias": "pytorch_model-10-of-20.bin", "transformer.h.33.mlp.dense_h_to_4h.weight": "pytorch_model-10-of-20.bin", "transformer.h.33.mlp.dense_h_to_4h.bias": "pytorch_model-10-of-20.bin", "transformer.h.33.mlp.dense_4h_to_h.weight": "pytorch_model-10-of-20.bin", "transformer.h.33.mlp.dense_4h_to_h.bias": "pytorch_model-10-of-20.bin", "transformer.h.34.input_layernorm.weight": "pytorch_model-10-of-20.bin", "transformer.h.34.input_layernorm.bias": "pytorch_model-10-of-20.bin", "transformer.h.34.self_attention.query_key_value.weight": "pytorch_model-10-of-20.bin", "transformer.h.34.self_attention.query_key_value.bias": "pytorch_model-10-of-20.bin", "transformer.h.34.self_attention.dense.weight": "pytorch_model-10-of-20.bin", "transformer.h.34.self_attention.dense.bias": "pytorch_model-10-of-20.bin", "transformer.h.34.post_attention_layernorm.weight": "pytorch_model-10-of-20.bin", "transformer.h.34.post_attention_layernorm.bias": "pytorch_model-10-of-20.bin", "transformer.h.34.mlp.dense_h_to_4h.weight": "pytorch_model-10-of-20.bin", "transformer.h.34.mlp.dense_h_to_4h.bias": "pytorch_model-10-of-20.bin", "transformer.h.34.mlp.dense_4h_to_h.weight": "pytorch_model-10-of-20.bin", "transformer.h.34.mlp.dense_4h_to_h.bias": "pytorch_model-10-of-20.bin", "transformer.h.35.input_layernorm.weight": "pytorch_model-10-of-20.bin", "transformer.h.35.input_layernorm.bias": "pytorch_model-10-of-20.bin", "transformer.h.35.self_attention.query_key_value.weight": "pytorch_model-11-of-20.bin", "transformer.h.35.self_attention.query_key_value.bias": "pytorch_model-11-of-20.bin", "transformer.h.35.self_attention.dense.weight": "pytorch_model-11-of-20.bin", "transformer.h.35.self_attention.dense.bias": "pytorch_model-11-of-20.bin", "transformer.h.35.post_attention_layernorm.weight": "pytorch_model-11-of-20.bin", "transformer.h.35.post_attention_layernorm.bias": "pytorch_model-11-of-20.bin", "transformer.h.35.mlp.dense_h_to_4h.weight": "pytorch_model-11-of-20.bin", "transformer.h.35.mlp.dense_h_to_4h.bias": "pytorch_model-11-of-20.bin", "transformer.h.35.mlp.dense_4h_to_h.weight": "pytorch_model-11-of-20.bin", "transformer.h.35.mlp.dense_4h_to_h.bias": "pytorch_model-11-of-20.bin", "transformer.h.36.input_layernorm.weight": "pytorch_model-11-of-20.bin", "transformer.h.36.input_layernorm.bias": "pytorch_model-11-of-20.bin", "transformer.h.36.self_attention.query_key_value.weight": "pytorch_model-11-of-20.bin", "transformer.h.36.self_attention.query_key_value.bias": "pytorch_model-11-of-20.bin", "transformer.h.36.self_attention.dense.weight": "pytorch_model-11-of-20.bin", "transformer.h.36.self_attention.dense.bias": "pytorch_model-11-of-20.bin", "transformer.h.36.post_attention_layernorm.weight": "pytorch_model-11-of-20.bin", "transformer.h.36.post_attention_layernorm.bias": "pytorch_model-11-of-20.bin", "transformer.h.36.mlp.dense_h_to_4h.weight": "pytorch_model-11-of-20.bin", "transformer.h.36.mlp.dense_h_to_4h.bias": "pytorch_model-11-of-20.bin", "transformer.h.36.mlp.dense_4h_to_h.weight": "pytorch_model-11-of-20.bin", "transformer.h.36.mlp.dense_4h_to_h.bias": "pytorch_model-11-of-20.bin", "transformer.h.37.input_layernorm.weight": "pytorch_model-11-of-20.bin", "transformer.h.37.input_layernorm.bias": "pytorch_model-11-of-20.bin", "transformer.h.37.self_attention.query_key_value.weight": "pytorch_model-11-of-20.bin", "transformer.h.37.self_attention.query_key_value.bias": "pytorch_model-11-of-20.bin", "transformer.h.37.self_attention.dense.weight": "pytorch_model-11-of-20.bin", "transformer.h.37.self_attention.dense.bias": "pytorch_model-11-of-20.bin", "transformer.h.37.post_attention_layernorm.weight": "pytorch_model-11-of-20.bin", "transformer.h.37.post_attention_layernorm.bias": "pytorch_model-11-of-20.bin", "transformer.h.37.mlp.dense_h_to_4h.weight": "pytorch_model-11-of-20.bin", "transformer.h.37.mlp.dense_h_to_4h.bias": "pytorch_model-11-of-20.bin", "transformer.h.37.mlp.dense_4h_to_h.weight": "pytorch_model-11-of-20.bin", "transformer.h.37.mlp.dense_4h_to_h.bias": "pytorch_model-11-of-20.bin", "transformer.h.38.input_layernorm.weight": "pytorch_model-11-of-20.bin", "transformer.h.38.input_layernorm.bias": "pytorch_model-11-of-20.bin", "transformer.h.38.self_attention.query_key_value.weight": "pytorch_model-11-of-20.bin", "transformer.h.38.self_attention.query_key_value.bias": "pytorch_model-11-of-20.bin", "transformer.h.38.self_attention.dense.weight": "pytorch_model-11-of-20.bin", "transformer.h.38.self_attention.dense.bias": "pytorch_model-11-of-20.bin", "transformer.h.38.post_attention_layernorm.weight": "pytorch_model-11-of-20.bin", "transformer.h.38.post_attention_layernorm.bias": "pytorch_model-11-of-20.bin", "transformer.h.38.mlp.dense_h_to_4h.weight": "pytorch_model-11-of-20.bin", "transformer.h.38.mlp.dense_h_to_4h.bias": "pytorch_model-11-of-20.bin", "transformer.h.38.mlp.dense_4h_to_h.weight": "pytorch_model-12-of-20.bin", "transformer.h.38.mlp.dense_4h_to_h.bias": "pytorch_model-12-of-20.bin", "transformer.h.39.input_layernorm.weight": "pytorch_model-12-of-20.bin", "transformer.h.39.input_layernorm.bias": "pytorch_model-12-of-20.bin", "transformer.h.39.self_attention.query_key_value.weight": "pytorch_model-12-of-20.bin", "transformer.h.39.self_attention.query_key_value.bias": "pytorch_model-12-of-20.bin", "transformer.h.39.self_attention.dense.weight": "pytorch_model-12-of-20.bin", "transformer.h.39.self_attention.dense.bias": "pytorch_model-12-of-20.bin", "transformer.h.39.post_attention_layernorm.weight": "pytorch_model-12-of-20.bin", "transformer.h.39.post_attention_layernorm.bias": "pytorch_model-12-of-20.bin", "transformer.h.39.mlp.dense_h_to_4h.weight": "pytorch_model-12-of-20.bin", "transformer.h.39.mlp.dense_h_to_4h.bias": "pytorch_model-12-of-20.bin", "transformer.h.39.mlp.dense_4h_to_h.weight": "pytorch_model-12-of-20.bin", "transformer.h.39.mlp.dense_4h_to_h.bias": "pytorch_model-12-of-20.bin", "transformer.h.40.input_layernorm.weight": "pytorch_model-12-of-20.bin", "transformer.h.40.input_layernorm.bias": "pytorch_model-12-of-20.bin", "transformer.h.40.self_attention.query_key_value.weight": "pytorch_model-12-of-20.bin", "transformer.h.40.self_attention.query_key_value.bias": "pytorch_model-12-of-20.bin", "transformer.h.40.self_attention.dense.weight": "pytorch_model-12-of-20.bin", "transformer.h.40.self_attention.dense.bias": "pytorch_model-12-of-20.bin", "transformer.h.40.post_attention_layernorm.weight": "pytorch_model-12-of-20.bin", "transformer.h.40.post_attention_layernorm.bias": "pytorch_model-12-of-20.bin", "transformer.h.40.mlp.dense_h_to_4h.weight": "pytorch_model-12-of-20.bin", "transformer.h.40.mlp.dense_h_to_4h.bias": "pytorch_model-12-of-20.bin", "transformer.h.40.mlp.dense_4h_to_h.weight": "pytorch_model-12-of-20.bin", "transformer.h.40.mlp.dense_4h_to_h.bias": "pytorch_model-12-of-20.bin", "transformer.h.41.input_layernorm.weight": "pytorch_model-12-of-20.bin", "transformer.h.41.input_layernorm.bias": "pytorch_model-12-of-20.bin", "transformer.h.41.self_attention.query_key_value.weight": "pytorch_model-12-of-20.bin", "transformer.h.41.self_attention.query_key_value.bias": "pytorch_model-12-of-20.bin", "transformer.h.41.self_attention.dense.weight": "pytorch_model-12-of-20.bin", "transformer.h.41.self_attention.dense.bias": "pytorch_model-12-of-20.bin", "transformer.h.41.post_attention_layernorm.weight": "pytorch_model-12-of-20.bin", "transformer.h.41.post_attention_layernorm.bias": "pytorch_model-12-of-20.bin", "transformer.h.41.mlp.dense_h_to_4h.weight": "pytorch_model-12-of-20.bin", "transformer.h.41.mlp.dense_h_to_4h.bias": "pytorch_model-12-of-20.bin", "transformer.h.41.mlp.dense_4h_to_h.weight": "pytorch_model-12-of-20.bin", "transformer.h.41.mlp.dense_4h_to_h.bias": "pytorch_model-12-of-20.bin", "transformer.h.42.input_layernorm.weight": "pytorch_model-12-of-20.bin", "transformer.h.42.input_layernorm.bias": "pytorch_model-12-of-20.bin", "transformer.h.42.self_attention.query_key_value.weight": "pytorch_model-12-of-20.bin", "transformer.h.42.self_attention.query_key_value.bias": "pytorch_model-12-of-20.bin", "transformer.h.42.self_attention.dense.weight": "pytorch_model-12-of-20.bin", "transformer.h.42.self_attention.dense.bias": "pytorch_model-12-of-20.bin", "transformer.h.42.post_attention_layernorm.weight": "pytorch_model-12-of-20.bin", "transformer.h.42.post_attention_layernorm.bias": "pytorch_model-12-of-20.bin", "transformer.h.42.mlp.dense_h_to_4h.weight": "pytorch_model-13-of-20.bin", "transformer.h.42.mlp.dense_h_to_4h.bias": "pytorch_model-13-of-20.bin", "transformer.h.42.mlp.dense_4h_to_h.weight": "pytorch_model-13-of-20.bin", "transformer.h.42.mlp.dense_4h_to_h.bias": "pytorch_model-13-of-20.bin", "transformer.h.43.input_layernorm.weight": "pytorch_model-13-of-20.bin", "transformer.h.43.input_layernorm.bias": "pytorch_model-13-of-20.bin", "transformer.h.43.self_attention.query_key_value.weight": "pytorch_model-13-of-20.bin", "transformer.h.43.self_attention.query_key_value.bias": "pytorch_model-13-of-20.bin", "transformer.h.43.self_attention.dense.weight": "pytorch_model-13-of-20.bin", "transformer.h.43.self_attention.dense.bias": "pytorch_model-13-of-20.bin", "transformer.h.43.post_attention_layernorm.weight": "pytorch_model-13-of-20.bin", "transformer.h.43.post_attention_layernorm.bias": "pytorch_model-13-of-20.bin", "transformer.h.43.mlp.dense_h_to_4h.weight": "pytorch_model-13-of-20.bin", "transformer.h.43.mlp.dense_h_to_4h.bias": "pytorch_model-13-of-20.bin", "transformer.h.43.mlp.dense_4h_to_h.weight": "pytorch_model-13-of-20.bin", "transformer.h.43.mlp.dense_4h_to_h.bias": "pytorch_model-13-of-20.bin", "transformer.h.44.input_layernorm.weight": "pytorch_model-13-of-20.bin", "transformer.h.44.input_layernorm.bias": "pytorch_model-13-of-20.bin", "transformer.h.44.self_attention.query_key_value.weight": "pytorch_model-13-of-20.bin", "transformer.h.44.self_attention.query_key_value.bias": "pytorch_model-13-of-20.bin", "transformer.h.44.self_attention.dense.weight": "pytorch_model-13-of-20.bin", "transformer.h.44.self_attention.dense.bias": "pytorch_model-13-of-20.bin", "transformer.h.44.post_attention_layernorm.weight": "pytorch_model-13-of-20.bin", "transformer.h.44.post_attention_layernorm.bias": "pytorch_model-13-of-20.bin", "transformer.h.44.mlp.dense_h_to_4h.weight": "pytorch_model-13-of-20.bin", "transformer.h.44.mlp.dense_h_to_4h.bias": "pytorch_model-13-of-20.bin", "transformer.h.44.mlp.dense_4h_to_h.weight": "pytorch_model-13-of-20.bin", "transformer.h.44.mlp.dense_4h_to_h.bias": "pytorch_model-13-of-20.bin", "transformer.h.45.input_layernorm.weight": "pytorch_model-13-of-20.bin", "transformer.h.45.input_layernorm.bias": "pytorch_model-13-of-20.bin", "transformer.h.45.self_attention.query_key_value.weight": "pytorch_model-13-of-20.bin", "transformer.h.45.self_attention.query_key_value.bias": "pytorch_model-13-of-20.bin", "transformer.h.45.self_attention.dense.weight": "pytorch_model-13-of-20.bin", "transformer.h.45.self_attention.dense.bias": "pytorch_model-13-of-20.bin", "transformer.h.45.post_attention_layernorm.weight": "pytorch_model-13-of-20.bin", "transformer.h.45.post_attention_layernorm.bias": "pytorch_model-13-of-20.bin", "transformer.h.45.mlp.dense_h_to_4h.weight": "pytorch_model-13-of-20.bin", "transformer.h.45.mlp.dense_h_to_4h.bias": "pytorch_model-13-of-20.bin", "transformer.h.45.mlp.dense_4h_to_h.weight": "pytorch_model-13-of-20.bin", "transformer.h.45.mlp.dense_4h_to_h.bias": "pytorch_model-13-of-20.bin", "transformer.h.46.input_layernorm.weight": "pytorch_model-13-of-20.bin", "transformer.h.46.input_layernorm.bias": "pytorch_model-13-of-20.bin", "transformer.h.46.self_attention.query_key_value.weight": "pytorch_model-14-of-20.bin", "transformer.h.46.self_attention.query_key_value.bias": "pytorch_model-14-of-20.bin", "transformer.h.46.self_attention.dense.weight": "pytorch_model-14-of-20.bin", "transformer.h.46.self_attention.dense.bias": "pytorch_model-14-of-20.bin", "transformer.h.46.post_attention_layernorm.weight": "pytorch_model-14-of-20.bin", "transformer.h.46.post_attention_layernorm.bias": "pytorch_model-14-of-20.bin", "transformer.h.46.mlp.dense_h_to_4h.weight": "pytorch_model-14-of-20.bin", "transformer.h.46.mlp.dense_h_to_4h.bias": "pytorch_model-14-of-20.bin", "transformer.h.46.mlp.dense_4h_to_h.weight": "pytorch_model-14-of-20.bin", "transformer.h.46.mlp.dense_4h_to_h.bias": "pytorch_model-14-of-20.bin", "transformer.h.47.input_layernorm.weight": "pytorch_model-14-of-20.bin", "transformer.h.47.input_layernorm.bias": "pytorch_model-14-of-20.bin", "transformer.h.47.self_attention.query_key_value.weight": "pytorch_model-14-of-20.bin", "transformer.h.47.self_attention.query_key_value.bias": "pytorch_model-14-of-20.bin", "transformer.h.47.self_attention.dense.weight": "pytorch_model-14-of-20.bin", "transformer.h.47.self_attention.dense.bias": "pytorch_model-14-of-20.bin", "transformer.h.47.post_attention_layernorm.weight": "pytorch_model-14-of-20.bin", "transformer.h.47.post_attention_layernorm.bias": "pytorch_model-14-of-20.bin", "transformer.h.47.mlp.dense_h_to_4h.weight": "pytorch_model-14-of-20.bin", "transformer.h.47.mlp.dense_h_to_4h.bias": "pytorch_model-14-of-20.bin", "transformer.h.47.mlp.dense_4h_to_h.weight": "pytorch_model-14-of-20.bin", "transformer.h.47.mlp.dense_4h_to_h.bias": "pytorch_model-14-of-20.bin", "transformer.h.48.input_layernorm.weight": "pytorch_model-14-of-20.bin", "transformer.h.48.input_layernorm.bias": "pytorch_model-14-of-20.bin", "transformer.h.48.self_attention.query_key_value.weight": "pytorch_model-14-of-20.bin", "transformer.h.48.self_attention.query_key_value.bias": "pytorch_model-14-of-20.bin", "transformer.h.48.self_attention.dense.weight": "pytorch_model-14-of-20.bin", "transformer.h.48.self_attention.dense.bias": "pytorch_model-14-of-20.bin", "transformer.h.48.post_attention_layernorm.weight": "pytorch_model-14-of-20.bin", "transformer.h.48.post_attention_layernorm.bias": "pytorch_model-14-of-20.bin", "transformer.h.48.mlp.dense_h_to_4h.weight": "pytorch_model-14-of-20.bin", "transformer.h.48.mlp.dense_h_to_4h.bias": "pytorch_model-14-of-20.bin", "transformer.h.48.mlp.dense_4h_to_h.weight": "pytorch_model-14-of-20.bin", "transformer.h.48.mlp.dense_4h_to_h.bias": "pytorch_model-14-of-20.bin", "transformer.h.49.input_layernorm.weight": "pytorch_model-14-of-20.bin", "transformer.h.49.input_layernorm.bias": "pytorch_model-14-of-20.bin", "transformer.h.49.self_attention.query_key_value.weight": "pytorch_model-14-of-20.bin", "transformer.h.49.self_attention.query_key_value.bias": "pytorch_model-14-of-20.bin", "transformer.h.49.self_attention.dense.weight": "pytorch_model-14-of-20.bin", "transformer.h.49.self_attention.dense.bias": "pytorch_model-14-of-20.bin", "transformer.h.49.post_attention_layernorm.weight": "pytorch_model-14-of-20.bin", "transformer.h.49.post_attention_layernorm.bias": "pytorch_model-14-of-20.bin", "transformer.h.49.mlp.dense_h_to_4h.weight": "pytorch_model-14-of-20.bin", "transformer.h.49.mlp.dense_h_to_4h.bias": "pytorch_model-14-of-20.bin", "transformer.h.49.mlp.dense_4h_to_h.weight": "pytorch_model-15-of-20.bin", "transformer.h.49.mlp.dense_4h_to_h.bias": "pytorch_model-15-of-20.bin", "transformer.h.50.input_layernorm.weight": "pytorch_model-15-of-20.bin", "transformer.h.50.input_layernorm.bias": "pytorch_model-15-of-20.bin", "transformer.h.50.self_attention.query_key_value.weight": "pytorch_model-15-of-20.bin", "transformer.h.50.self_attention.query_key_value.bias": "pytorch_model-15-of-20.bin", "transformer.h.50.self_attention.dense.weight": "pytorch_model-15-of-20.bin", "transformer.h.50.self_attention.dense.bias": "pytorch_model-15-of-20.bin", "transformer.h.50.post_attention_layernorm.weight": "pytorch_model-15-of-20.bin", "transformer.h.50.post_attention_layernorm.bias": "pytorch_model-15-of-20.bin", "transformer.h.50.mlp.dense_h_to_4h.weight": "pytorch_model-15-of-20.bin", "transformer.h.50.mlp.dense_h_to_4h.bias": "pytorch_model-15-of-20.bin", "transformer.h.50.mlp.dense_4h_to_h.weight": "pytorch_model-15-of-20.bin", "transformer.h.50.mlp.dense_4h_to_h.bias": "pytorch_model-15-of-20.bin", "transformer.h.51.input_layernorm.weight": "pytorch_model-15-of-20.bin", "transformer.h.51.input_layernorm.bias": "pytorch_model-15-of-20.bin", "transformer.h.51.self_attention.query_key_value.weight": "pytorch_model-15-of-20.bin", "transformer.h.51.self_attention.query_key_value.bias": "pytorch_model-15-of-20.bin", "transformer.h.51.self_attention.dense.weight": "pytorch_model-15-of-20.bin", "transformer.h.51.self_attention.dense.bias": "pytorch_model-15-of-20.bin", "transformer.h.51.post_attention_layernorm.weight": "pytorch_model-15-of-20.bin", "transformer.h.51.post_attention_layernorm.bias": "pytorch_model-15-of-20.bin", "transformer.h.51.mlp.dense_h_to_4h.weight": "pytorch_model-15-of-20.bin", "transformer.h.51.mlp.dense_h_to_4h.bias": "pytorch_model-15-of-20.bin", "transformer.h.51.mlp.dense_4h_to_h.weight": "pytorch_model-15-of-20.bin", "transformer.h.51.mlp.dense_4h_to_h.bias": "pytorch_model-15-of-20.bin", "transformer.h.52.input_layernorm.weight": "pytorch_model-15-of-20.bin", "transformer.h.52.input_layernorm.bias": "pytorch_model-15-of-20.bin", "transformer.h.52.self_attention.query_key_value.weight": "pytorch_model-15-of-20.bin", "transformer.h.52.self_attention.query_key_value.bias": "pytorch_model-15-of-20.bin", "transformer.h.52.self_attention.dense.weight": "pytorch_model-15-of-20.bin", "transformer.h.52.self_attention.dense.bias": "pytorch_model-15-of-20.bin", "transformer.h.52.post_attention_layernorm.weight": "pytorch_model-15-of-20.bin", "transformer.h.52.post_attention_layernorm.bias": "pytorch_model-15-of-20.bin", "transformer.h.52.mlp.dense_h_to_4h.weight": "pytorch_model-15-of-20.bin", "transformer.h.52.mlp.dense_h_to_4h.bias": "pytorch_model-15-of-20.bin", "transformer.h.52.mlp.dense_4h_to_h.weight": "pytorch_model-15-of-20.bin", "transformer.h.52.mlp.dense_4h_to_h.bias": "pytorch_model-15-of-20.bin", "transformer.h.53.input_layernorm.weight": "pytorch_model-15-of-20.bin", "transformer.h.53.input_layernorm.bias": "pytorch_model-15-of-20.bin", "transformer.h.53.self_attention.query_key_value.weight": "pytorch_model-15-of-20.bin", "transformer.h.53.self_attention.query_key_value.bias": "pytorch_model-15-of-20.bin", "transformer.h.53.self_attention.dense.weight": "pytorch_model-15-of-20.bin", "transformer.h.53.self_attention.dense.bias": "pytorch_model-15-of-20.bin", "transformer.h.53.post_attention_layernorm.weight": "pytorch_model-15-of-20.bin", "transformer.h.53.post_attention_layernorm.bias": "pytorch_model-15-of-20.bin", "transformer.h.53.mlp.dense_h_to_4h.weight": "pytorch_model-16-of-20.bin", "transformer.h.53.mlp.dense_h_to_4h.bias": "pytorch_model-16-of-20.bin", "transformer.h.53.mlp.dense_4h_to_h.weight": "pytorch_model-16-of-20.bin", "transformer.h.53.mlp.dense_4h_to_h.bias": "pytorch_model-16-of-20.bin", "transformer.h.54.input_layernorm.weight": "pytorch_model-16-of-20.bin", "transformer.h.54.input_layernorm.bias": "pytorch_model-16-of-20.bin", "transformer.h.54.self_attention.query_key_value.weight": "pytorch_model-16-of-20.bin", "transformer.h.54.self_attention.query_key_value.bias": "pytorch_model-16-of-20.bin", "transformer.h.54.self_attention.dense.weight": "pytorch_model-16-of-20.bin", "transformer.h.54.self_attention.dense.bias": "pytorch_model-16-of-20.bin", "transformer.h.54.post_attention_layernorm.weight": "pytorch_model-16-of-20.bin", "transformer.h.54.post_attention_layernorm.bias": "pytorch_model-16-of-20.bin", "transformer.h.54.mlp.dense_h_to_4h.weight": "pytorch_model-16-of-20.bin", "transformer.h.54.mlp.dense_h_to_4h.bias": "pytorch_model-16-of-20.bin", "transformer.h.54.mlp.dense_4h_to_h.weight": "pytorch_model-16-of-20.bin", "transformer.h.54.mlp.dense_4h_to_h.bias": "pytorch_model-16-of-20.bin", "transformer.h.55.input_layernorm.weight": "pytorch_model-16-of-20.bin", "transformer.h.55.input_layernorm.bias": "pytorch_model-16-of-20.bin", "transformer.h.55.self_attention.query_key_value.weight": "pytorch_model-16-of-20.bin", "transformer.h.55.self_attention.query_key_value.bias": "pytorch_model-16-of-20.bin", "transformer.h.55.self_attention.dense.weight": "pytorch_model-16-of-20.bin", "transformer.h.55.self_attention.dense.bias": "pytorch_model-16-of-20.bin", "transformer.h.55.post_attention_layernorm.weight": "pytorch_model-16-of-20.bin", "transformer.h.55.post_attention_layernorm.bias": "pytorch_model-16-of-20.bin", "transformer.h.55.mlp.dense_h_to_4h.weight": "pytorch_model-16-of-20.bin", "transformer.h.55.mlp.dense_h_to_4h.bias": "pytorch_model-16-of-20.bin", "transformer.h.55.mlp.dense_4h_to_h.weight": "pytorch_model-16-of-20.bin", "transformer.h.55.mlp.dense_4h_to_h.bias": "pytorch_model-16-of-20.bin", "transformer.h.56.input_layernorm.weight": "pytorch_model-16-of-20.bin", "transformer.h.56.input_layernorm.bias": "pytorch_model-16-of-20.bin", "transformer.h.56.self_attention.query_key_value.weight": "pytorch_model-16-of-20.bin", "transformer.h.56.self_attention.query_key_value.bias": "pytorch_model-16-of-20.bin", "transformer.h.56.self_attention.dense.weight": "pytorch_model-16-of-20.bin", "transformer.h.56.self_attention.dense.bias": "pytorch_model-16-of-20.bin", "transformer.h.56.post_attention_layernorm.weight": "pytorch_model-16-of-20.bin", "transformer.h.56.post_attention_layernorm.bias": "pytorch_model-16-of-20.bin", "transformer.h.56.mlp.dense_h_to_4h.weight": "pytorch_model-16-of-20.bin", "transformer.h.56.mlp.dense_h_to_4h.bias": "pytorch_model-16-of-20.bin", "transformer.h.56.mlp.dense_4h_to_h.weight": "pytorch_model-16-of-20.bin", "transformer.h.56.mlp.dense_4h_to_h.bias": "pytorch_model-16-of-20.bin", "transformer.h.57.input_layernorm.weight": "pytorch_model-16-of-20.bin", "transformer.h.57.input_layernorm.bias": "pytorch_model-16-of-20.bin", "transformer.h.57.self_attention.query_key_value.weight": "pytorch_model-17-of-20.bin", "transformer.h.57.self_attention.query_key_value.bias": "pytorch_model-17-of-20.bin", "transformer.h.57.self_attention.dense.weight": "pytorch_model-17-of-20.bin", "transformer.h.57.self_attention.dense.bias": "pytorch_model-17-of-20.bin", "transformer.h.57.post_attention_layernorm.weight": "pytorch_model-17-of-20.bin", "transformer.h.57.post_attention_layernorm.bias": "pytorch_model-17-of-20.bin", "transformer.h.57.mlp.dense_h_to_4h.weight": "pytorch_model-17-of-20.bin", "transformer.h.57.mlp.dense_h_to_4h.bias": "pytorch_model-17-of-20.bin", "transformer.h.57.mlp.dense_4h_to_h.weight": "pytorch_model-17-of-20.bin", "transformer.h.57.mlp.dense_4h_to_h.bias": "pytorch_model-17-of-20.bin", "transformer.h.58.input_layernorm.weight": "pytorch_model-17-of-20.bin", "transformer.h.58.input_layernorm.bias": "pytorch_model-17-of-20.bin", "transformer.h.58.self_attention.query_key_value.weight": "pytorch_model-17-of-20.bin", "transformer.h.58.self_attention.query_key_value.bias": "pytorch_model-17-of-20.bin", "transformer.h.58.self_attention.dense.weight": "pytorch_model-17-of-20.bin", "transformer.h.58.self_attention.dense.bias": "pytorch_model-17-of-20.bin", "transformer.h.58.post_attention_layernorm.weight": "pytorch_model-17-of-20.bin", "transformer.h.58.post_attention_layernorm.bias": "pytorch_model-17-of-20.bin", "transformer.h.58.mlp.dense_h_to_4h.weight": "pytorch_model-17-of-20.bin", "transformer.h.58.mlp.dense_h_to_4h.bias": "pytorch_model-17-of-20.bin", "transformer.h.58.mlp.dense_4h_to_h.weight": "pytorch_model-17-of-20.bin", "transformer.h.58.mlp.dense_4h_to_h.bias": "pytorch_model-17-of-20.bin", "transformer.h.59.input_layernorm.weight": "pytorch_model-17-of-20.bin", "transformer.h.59.input_layernorm.bias": "pytorch_model-17-of-20.bin", "transformer.h.59.self_attention.query_key_value.weight": "pytorch_model-17-of-20.bin", "transformer.h.59.self_attention.query_key_value.bias": "pytorch_model-17-of-20.bin", "transformer.h.59.self_attention.dense.weight": "pytorch_model-17-of-20.bin", "transformer.h.59.self_attention.dense.bias": "pytorch_model-17-of-20.bin", "transformer.h.59.post_attention_layernorm.weight": "pytorch_model-17-of-20.bin", "transformer.h.59.post_attention_layernorm.bias": "pytorch_model-17-of-20.bin", "transformer.h.59.mlp.dense_h_to_4h.weight": "pytorch_model-17-of-20.bin", "transformer.h.59.mlp.dense_h_to_4h.bias": "pytorch_model-17-of-20.bin", "transformer.h.59.mlp.dense_4h_to_h.weight": "pytorch_model-17-of-20.bin", "transformer.h.59.mlp.dense_4h_to_h.bias": "pytorch_model-17-of-20.bin", "transformer.h.60.input_layernorm.weight": "pytorch_model-17-of-20.bin", "transformer.h.60.input_layernorm.bias": "pytorch_model-17-of-20.bin", "transformer.h.60.self_attention.query_key_value.weight": "pytorch_model-17-of-20.bin", "transformer.h.60.self_attention.query_key_value.bias": "pytorch_model-17-of-20.bin", "transformer.h.60.self_attention.dense.weight": "pytorch_model-17-of-20.bin", "transformer.h.60.self_attention.dense.bias": "pytorch_model-17-of-20.bin", "transformer.h.60.post_attention_layernorm.weight": "pytorch_model-17-of-20.bin", "transformer.h.60.post_attention_layernorm.bias": "pytorch_model-17-of-20.bin", "transformer.h.60.mlp.dense_h_to_4h.weight": "pytorch_model-17-of-20.bin", "transformer.h.60.mlp.dense_h_to_4h.bias": "pytorch_model-17-of-20.bin", "transformer.h.60.mlp.dense_4h_to_h.weight": "pytorch_model-18-of-20.bin", "transformer.h.60.mlp.dense_4h_to_h.bias": "pytorch_model-18-of-20.bin", "transformer.h.61.input_layernorm.weight": "pytorch_model-18-of-20.bin", "transformer.h.61.input_layernorm.bias": "pytorch_model-18-of-20.bin", "transformer.h.61.self_attention.query_key_value.weight": "pytorch_model-18-of-20.bin", "transformer.h.61.self_attention.query_key_value.bias": "pytorch_model-18-of-20.bin", "transformer.h.61.self_attention.dense.weight": "pytorch_model-18-of-20.bin", "transformer.h.61.self_attention.dense.bias": "pytorch_model-18-of-20.bin", "transformer.h.61.post_attention_layernorm.weight": "pytorch_model-18-of-20.bin", "transformer.h.61.post_attention_layernorm.bias": "pytorch_model-18-of-20.bin", "transformer.h.61.mlp.dense_h_to_4h.weight": "pytorch_model-18-of-20.bin", "transformer.h.61.mlp.dense_h_to_4h.bias": "pytorch_model-18-of-20.bin", "transformer.h.61.mlp.dense_4h_to_h.weight": "pytorch_model-18-of-20.bin", "transformer.h.61.mlp.dense_4h_to_h.bias": "pytorch_model-18-of-20.bin", "transformer.h.62.input_layernorm.weight": "pytorch_model-18-of-20.bin", "transformer.h.62.input_layernorm.bias": "pytorch_model-18-of-20.bin", "transformer.h.62.self_attention.query_key_value.weight": "pytorch_model-18-of-20.bin", "transformer.h.62.self_attention.query_key_value.bias": "pytorch_model-18-of-20.bin", "transformer.h.62.self_attention.dense.weight": "pytorch_model-18-of-20.bin", "transformer.h.62.self_attention.dense.bias": "pytorch_model-18-of-20.bin", "transformer.h.62.post_attention_layernorm.weight": "pytorch_model-18-of-20.bin", "transformer.h.62.post_attention_layernorm.bias": "pytorch_model-18-of-20.bin", "transformer.h.62.mlp.dense_h_to_4h.weight": "pytorch_model-18-of-20.bin", "transformer.h.62.mlp.dense_h_to_4h.bias": "pytorch_model-18-of-20.bin", "transformer.h.62.mlp.dense_4h_to_h.weight": "pytorch_model-18-of-20.bin", "transformer.h.62.mlp.dense_4h_to_h.bias": "pytorch_model-18-of-20.bin", "transformer.h.63.input_layernorm.weight": "pytorch_model-18-of-20.bin", "transformer.h.63.input_layernorm.bias": "pytorch_model-18-of-20.bin", "transformer.h.63.self_attention.query_key_value.weight": "pytorch_model-18-of-20.bin", "transformer.h.63.self_attention.query_key_value.bias": "pytorch_model-18-of-20.bin", "transformer.h.63.self_attention.dense.weight": "pytorch_model-18-of-20.bin", "transformer.h.63.self_attention.dense.bias": "pytorch_model-18-of-20.bin", "transformer.h.63.post_attention_layernorm.weight": "pytorch_model-18-of-20.bin", "transformer.h.63.post_attention_layernorm.bias": "pytorch_model-18-of-20.bin", "transformer.h.63.mlp.dense_h_to_4h.weight": "pytorch_model-18-of-20.bin", "transformer.h.63.mlp.dense_h_to_4h.bias": "pytorch_model-18-of-20.bin", "transformer.h.63.mlp.dense_4h_to_h.weight": "pytorch_model-18-of-20.bin", "transformer.h.63.mlp.dense_4h_to_h.bias": "pytorch_model-18-of-20.bin", "transformer.h.64.input_layernorm.weight": "pytorch_model-18-of-20.bin", "transformer.h.64.input_layernorm.bias": "pytorch_model-18-of-20.bin", "transformer.h.64.self_attention.query_key_value.weight": "pytorch_model-18-of-20.bin", "transformer.h.64.self_attention.query_key_value.bias": "pytorch_model-18-of-20.bin", "transformer.h.64.self_attention.dense.weight": "pytorch_model-18-of-20.bin", "transformer.h.64.self_attention.dense.bias": "pytorch_model-18-of-20.bin", "transformer.h.64.post_attention_layernorm.weight": "pytorch_model-18-of-20.bin", "transformer.h.64.post_attention_layernorm.bias": "pytorch_model-18-of-20.bin", "transformer.h.64.mlp.dense_h_to_4h.weight": "pytorch_model-19-of-20.bin", "transformer.h.64.mlp.dense_h_to_4h.bias": "pytorch_model-19-of-20.bin", "transformer.h.64.mlp.dense_4h_to_h.weight": "pytorch_model-19-of-20.bin", "transformer.h.64.mlp.dense_4h_to_h.bias": "pytorch_model-19-of-20.bin", "transformer.h.65.input_layernorm.weight": "pytorch_model-19-of-20.bin", "transformer.h.65.input_layernorm.bias": "pytorch_model-19-of-20.bin", "transformer.h.65.self_attention.query_key_value.weight": "pytorch_model-19-of-20.bin", "transformer.h.65.self_attention.query_key_value.bias": "pytorch_model-19-of-20.bin", "transformer.h.65.self_attention.dense.weight": "pytorch_model-19-of-20.bin", "transformer.h.65.self_attention.dense.bias": "pytorch_model-19-of-20.bin", "transformer.h.65.post_attention_layernorm.weight": "pytorch_model-19-of-20.bin", "transformer.h.65.post_attention_layernorm.bias": "pytorch_model-19-of-20.bin", "transformer.h.65.mlp.dense_h_to_4h.weight": "pytorch_model-19-of-20.bin", "transformer.h.65.mlp.dense_h_to_4h.bias": "pytorch_model-19-of-20.bin", "transformer.h.65.mlp.dense_4h_to_h.weight": "pytorch_model-19-of-20.bin", "transformer.h.65.mlp.dense_4h_to_h.bias": "pytorch_model-19-of-20.bin", "transformer.h.66.input_layernorm.weight": "pytorch_model-19-of-20.bin", "transformer.h.66.input_layernorm.bias": "pytorch_model-19-of-20.bin", "transformer.h.66.self_attention.query_key_value.weight": "pytorch_model-19-of-20.bin", "transformer.h.66.self_attention.query_key_value.bias": "pytorch_model-19-of-20.bin", "transformer.h.66.self_attention.dense.weight": "pytorch_model-19-of-20.bin", "transformer.h.66.self_attention.dense.bias": "pytorch_model-19-of-20.bin", "transformer.h.66.post_attention_layernorm.weight": "pytorch_model-19-of-20.bin", "transformer.h.66.post_attention_layernorm.bias": "pytorch_model-19-of-20.bin", "transformer.h.66.mlp.dense_h_to_4h.weight": "pytorch_model-19-of-20.bin", "transformer.h.66.mlp.dense_h_to_4h.bias": "pytorch_model-19-of-20.bin", "transformer.h.66.mlp.dense_4h_to_h.weight": "pytorch_model-19-of-20.bin", "transformer.h.66.mlp.dense_4h_to_h.bias": "pytorch_model-19-of-20.bin", "transformer.h.67.input_layernorm.weight": "pytorch_model-19-of-20.bin", "transformer.h.67.input_layernorm.bias": "pytorch_model-19-of-20.bin", "transformer.h.67.self_attention.query_key_value.weight": "pytorch_model-19-of-20.bin", "transformer.h.67.self_attention.query_key_value.bias": "pytorch_model-19-of-20.bin", "transformer.h.67.self_attention.dense.weight": "pytorch_model-19-of-20.bin", "transformer.h.67.self_attention.dense.bias": "pytorch_model-19-of-20.bin", "transformer.h.67.post_attention_layernorm.weight": "pytorch_model-19-of-20.bin", "transformer.h.67.post_attention_layernorm.bias": "pytorch_model-19-of-20.bin", "transformer.h.67.mlp.dense_h_to_4h.weight": "pytorch_model-19-of-20.bin", "transformer.h.67.mlp.dense_h_to_4h.bias": "pytorch_model-19-of-20.bin", "transformer.h.67.mlp.dense_4h_to_h.weight": "pytorch_model-19-of-20.bin", "transformer.h.67.mlp.dense_4h_to_h.bias": "pytorch_model-19-of-20.bin", "transformer.h.68.input_layernorm.weight": "pytorch_model-19-of-20.bin", "transformer.h.68.input_layernorm.bias": "pytorch_model-19-of-20.bin", "transformer.h.68.self_attention.query_key_value.weight": "pytorch_model-20-of-20.bin", "transformer.h.68.self_attention.query_key_value.bias": "pytorch_model-20-of-20.bin", "transformer.h.68.self_attention.dense.weight": "pytorch_model-20-of-20.bin", "transformer.h.68.self_attention.dense.bias": "pytorch_model-20-of-20.bin", "transformer.h.68.post_attention_layernorm.weight": "pytorch_model-20-of-20.bin", "transformer.h.68.post_attention_layernorm.bias": "pytorch_model-20-of-20.bin", "transformer.h.68.mlp.dense_h_to_4h.weight": "pytorch_model-20-of-20.bin", "transformer.h.68.mlp.dense_h_to_4h.bias": "pytorch_model-20-of-20.bin", "transformer.h.68.mlp.dense_4h_to_h.weight": "pytorch_model-20-of-20.bin", "transformer.h.68.mlp.dense_4h_to_h.bias": "pytorch_model-20-of-20.bin", "transformer.h.69.input_layernorm.weight": "pytorch_model-20-of-20.bin", "transformer.h.69.input_layernorm.bias": "pytorch_model-20-of-20.bin", "transformer.h.69.self_attention.query_key_value.weight": "pytorch_model-20-of-20.bin", "transformer.h.69.self_attention.query_key_value.bias": "pytorch_model-20-of-20.bin", "transformer.h.69.self_attention.dense.weight": "pytorch_model-20-of-20.bin", "transformer.h.69.self_attention.dense.bias": "pytorch_model-20-of-20.bin", "transformer.h.69.post_attention_layernorm.weight": "pytorch_model-20-of-20.bin", "transformer.h.69.post_attention_layernorm.bias": "pytorch_model-20-of-20.bin", "transformer.h.69.mlp.dense_h_to_4h.weight": "pytorch_model-20-of-20.bin", "transformer.h.69.mlp.dense_h_to_4h.bias": "pytorch_model-20-of-20.bin", "transformer.h.69.mlp.dense_4h_to_h.weight": "pytorch_model-20-of-20.bin", "transformer.h.69.mlp.dense_4h_to_h.bias": "pytorch_model-20-of-20.bin", "transformer.ln_f.weight": "pytorch_model-20-of-20.bin", "transformer.ln_f.bias": "pytorch_model-20-of-20.bin", "lm_head.weight": "pytorch_model-20-of-20.bin"}}

pytorch_model.bin.sambatensor_index.json

@@ -0,0 +1 @@
+{"transformer.word_embeddings.weight": "bloomforcausallm__transformer__word_embeddings__weight", "transformer.word_embeddings_layernorm.weight": "bloomforcausallm__transformer__word_embeddings_layernorm__weight", "transformer.word_embeddings_layernorm.bias": "bloomforcausallm__transformer__word_embeddings_layernorm__bias", "transformer.h.0.input_layernorm.weight": "bloomforcausallm__transformer__h__0__input_layernorm__weight", "transformer.h.0.input_layernorm.bias": "bloomforcausallm__transformer__h__0__input_layernorm__bias", "transformer.h.0.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__0__self_attention__query_key_value__weight", "transformer.h.0.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__0__self_attention__query_key_value__bias", "transformer.h.0.self_attention.dense.weight": "bloomforcausallm__transformer__h__0__self_attention__dense__weight", "transformer.h.0.self_attention.dense.bias": "bloomforcausallm__transformer__h__0__self_attention__dense__bias", "transformer.h.0.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__0__post_attention_layernorm__weight", "transformer.h.0.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__0__post_attention_layernorm__bias", "transformer.h.0.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__0__mlp__dense_h_to_4h__weight", "transformer.h.0.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__0__mlp__dense_h_to_4h__bias", "transformer.h.0.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__0__mlp__dense_4h_to_h__weight", "transformer.h.0.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__0__mlp__dense_4h_to_h__bias", "transformer.h.1.input_layernorm.weight": "bloomforcausallm__transformer__h__1__input_layernorm__weight", "transformer.h.1.input_layernorm.bias": "bloomforcausallm__transformer__h__1__input_layernorm__bias", "transformer.h.1.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__1__self_attention__query_key_value__weight", "transformer.h.1.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__1__self_attention__query_key_value__bias", "transformer.h.1.self_attention.dense.weight": "bloomforcausallm__transformer__h__1__self_attention__dense__weight", "transformer.h.1.self_attention.dense.bias": "bloomforcausallm__transformer__h__1__self_attention__dense__bias", "transformer.h.1.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__1__post_attention_layernorm__weight", "transformer.h.1.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__1__post_attention_layernorm__bias", "transformer.h.1.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__1__mlp__dense_h_to_4h__weight", "transformer.h.1.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__1__mlp__dense_h_to_4h__bias", "transformer.h.1.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__1__mlp__dense_4h_to_h__weight", "transformer.h.1.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__1__mlp__dense_4h_to_h__bias", "transformer.h.2.input_layernorm.weight": "bloomforcausallm__transformer__h__2__input_layernorm__weight", "transformer.h.2.input_layernorm.bias": "bloomforcausallm__transformer__h__2__input_layernorm__bias", "transformer.h.2.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__2__self_attention__query_key_value__weight", "transformer.h.2.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__2__self_attention__query_key_value__bias", "transformer.h.2.self_attention.dense.weight": "bloomforcausallm__transformer__h__2__self_attention__dense__weight", "transformer.h.2.self_attention.dense.bias": "bloomforcausallm__transformer__h__2__self_attention__dense__bias", "transformer.h.2.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__2__post_attention_layernorm__weight", "transformer.h.2.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__2__post_attention_layernorm__bias", "transformer.h.2.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__2__mlp__dense_h_to_4h__weight", "transformer.h.2.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__2__mlp__dense_h_to_4h__bias", "transformer.h.2.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__2__mlp__dense_4h_to_h__weight", "transformer.h.2.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__2__mlp__dense_4h_to_h__bias", "transformer.h.3.input_layernorm.weight": "bloomforcausallm__transformer__h__3__input_layernorm__weight", "transformer.h.3.input_layernorm.bias": "bloomforcausallm__transformer__h__3__input_layernorm__bias", "transformer.h.3.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__3__self_attention__query_key_value__weight", "transformer.h.3.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__3__self_attention__query_key_value__bias", "transformer.h.3.self_attention.dense.weight": "bloomforcausallm__transformer__h__3__self_attention__dense__weight", "transformer.h.3.self_attention.dense.bias": "bloomforcausallm__transformer__h__3__self_attention__dense__bias", "transformer.h.3.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__3__post_attention_layernorm__weight", "transformer.h.3.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__3__post_attention_layernorm__bias", "transformer.h.3.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__3__mlp__dense_h_to_4h__weight", "transformer.h.3.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__3__mlp__dense_h_to_4h__bias", "transformer.h.3.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__3__mlp__dense_4h_to_h__weight", "transformer.h.3.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__3__mlp__dense_4h_to_h__bias", "transformer.h.4.input_layernorm.weight": "bloomforcausallm__transformer__h__4__input_layernorm__weight", "transformer.h.4.input_layernorm.bias": "bloomforcausallm__transformer__h__4__input_layernorm__bias", "transformer.h.4.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__4__self_attention__query_key_value__weight", "transformer.h.4.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__4__self_attention__query_key_value__bias", "transformer.h.4.self_attention.dense.weight": "bloomforcausallm__transformer__h__4__self_attention__dense__weight", "transformer.h.4.self_attention.dense.bias": "bloomforcausallm__transformer__h__4__self_attention__dense__bias", "transformer.h.4.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__4__post_attention_layernorm__weight", "transformer.h.4.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__4__post_attention_layernorm__bias", "transformer.h.4.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__4__mlp__dense_h_to_4h__weight", "transformer.h.4.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__4__mlp__dense_h_to_4h__bias", "transformer.h.4.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__4__mlp__dense_4h_to_h__weight", "transformer.h.4.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__4__mlp__dense_4h_to_h__bias", "transformer.h.5.input_layernorm.weight": "bloomforcausallm__transformer__h__5__input_layernorm__weight", "transformer.h.5.input_layernorm.bias": "bloomforcausallm__transformer__h__5__input_layernorm__bias", "transformer.h.5.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__5__self_attention__query_key_value__weight", "transformer.h.5.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__5__self_attention__query_key_value__bias", "transformer.h.5.self_attention.dense.weight": "bloomforcausallm__transformer__h__5__self_attention__dense__weight", "transformer.h.5.self_attention.dense.bias": "bloomforcausallm__transformer__h__5__self_attention__dense__bias", "transformer.h.5.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__5__post_attention_layernorm__weight", "transformer.h.5.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__5__post_attention_layernorm__bias", "transformer.h.5.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__5__mlp__dense_h_to_4h__weight", "transformer.h.5.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__5__mlp__dense_h_to_4h__bias", "transformer.h.5.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__5__mlp__dense_4h_to_h__weight", "transformer.h.5.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__5__mlp__dense_4h_to_h__bias", "transformer.h.6.input_layernorm.weight": "bloomforcausallm__transformer__h__6__input_layernorm__weight", "transformer.h.6.input_layernorm.bias": "bloomforcausallm__transformer__h__6__input_layernorm__bias", "transformer.h.6.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__6__self_attention__query_key_value__weight", "transformer.h.6.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__6__self_attention__query_key_value__bias", "transformer.h.6.self_attention.dense.weight": "bloomforcausallm__transformer__h__6__self_attention__dense__weight", "transformer.h.6.self_attention.dense.bias": "bloomforcausallm__transformer__h__6__self_attention__dense__bias", "transformer.h.6.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__6__post_attention_layernorm__weight", "transformer.h.6.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__6__post_attention_layernorm__bias", "transformer.h.6.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__6__mlp__dense_h_to_4h__weight", "transformer.h.6.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__6__mlp__dense_h_to_4h__bias", "transformer.h.6.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__6__mlp__dense_4h_to_h__weight", "transformer.h.6.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__6__mlp__dense_4h_to_h__bias", "transformer.h.7.input_layernorm.weight": "bloomforcausallm__transformer__h__7__input_layernorm__weight", "transformer.h.7.input_layernorm.bias": "bloomforcausallm__transformer__h__7__input_layernorm__bias", "transformer.h.7.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__7__self_attention__query_key_value__weight", "transformer.h.7.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__7__self_attention__query_key_value__bias", "transformer.h.7.self_attention.dense.weight": "bloomforcausallm__transformer__h__7__self_attention__dense__weight", "transformer.h.7.self_attention.dense.bias": "bloomforcausallm__transformer__h__7__self_attention__dense__bias", "transformer.h.7.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__7__post_attention_layernorm__weight", "transformer.h.7.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__7__post_attention_layernorm__bias", "transformer.h.7.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__7__mlp__dense_h_to_4h__weight", "transformer.h.7.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__7__mlp__dense_h_to_4h__bias", "transformer.h.7.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__7__mlp__dense_4h_to_h__weight", "transformer.h.7.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__7__mlp__dense_4h_to_h__bias", "transformer.h.8.input_layernorm.weight": "bloomforcausallm__transformer__h__8__input_layernorm__weight", "transformer.h.8.input_layernorm.bias": "bloomforcausallm__transformer__h__8__input_layernorm__bias", "transformer.h.8.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__8__self_attention__query_key_value__weight", "transformer.h.8.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__8__self_attention__query_key_value__bias", "transformer.h.8.self_attention.dense.weight": "bloomforcausallm__transformer__h__8__self_attention__dense__weight", "transformer.h.8.self_attention.dense.bias": "bloomforcausallm__transformer__h__8__self_attention__dense__bias", "transformer.h.8.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__8__post_attention_layernorm__weight", "transformer.h.8.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__8__post_attention_layernorm__bias", "transformer.h.8.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__8__mlp__dense_h_to_4h__weight", "transformer.h.8.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__8__mlp__dense_h_to_4h__bias", "transformer.h.8.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__8__mlp__dense_4h_to_h__weight", "transformer.h.8.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__8__mlp__dense_4h_to_h__bias", "transformer.h.9.input_layernorm.weight": "bloomforcausallm__transformer__h__9__input_layernorm__weight", "transformer.h.9.input_layernorm.bias": "bloomforcausallm__transformer__h__9__input_layernorm__bias", "transformer.h.9.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__9__self_attention__query_key_value__weight", "transformer.h.9.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__9__self_attention__query_key_value__bias", "transformer.h.9.self_attention.dense.weight": "bloomforcausallm__transformer__h__9__self_attention__dense__weight", "transformer.h.9.self_attention.dense.bias": "bloomforcausallm__transformer__h__9__self_attention__dense__bias", "transformer.h.9.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__9__post_attention_layernorm__weight", "transformer.h.9.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__9__post_attention_layernorm__bias", "transformer.h.9.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__9__mlp__dense_h_to_4h__weight", "transformer.h.9.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__9__mlp__dense_h_to_4h__bias", "transformer.h.9.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__9__mlp__dense_4h_to_h__weight", "transformer.h.9.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__9__mlp__dense_4h_to_h__bias", "transformer.h.10.input_layernorm.weight": "bloomforcausallm__transformer__h__10__input_layernorm__weight", "transformer.h.10.input_layernorm.bias": "bloomforcausallm__transformer__h__10__input_layernorm__bias", "transformer.h.10.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__10__self_attention__query_key_value__weight", "transformer.h.10.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__10__self_attention__query_key_value__bias", "transformer.h.10.self_attention.dense.weight": "bloomforcausallm__transformer__h__10__self_attention__dense__weight", "transformer.h.10.self_attention.dense.bias": "bloomforcausallm__transformer__h__10__self_attention__dense__bias", "transformer.h.10.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__10__post_attention_layernorm__weight", "transformer.h.10.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__10__post_attention_layernorm__bias", "transformer.h.10.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__10__mlp__dense_h_to_4h__weight", "transformer.h.10.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__10__mlp__dense_h_to_4h__bias", "transformer.h.10.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__10__mlp__dense_4h_to_h__weight", "transformer.h.10.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__10__mlp__dense_4h_to_h__bias", "transformer.h.11.input_layernorm.weight": "bloomforcausallm__transformer__h__11__input_layernorm__weight", "transformer.h.11.input_layernorm.bias": "bloomforcausallm__transformer__h__11__input_layernorm__bias", "transformer.h.11.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__11__self_attention__query_key_value__weight", "transformer.h.11.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__11__self_attention__query_key_value__bias", "transformer.h.11.self_attention.dense.weight": "bloomforcausallm__transformer__h__11__self_attention__dense__weight", "transformer.h.11.self_attention.dense.bias": "bloomforcausallm__transformer__h__11__self_attention__dense__bias", "transformer.h.11.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__11__post_attention_layernorm__weight", "transformer.h.11.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__11__post_attention_layernorm__bias", "transformer.h.11.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__11__mlp__dense_h_to_4h__weight", "transformer.h.11.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__11__mlp__dense_h_to_4h__bias", "transformer.h.11.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__11__mlp__dense_4h_to_h__weight", "transformer.h.11.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__11__mlp__dense_4h_to_h__bias", "transformer.h.12.input_layernorm.weight": "bloomforcausallm__transformer__h__12__input_layernorm__weight", "transformer.h.12.input_layernorm.bias": "bloomforcausallm__transformer__h__12__input_layernorm__bias", "transformer.h.12.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__12__self_attention__query_key_value__weight", "transformer.h.12.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__12__self_attention__query_key_value__bias", "transformer.h.12.self_attention.dense.weight": "bloomforcausallm__transformer__h__12__self_attention__dense__weight", "transformer.h.12.self_attention.dense.bias": "bloomforcausallm__transformer__h__12__self_attention__dense__bias", "transformer.h.12.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__12__post_attention_layernorm__weight", "transformer.h.12.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__12__post_attention_layernorm__bias", "transformer.h.12.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__12__mlp__dense_h_to_4h__weight", "transformer.h.12.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__12__mlp__dense_h_to_4h__bias", "transformer.h.12.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__12__mlp__dense_4h_to_h__weight", "transformer.h.12.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__12__mlp__dense_4h_to_h__bias", "transformer.h.13.input_layernorm.weight": "bloomforcausallm__transformer__h__13__input_layernorm__weight", "transformer.h.13.input_layernorm.bias": "bloomforcausallm__transformer__h__13__input_layernorm__bias", "transformer.h.13.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__13__self_attention__query_key_value__weight", "transformer.h.13.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__13__self_attention__query_key_value__bias", "transformer.h.13.self_attention.dense.weight": "bloomforcausallm__transformer__h__13__self_attention__dense__weight", "transformer.h.13.self_attention.dense.bias": "bloomforcausallm__transformer__h__13__self_attention__dense__bias", "transformer.h.13.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__13__post_attention_layernorm__weight", "transformer.h.13.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__13__post_attention_layernorm__bias", "transformer.h.13.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__13__mlp__dense_h_to_4h__weight", "transformer.h.13.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__13__mlp__dense_h_to_4h__bias", "transformer.h.13.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__13__mlp__dense_4h_to_h__weight", "transformer.h.13.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__13__mlp__dense_4h_to_h__bias", "transformer.h.14.input_layernorm.weight": "bloomforcausallm__transformer__h__14__input_layernorm__weight", "transformer.h.14.input_layernorm.bias": "bloomforcausallm__transformer__h__14__input_layernorm__bias", "transformer.h.14.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__14__self_attention__query_key_value__weight", "transformer.h.14.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__14__self_attention__query_key_value__bias", "transformer.h.14.self_attention.dense.weight": "bloomforcausallm__transformer__h__14__self_attention__dense__weight", "transformer.h.14.self_attention.dense.bias": "bloomforcausallm__transformer__h__14__self_attention__dense__bias", "transformer.h.14.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__14__post_attention_layernorm__weight", "transformer.h.14.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__14__post_attention_layernorm__bias", "transformer.h.14.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__14__mlp__dense_h_to_4h__weight", "transformer.h.14.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__14__mlp__dense_h_to_4h__bias", "transformer.h.14.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__14__mlp__dense_4h_to_h__weight", "transformer.h.14.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__14__mlp__dense_4h_to_h__bias", "transformer.h.15.input_layernorm.weight": "bloomforcausallm__transformer__h__15__input_layernorm__weight", "transformer.h.15.input_layernorm.bias": "bloomforcausallm__transformer__h__15__input_layernorm__bias", "transformer.h.15.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__15__self_attention__query_key_value__weight", "transformer.h.15.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__15__self_attention__query_key_value__bias", "transformer.h.15.self_attention.dense.weight": "bloomforcausallm__transformer__h__15__self_attention__dense__weight", "transformer.h.15.self_attention.dense.bias": "bloomforcausallm__transformer__h__15__self_attention__dense__bias", "transformer.h.15.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__15__post_attention_layernorm__weight", "transformer.h.15.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__15__post_attention_layernorm__bias", "transformer.h.15.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__15__mlp__dense_h_to_4h__weight", "transformer.h.15.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__15__mlp__dense_h_to_4h__bias", "transformer.h.15.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__15__mlp__dense_4h_to_h__weight", "transformer.h.15.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__15__mlp__dense_4h_to_h__bias", "transformer.h.16.input_layernorm.weight": "bloomforcausallm__transformer__h__16__input_layernorm__weight", "transformer.h.16.input_layernorm.bias": "bloomforcausallm__transformer__h__16__input_layernorm__bias", "transformer.h.16.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__16__self_attention__query_key_value__weight", "transformer.h.16.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__16__self_attention__query_key_value__bias", "transformer.h.16.self_attention.dense.weight": "bloomforcausallm__transformer__h__16__self_attention__dense__weight", "transformer.h.16.self_attention.dense.bias": "bloomforcausallm__transformer__h__16__self_attention__dense__bias", "transformer.h.16.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__16__post_attention_layernorm__weight", "transformer.h.16.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__16__post_attention_layernorm__bias", "transformer.h.16.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__16__mlp__dense_h_to_4h__weight", "transformer.h.16.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__16__mlp__dense_h_to_4h__bias", "transformer.h.16.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__16__mlp__dense_4h_to_h__weight", "transformer.h.16.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__16__mlp__dense_4h_to_h__bias", "transformer.h.17.input_layernorm.weight": "bloomforcausallm__transformer__h__17__input_layernorm__weight", "transformer.h.17.input_layernorm.bias": "bloomforcausallm__transformer__h__17__input_layernorm__bias", "transformer.h.17.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__17__self_attention__query_key_value__weight", "transformer.h.17.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__17__self_attention__query_key_value__bias", "transformer.h.17.self_attention.dense.weight": "bloomforcausallm__transformer__h__17__self_attention__dense__weight", "transformer.h.17.self_attention.dense.bias": "bloomforcausallm__transformer__h__17__self_attention__dense__bias", "transformer.h.17.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__17__post_attention_layernorm__weight", "transformer.h.17.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__17__post_attention_layernorm__bias", "transformer.h.17.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__17__mlp__dense_h_to_4h__weight", "transformer.h.17.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__17__mlp__dense_h_to_4h__bias", "transformer.h.17.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__17__mlp__dense_4h_to_h__weight", "transformer.h.17.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__17__mlp__dense_4h_to_h__bias", "transformer.h.18.input_layernorm.weight": "bloomforcausallm__transformer__h__18__input_layernorm__weight", "transformer.h.18.input_layernorm.bias": "bloomforcausallm__transformer__h__18__input_layernorm__bias", "transformer.h.18.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__18__self_attention__query_key_value__weight", "transformer.h.18.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__18__self_attention__query_key_value__bias", "transformer.h.18.self_attention.dense.weight": "bloomforcausallm__transformer__h__18__self_attention__dense__weight", "transformer.h.18.self_attention.dense.bias": "bloomforcausallm__transformer__h__18__self_attention__dense__bias", "transformer.h.18.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__18__post_attention_layernorm__weight", "transformer.h.18.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__18__post_attention_layernorm__bias", "transformer.h.18.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__18__mlp__dense_h_to_4h__weight", "transformer.h.18.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__18__mlp__dense_h_to_4h__bias", "transformer.h.18.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__18__mlp__dense_4h_to_h__weight", "transformer.h.18.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__18__mlp__dense_4h_to_h__bias", "transformer.h.19.input_layernorm.weight": "bloomforcausallm__transformer__h__19__input_layernorm__weight", "transformer.h.19.input_layernorm.bias": "bloomforcausallm__transformer__h__19__input_layernorm__bias", "transformer.h.19.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__19__self_attention__query_key_value__weight", "transformer.h.19.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__19__self_attention__query_key_value__bias", "transformer.h.19.self_attention.dense.weight": "bloomforcausallm__transformer__h__19__self_attention__dense__weight", "transformer.h.19.self_attention.dense.bias": "bloomforcausallm__transformer__h__19__self_attention__dense__bias", "transformer.h.19.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__19__post_attention_layernorm__weight", "transformer.h.19.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__19__post_attention_layernorm__bias", "transformer.h.19.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__19__mlp__dense_h_to_4h__weight", "transformer.h.19.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__19__mlp__dense_h_to_4h__bias", "transformer.h.19.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__19__mlp__dense_4h_to_h__weight", "transformer.h.19.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__19__mlp__dense_4h_to_h__bias", "transformer.h.20.input_layernorm.weight": "bloomforcausallm__transformer__h__20__input_layernorm__weight", "transformer.h.20.input_layernorm.bias": "bloomforcausallm__transformer__h__20__input_layernorm__bias", "transformer.h.20.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__20__self_attention__query_key_value__weight", "transformer.h.20.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__20__self_attention__query_key_value__bias", "transformer.h.20.self_attention.dense.weight": "bloomforcausallm__transformer__h__20__self_attention__dense__weight", "transformer.h.20.self_attention.dense.bias": "bloomforcausallm__transformer__h__20__self_attention__dense__bias", "transformer.h.20.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__20__post_attention_layernorm__weight", "transformer.h.20.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__20__post_attention_layernorm__bias", "transformer.h.20.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__20__mlp__dense_h_to_4h__weight", "transformer.h.20.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__20__mlp__dense_h_to_4h__bias", "transformer.h.20.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__20__mlp__dense_4h_to_h__weight", "transformer.h.20.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__20__mlp__dense_4h_to_h__bias", "transformer.h.21.input_layernorm.weight": "bloomforcausallm__transformer__h__21__input_layernorm__weight", "transformer.h.21.input_layernorm.bias": "bloomforcausallm__transformer__h__21__input_layernorm__bias", "transformer.h.21.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__21__self_attention__query_key_value__weight", "transformer.h.21.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__21__self_attention__query_key_value__bias", "transformer.h.21.self_attention.dense.weight": "bloomforcausallm__transformer__h__21__self_attention__dense__weight", "transformer.h.21.self_attention.dense.bias": "bloomforcausallm__transformer__h__21__self_attention__dense__bias", "transformer.h.21.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__21__post_attention_layernorm__weight", "transformer.h.21.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__21__post_attention_layernorm__bias", "transformer.h.21.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__21__mlp__dense_h_to_4h__weight", "transformer.h.21.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__21__mlp__dense_h_to_4h__bias", "transformer.h.21.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__21__mlp__dense_4h_to_h__weight", "transformer.h.21.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__21__mlp__dense_4h_to_h__bias", "transformer.h.22.input_layernorm.weight": "bloomforcausallm__transformer__h__22__input_layernorm__weight", "transformer.h.22.input_layernorm.bias": "bloomforcausallm__transformer__h__22__input_layernorm__bias", "transformer.h.22.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__22__self_attention__query_key_value__weight", "transformer.h.22.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__22__self_attention__query_key_value__bias", "transformer.h.22.self_attention.dense.weight": "bloomforcausallm__transformer__h__22__self_attention__dense__weight", "transformer.h.22.self_attention.dense.bias": "bloomforcausallm__transformer__h__22__self_attention__dense__bias", "transformer.h.22.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__22__post_attention_layernorm__weight", "transformer.h.22.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__22__post_attention_layernorm__bias", "transformer.h.22.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__22__mlp__dense_h_to_4h__weight", "transformer.h.22.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__22__mlp__dense_h_to_4h__bias", "transformer.h.22.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__22__mlp__dense_4h_to_h__weight", "transformer.h.22.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__22__mlp__dense_4h_to_h__bias", "transformer.h.23.input_layernorm.weight": "bloomforcausallm__transformer__h__23__input_layernorm__weight", "transformer.h.23.input_layernorm.bias": "bloomforcausallm__transformer__h__23__input_layernorm__bias", "transformer.h.23.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__23__self_attention__query_key_value__weight", "transformer.h.23.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__23__self_attention__query_key_value__bias", "transformer.h.23.self_attention.dense.weight": "bloomforcausallm__transformer__h__23__self_attention__dense__weight", "transformer.h.23.self_attention.dense.bias": "bloomforcausallm__transformer__h__23__self_attention__dense__bias", "transformer.h.23.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__23__post_attention_layernorm__weight", "transformer.h.23.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__23__post_attention_layernorm__bias", "transformer.h.23.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__23__mlp__dense_h_to_4h__weight", "transformer.h.23.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__23__mlp__dense_h_to_4h__bias", "transformer.h.23.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__23__mlp__dense_4h_to_h__weight", "transformer.h.23.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__23__mlp__dense_4h_to_h__bias", "transformer.h.24.input_layernorm.weight": "bloomforcausallm__transformer__h__24__input_layernorm__weight", "transformer.h.24.input_layernorm.bias": "bloomforcausallm__transformer__h__24__input_layernorm__bias", "transformer.h.24.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__24__self_attention__query_key_value__weight", "transformer.h.24.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__24__self_attention__query_key_value__bias", "transformer.h.24.self_attention.dense.weight": "bloomforcausallm__transformer__h__24__self_attention__dense__weight", "transformer.h.24.self_attention.dense.bias": "bloomforcausallm__transformer__h__24__self_attention__dense__bias", "transformer.h.24.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__24__post_attention_layernorm__weight", "transformer.h.24.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__24__post_attention_layernorm__bias", "transformer.h.24.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__24__mlp__dense_h_to_4h__weight", "transformer.h.24.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__24__mlp__dense_h_to_4h__bias", "transformer.h.24.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__24__mlp__dense_4h_to_h__weight", "transformer.h.24.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__24__mlp__dense_4h_to_h__bias", "transformer.h.25.input_layernorm.weight": "bloomforcausallm__transformer__h__25__input_layernorm__weight", "transformer.h.25.input_layernorm.bias": "bloomforcausallm__transformer__h__25__input_layernorm__bias", "transformer.h.25.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__25__self_attention__query_key_value__weight", "transformer.h.25.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__25__self_attention__query_key_value__bias", "transformer.h.25.self_attention.dense.weight": "bloomforcausallm__transformer__h__25__self_attention__dense__weight", "transformer.h.25.self_attention.dense.bias": "bloomforcausallm__transformer__h__25__self_attention__dense__bias", "transformer.h.25.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__25__post_attention_layernorm__weight", "transformer.h.25.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__25__post_attention_layernorm__bias", "transformer.h.25.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__25__mlp__dense_h_to_4h__weight", "transformer.h.25.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__25__mlp__dense_h_to_4h__bias", "transformer.h.25.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__25__mlp__dense_4h_to_h__weight", "transformer.h.25.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__25__mlp__dense_4h_to_h__bias", "transformer.h.26.input_layernorm.weight": "bloomforcausallm__transformer__h__26__input_layernorm__weight", "transformer.h.26.input_layernorm.bias": "bloomforcausallm__transformer__h__26__input_layernorm__bias", "transformer.h.26.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__26__self_attention__query_key_value__weight", "transformer.h.26.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__26__self_attention__query_key_value__bias", "transformer.h.26.self_attention.dense.weight": "bloomforcausallm__transformer__h__26__self_attention__dense__weight", "transformer.h.26.self_attention.dense.bias": "bloomforcausallm__transformer__h__26__self_attention__dense__bias", "transformer.h.26.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__26__post_attention_layernorm__weight", "transformer.h.26.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__26__post_attention_layernorm__bias", "transformer.h.26.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__26__mlp__dense_h_to_4h__weight", "transformer.h.26.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__26__mlp__dense_h_to_4h__bias", "transformer.h.26.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__26__mlp__dense_4h_to_h__weight", "transformer.h.26.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__26__mlp__dense_4h_to_h__bias", "transformer.h.27.input_layernorm.weight": "bloomforcausallm__transformer__h__27__input_layernorm__weight", "transformer.h.27.input_layernorm.bias": "bloomforcausallm__transformer__h__27__input_layernorm__bias", "transformer.h.27.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__27__self_attention__query_key_value__weight", "transformer.h.27.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__27__self_attention__query_key_value__bias", "transformer.h.27.self_attention.dense.weight": "bloomforcausallm__transformer__h__27__self_attention__dense__weight", "transformer.h.27.self_attention.dense.bias": "bloomforcausallm__transformer__h__27__self_attention__dense__bias", "transformer.h.27.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__27__post_attention_layernorm__weight", "transformer.h.27.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__27__post_attention_layernorm__bias", "transformer.h.27.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__27__mlp__dense_h_to_4h__weight", "transformer.h.27.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__27__mlp__dense_h_to_4h__bias", "transformer.h.27.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__27__mlp__dense_4h_to_h__weight", "transformer.h.27.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__27__mlp__dense_4h_to_h__bias", "transformer.h.28.input_layernorm.weight": "bloomforcausallm__transformer__h__28__input_layernorm__weight", "transformer.h.28.input_layernorm.bias": "bloomforcausallm__transformer__h__28__input_layernorm__bias", "transformer.h.28.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__28__self_attention__query_key_value__weight", "transformer.h.28.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__28__self_attention__query_key_value__bias", "transformer.h.28.self_attention.dense.weight": "bloomforcausallm__transformer__h__28__self_attention__dense__weight", "transformer.h.28.self_attention.dense.bias": "bloomforcausallm__transformer__h__28__self_attention__dense__bias", "transformer.h.28.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__28__post_attention_layernorm__weight", "transformer.h.28.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__28__post_attention_layernorm__bias", "transformer.h.28.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__28__mlp__dense_h_to_4h__weight", "transformer.h.28.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__28__mlp__dense_h_to_4h__bias", "transformer.h.28.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__28__mlp__dense_4h_to_h__weight", "transformer.h.28.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__28__mlp__dense_4h_to_h__bias", "transformer.h.29.input_layernorm.weight": "bloomforcausallm__transformer__h__29__input_layernorm__weight", "transformer.h.29.input_layernorm.bias": "bloomforcausallm__transformer__h__29__input_layernorm__bias", "transformer.h.29.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__29__self_attention__query_key_value__weight", "transformer.h.29.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__29__self_attention__query_key_value__bias", "transformer.h.29.self_attention.dense.weight": "bloomforcausallm__transformer__h__29__self_attention__dense__weight", "transformer.h.29.self_attention.dense.bias": "bloomforcausallm__transformer__h__29__self_attention__dense__bias", "transformer.h.29.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__29__post_attention_layernorm__weight", "transformer.h.29.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__29__post_attention_layernorm__bias", "transformer.h.29.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__29__mlp__dense_h_to_4h__weight", "transformer.h.29.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__29__mlp__dense_h_to_4h__bias", "transformer.h.29.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__29__mlp__dense_4h_to_h__weight", "transformer.h.29.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__29__mlp__dense_4h_to_h__bias", "transformer.h.30.input_layernorm.weight": "bloomforcausallm__transformer__h__30__input_layernorm__weight", "transformer.h.30.input_layernorm.bias": "bloomforcausallm__transformer__h__30__input_layernorm__bias", "transformer.h.30.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__30__self_attention__query_key_value__weight", "transformer.h.30.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__30__self_attention__query_key_value__bias", "transformer.h.30.self_attention.dense.weight": "bloomforcausallm__transformer__h__30__self_attention__dense__weight", "transformer.h.30.self_attention.dense.bias": "bloomforcausallm__transformer__h__30__self_attention__dense__bias", "transformer.h.30.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__30__post_attention_layernorm__weight", "transformer.h.30.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__30__post_attention_layernorm__bias", "transformer.h.30.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__30__mlp__dense_h_to_4h__weight", "transformer.h.30.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__30__mlp__dense_h_to_4h__bias", "transformer.h.30.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__30__mlp__dense_4h_to_h__weight", "transformer.h.30.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__30__mlp__dense_4h_to_h__bias", "transformer.h.31.input_layernorm.weight": "bloomforcausallm__transformer__h__31__input_layernorm__weight", "transformer.h.31.input_layernorm.bias": "bloomforcausallm__transformer__h__31__input_layernorm__bias", "transformer.h.31.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__31__self_attention__query_key_value__weight", "transformer.h.31.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__31__self_attention__query_key_value__bias", "transformer.h.31.self_attention.dense.weight": "bloomforcausallm__transformer__h__31__self_attention__dense__weight", "transformer.h.31.self_attention.dense.bias": "bloomforcausallm__transformer__h__31__self_attention__dense__bias", "transformer.h.31.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__31__post_attention_layernorm__weight", "transformer.h.31.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__31__post_attention_layernorm__bias", "transformer.h.31.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__31__mlp__dense_h_to_4h__weight", "transformer.h.31.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__31__mlp__dense_h_to_4h__bias", "transformer.h.31.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__31__mlp__dense_4h_to_h__weight", "transformer.h.31.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__31__mlp__dense_4h_to_h__bias", "transformer.h.32.input_layernorm.weight": "bloomforcausallm__transformer__h__32__input_layernorm__weight", "transformer.h.32.input_layernorm.bias": "bloomforcausallm__transformer__h__32__input_layernorm__bias", "transformer.h.32.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__32__self_attention__query_key_value__weight", "transformer.h.32.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__32__self_attention__query_key_value__bias", "transformer.h.32.self_attention.dense.weight": "bloomforcausallm__transformer__h__32__self_attention__dense__weight", "transformer.h.32.self_attention.dense.bias": "bloomforcausallm__transformer__h__32__self_attention__dense__bias", "transformer.h.32.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__32__post_attention_layernorm__weight", "transformer.h.32.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__32__post_attention_layernorm__bias", "transformer.h.32.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__32__mlp__dense_h_to_4h__weight", "transformer.h.32.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__32__mlp__dense_h_to_4h__bias", "transformer.h.32.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__32__mlp__dense_4h_to_h__weight", "transformer.h.32.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__32__mlp__dense_4h_to_h__bias", "transformer.h.33.input_layernorm.weight": "bloomforcausallm__transformer__h__33__input_layernorm__weight", "transformer.h.33.input_layernorm.bias": "bloomforcausallm__transformer__h__33__input_layernorm__bias", "transformer.h.33.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__33__self_attention__query_key_value__weight", "transformer.h.33.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__33__self_attention__query_key_value__bias", "transformer.h.33.self_attention.dense.weight": "bloomforcausallm__transformer__h__33__self_attention__dense__weight", "transformer.h.33.self_attention.dense.bias": "bloomforcausallm__transformer__h__33__self_attention__dense__bias", "transformer.h.33.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__33__post_attention_layernorm__weight", "transformer.h.33.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__33__post_attention_layernorm__bias", "transformer.h.33.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__33__mlp__dense_h_to_4h__weight", "transformer.h.33.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__33__mlp__dense_h_to_4h__bias", "transformer.h.33.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__33__mlp__dense_4h_to_h__weight", "transformer.h.33.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__33__mlp__dense_4h_to_h__bias", "transformer.h.34.input_layernorm.weight": "bloomforcausallm__transformer__h__34__input_layernorm__weight", "transformer.h.34.input_layernorm.bias": "bloomforcausallm__transformer__h__34__input_layernorm__bias", "transformer.h.34.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__34__self_attention__query_key_value__weight", "transformer.h.34.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__34__self_attention__query_key_value__bias", "transformer.h.34.self_attention.dense.weight": "bloomforcausallm__transformer__h__34__self_attention__dense__weight", "transformer.h.34.self_attention.dense.bias": "bloomforcausallm__transformer__h__34__self_attention__dense__bias", "transformer.h.34.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__34__post_attention_layernorm__weight", "transformer.h.34.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__34__post_attention_layernorm__bias", "transformer.h.34.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__34__mlp__dense_h_to_4h__weight", "transformer.h.34.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__34__mlp__dense_h_to_4h__bias", "transformer.h.34.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__34__mlp__dense_4h_to_h__weight", "transformer.h.34.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__34__mlp__dense_4h_to_h__bias", "transformer.h.35.input_layernorm.weight": "bloomforcausallm__transformer__h__35__input_layernorm__weight", "transformer.h.35.input_layernorm.bias": "bloomforcausallm__transformer__h__35__input_layernorm__bias", "transformer.h.35.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__35__self_attention__query_key_value__weight", "transformer.h.35.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__35__self_attention__query_key_value__bias", "transformer.h.35.self_attention.dense.weight": "bloomforcausallm__transformer__h__35__self_attention__dense__weight", "transformer.h.35.self_attention.dense.bias": "bloomforcausallm__transformer__h__35__self_attention__dense__bias", "transformer.h.35.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__35__post_attention_layernorm__weight", "transformer.h.35.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__35__post_attention_layernorm__bias", "transformer.h.35.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__35__mlp__dense_h_to_4h__weight", "transformer.h.35.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__35__mlp__dense_h_to_4h__bias", "transformer.h.35.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__35__mlp__dense_4h_to_h__weight", "transformer.h.35.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__35__mlp__dense_4h_to_h__bias", "transformer.h.36.input_layernorm.weight": "bloomforcausallm__transformer__h__36__input_layernorm__weight", "transformer.h.36.input_layernorm.bias": "bloomforcausallm__transformer__h__36__input_layernorm__bias", "transformer.h.36.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__36__self_attention__query_key_value__weight", "transformer.h.36.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__36__self_attention__query_key_value__bias", "transformer.h.36.self_attention.dense.weight": "bloomforcausallm__transformer__h__36__self_attention__dense__weight", "transformer.h.36.self_attention.dense.bias": "bloomforcausallm__transformer__h__36__self_attention__dense__bias", "transformer.h.36.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__36__post_attention_layernorm__weight", "transformer.h.36.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__36__post_attention_layernorm__bias", "transformer.h.36.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__36__mlp__dense_h_to_4h__weight", "transformer.h.36.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__36__mlp__dense_h_to_4h__bias", "transformer.h.36.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__36__mlp__dense_4h_to_h__weight", "transformer.h.36.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__36__mlp__dense_4h_to_h__bias", "transformer.h.37.input_layernorm.weight": "bloomforcausallm__transformer__h__37__input_layernorm__weight", "transformer.h.37.input_layernorm.bias": "bloomforcausallm__transformer__h__37__input_layernorm__bias", "transformer.h.37.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__37__self_attention__query_key_value__weight", "transformer.h.37.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__37__self_attention__query_key_value__bias", "transformer.h.37.self_attention.dense.weight": "bloomforcausallm__transformer__h__37__self_attention__dense__weight", "transformer.h.37.self_attention.dense.bias": "bloomforcausallm__transformer__h__37__self_attention__dense__bias", "transformer.h.37.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__37__post_attention_layernorm__weight", "transformer.h.37.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__37__post_attention_layernorm__bias", "transformer.h.37.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__37__mlp__dense_h_to_4h__weight", "transformer.h.37.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__37__mlp__dense_h_to_4h__bias", "transformer.h.37.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__37__mlp__dense_4h_to_h__weight", "transformer.h.37.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__37__mlp__dense_4h_to_h__bias", "transformer.h.38.input_layernorm.weight": "bloomforcausallm__transformer__h__38__input_layernorm__weight", "transformer.h.38.input_layernorm.bias": "bloomforcausallm__transformer__h__38__input_layernorm__bias", "transformer.h.38.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__38__self_attention__query_key_value__weight", "transformer.h.38.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__38__self_attention__query_key_value__bias", "transformer.h.38.self_attention.dense.weight": "bloomforcausallm__transformer__h__38__self_attention__dense__weight", "transformer.h.38.self_attention.dense.bias": "bloomforcausallm__transformer__h__38__self_attention__dense__bias", "transformer.h.38.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__38__post_attention_layernorm__weight", "transformer.h.38.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__38__post_attention_layernorm__bias", "transformer.h.38.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__38__mlp__dense_h_to_4h__weight", "transformer.h.38.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__38__mlp__dense_h_to_4h__bias", "transformer.h.38.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__38__mlp__dense_4h_to_h__weight", "transformer.h.38.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__38__mlp__dense_4h_to_h__bias", "transformer.h.39.input_layernorm.weight": "bloomforcausallm__transformer__h__39__input_layernorm__weight", "transformer.h.39.input_layernorm.bias": "bloomforcausallm__transformer__h__39__input_layernorm__bias", "transformer.h.39.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__39__self_attention__query_key_value__weight", "transformer.h.39.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__39__self_attention__query_key_value__bias", "transformer.h.39.self_attention.dense.weight": "bloomforcausallm__transformer__h__39__self_attention__dense__weight", "transformer.h.39.self_attention.dense.bias": "bloomforcausallm__transformer__h__39__self_attention__dense__bias", "transformer.h.39.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__39__post_attention_layernorm__weight", "transformer.h.39.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__39__post_attention_layernorm__bias", "transformer.h.39.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__39__mlp__dense_h_to_4h__weight", "transformer.h.39.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__39__mlp__dense_h_to_4h__bias", "transformer.h.39.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__39__mlp__dense_4h_to_h__weight", "transformer.h.39.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__39__mlp__dense_4h_to_h__bias", "transformer.h.40.input_layernorm.weight": "bloomforcausallm__transformer__h__40__input_layernorm__weight", "transformer.h.40.input_layernorm.bias": "bloomforcausallm__transformer__h__40__input_layernorm__bias", "transformer.h.40.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__40__self_attention__query_key_value__weight", "transformer.h.40.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__40__self_attention__query_key_value__bias", "transformer.h.40.self_attention.dense.weight": "bloomforcausallm__transformer__h__40__self_attention__dense__weight", "transformer.h.40.self_attention.dense.bias": "bloomforcausallm__transformer__h__40__self_attention__dense__bias", "transformer.h.40.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__40__post_attention_layernorm__weight", "transformer.h.40.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__40__post_attention_layernorm__bias", "transformer.h.40.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__40__mlp__dense_h_to_4h__weight", "transformer.h.40.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__40__mlp__dense_h_to_4h__bias", "transformer.h.40.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__40__mlp__dense_4h_to_h__weight", "transformer.h.40.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__40__mlp__dense_4h_to_h__bias", "transformer.h.41.input_layernorm.weight": "bloomforcausallm__transformer__h__41__input_layernorm__weight", "transformer.h.41.input_layernorm.bias": "bloomforcausallm__transformer__h__41__input_layernorm__bias", "transformer.h.41.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__41__self_attention__query_key_value__weight", "transformer.h.41.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__41__self_attention__query_key_value__bias", "transformer.h.41.self_attention.dense.weight": "bloomforcausallm__transformer__h__41__self_attention__dense__weight", "transformer.h.41.self_attention.dense.bias": "bloomforcausallm__transformer__h__41__self_attention__dense__bias", "transformer.h.41.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__41__post_attention_layernorm__weight", "transformer.h.41.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__41__post_attention_layernorm__bias", "transformer.h.41.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__41__mlp__dense_h_to_4h__weight", "transformer.h.41.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__41__mlp__dense_h_to_4h__bias", "transformer.h.41.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__41__mlp__dense_4h_to_h__weight", "transformer.h.41.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__41__mlp__dense_4h_to_h__bias", "transformer.h.42.input_layernorm.weight": "bloomforcausallm__transformer__h__42__input_layernorm__weight", "transformer.h.42.input_layernorm.bias": "bloomforcausallm__transformer__h__42__input_layernorm__bias", "transformer.h.42.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__42__self_attention__query_key_value__weight", "transformer.h.42.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__42__self_attention__query_key_value__bias", "transformer.h.42.self_attention.dense.weight": "bloomforcausallm__transformer__h__42__self_attention__dense__weight", "transformer.h.42.self_attention.dense.bias": "bloomforcausallm__transformer__h__42__self_attention__dense__bias", "transformer.h.42.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__42__post_attention_layernorm__weight", "transformer.h.42.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__42__post_attention_layernorm__bias", "transformer.h.42.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__42__mlp__dense_h_to_4h__weight", "transformer.h.42.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__42__mlp__dense_h_to_4h__bias", "transformer.h.42.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__42__mlp__dense_4h_to_h__weight", "transformer.h.42.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__42__mlp__dense_4h_to_h__bias", "transformer.h.43.input_layernorm.weight": "bloomforcausallm__transformer__h__43__input_layernorm__weight", "transformer.h.43.input_layernorm.bias": "bloomforcausallm__transformer__h__43__input_layernorm__bias", "transformer.h.43.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__43__self_attention__query_key_value__weight", "transformer.h.43.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__43__self_attention__query_key_value__bias", "transformer.h.43.self_attention.dense.weight": "bloomforcausallm__transformer__h__43__self_attention__dense__weight", "transformer.h.43.self_attention.dense.bias": "bloomforcausallm__transformer__h__43__self_attention__dense__bias", "transformer.h.43.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__43__post_attention_layernorm__weight", "transformer.h.43.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__43__post_attention_layernorm__bias", "transformer.h.43.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__43__mlp__dense_h_to_4h__weight", "transformer.h.43.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__43__mlp__dense_h_to_4h__bias", "transformer.h.43.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__43__mlp__dense_4h_to_h__weight", "transformer.h.43.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__43__mlp__dense_4h_to_h__bias", "transformer.h.44.input_layernorm.weight": "bloomforcausallm__transformer__h__44__input_layernorm__weight", "transformer.h.44.input_layernorm.bias": "bloomforcausallm__transformer__h__44__input_layernorm__bias", "transformer.h.44.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__44__self_attention__query_key_value__weight", "transformer.h.44.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__44__self_attention__query_key_value__bias", "transformer.h.44.self_attention.dense.weight": "bloomforcausallm__transformer__h__44__self_attention__dense__weight", "transformer.h.44.self_attention.dense.bias": "bloomforcausallm__transformer__h__44__self_attention__dense__bias", "transformer.h.44.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__44__post_attention_layernorm__weight", "transformer.h.44.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__44__post_attention_layernorm__bias", "transformer.h.44.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__44__mlp__dense_h_to_4h__weight", "transformer.h.44.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__44__mlp__dense_h_to_4h__bias", "transformer.h.44.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__44__mlp__dense_4h_to_h__weight", "transformer.h.44.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__44__mlp__dense_4h_to_h__bias", "transformer.h.45.input_layernorm.weight": "bloomforcausallm__transformer__h__45__input_layernorm__weight", "transformer.h.45.input_layernorm.bias": "bloomforcausallm__transformer__h__45__input_layernorm__bias", "transformer.h.45.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__45__self_attention__query_key_value__weight", "transformer.h.45.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__45__self_attention__query_key_value__bias", "transformer.h.45.self_attention.dense.weight": "bloomforcausallm__transformer__h__45__self_attention__dense__weight", "transformer.h.45.self_attention.dense.bias": "bloomforcausallm__transformer__h__45__self_attention__dense__bias", "transformer.h.45.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__45__post_attention_layernorm__weight", "transformer.h.45.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__45__post_attention_layernorm__bias", "transformer.h.45.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__45__mlp__dense_h_to_4h__weight", "transformer.h.45.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__45__mlp__dense_h_to_4h__bias", "transformer.h.45.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__45__mlp__dense_4h_to_h__weight", "transformer.h.45.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__45__mlp__dense_4h_to_h__bias", "transformer.h.46.input_layernorm.weight": "bloomforcausallm__transformer__h__46__input_layernorm__weight", "transformer.h.46.input_layernorm.bias": "bloomforcausallm__transformer__h__46__input_layernorm__bias", "transformer.h.46.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__46__self_attention__query_key_value__weight", "transformer.h.46.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__46__self_attention__query_key_value__bias", "transformer.h.46.self_attention.dense.weight": "bloomforcausallm__transformer__h__46__self_attention__dense__weight", "transformer.h.46.self_attention.dense.bias": "bloomforcausallm__transformer__h__46__self_attention__dense__bias", "transformer.h.46.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__46__post_attention_layernorm__weight", "transformer.h.46.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__46__post_attention_layernorm__bias", "transformer.h.46.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__46__mlp__dense_h_to_4h__weight", "transformer.h.46.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__46__mlp__dense_h_to_4h__bias", "transformer.h.46.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__46__mlp__dense_4h_to_h__weight", "transformer.h.46.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__46__mlp__dense_4h_to_h__bias", "transformer.h.47.input_layernorm.weight": "bloomforcausallm__transformer__h__47__input_layernorm__weight", "transformer.h.47.input_layernorm.bias": "bloomforcausallm__transformer__h__47__input_layernorm__bias", "transformer.h.47.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__47__self_attention__query_key_value__weight", "transformer.h.47.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__47__self_attention__query_key_value__bias", "transformer.h.47.self_attention.dense.weight": "bloomforcausallm__transformer__h__47__self_attention__dense__weight", "transformer.h.47.self_attention.dense.bias": "bloomforcausallm__transformer__h__47__self_attention__dense__bias", "transformer.h.47.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__47__post_attention_layernorm__weight", "transformer.h.47.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__47__post_attention_layernorm__bias", "transformer.h.47.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__47__mlp__dense_h_to_4h__weight", "transformer.h.47.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__47__mlp__dense_h_to_4h__bias", "transformer.h.47.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__47__mlp__dense_4h_to_h__weight", "transformer.h.47.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__47__mlp__dense_4h_to_h__bias", "transformer.h.48.input_layernorm.weight": "bloomforcausallm__transformer__h__48__input_layernorm__weight", "transformer.h.48.input_layernorm.bias": "bloomforcausallm__transformer__h__48__input_layernorm__bias", "transformer.h.48.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__48__self_attention__query_key_value__weight", "transformer.h.48.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__48__self_attention__query_key_value__bias", "transformer.h.48.self_attention.dense.weight": "bloomforcausallm__transformer__h__48__self_attention__dense__weight", "transformer.h.48.self_attention.dense.bias": "bloomforcausallm__transformer__h__48__self_attention__dense__bias", "transformer.h.48.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__48__post_attention_layernorm__weight", "transformer.h.48.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__48__post_attention_layernorm__bias", "transformer.h.48.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__48__mlp__dense_h_to_4h__weight", "transformer.h.48.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__48__mlp__dense_h_to_4h__bias", "transformer.h.48.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__48__mlp__dense_4h_to_h__weight", "transformer.h.48.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__48__mlp__dense_4h_to_h__bias", "transformer.h.49.input_layernorm.weight": "bloomforcausallm__transformer__h__49__input_layernorm__weight", "transformer.h.49.input_layernorm.bias": "bloomforcausallm__transformer__h__49__input_layernorm__bias", "transformer.h.49.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__49__self_attention__query_key_value__weight", "transformer.h.49.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__49__self_attention__query_key_value__bias", "transformer.h.49.self_attention.dense.weight": "bloomforcausallm__transformer__h__49__self_attention__dense__weight", "transformer.h.49.self_attention.dense.bias": "bloomforcausallm__transformer__h__49__self_attention__dense__bias", "transformer.h.49.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__49__post_attention_layernorm__weight", "transformer.h.49.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__49__post_attention_layernorm__bias", "transformer.h.49.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__49__mlp__dense_h_to_4h__weight", "transformer.h.49.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__49__mlp__dense_h_to_4h__bias", "transformer.h.49.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__49__mlp__dense_4h_to_h__weight", "transformer.h.49.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__49__mlp__dense_4h_to_h__bias", "transformer.h.50.input_layernorm.weight": "bloomforcausallm__transformer__h__50__input_layernorm__weight", "transformer.h.50.input_layernorm.bias": "bloomforcausallm__transformer__h__50__input_layernorm__bias", "transformer.h.50.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__50__self_attention__query_key_value__weight", "transformer.h.50.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__50__self_attention__query_key_value__bias", "transformer.h.50.self_attention.dense.weight": "bloomforcausallm__transformer__h__50__self_attention__dense__weight", "transformer.h.50.self_attention.dense.bias": "bloomforcausallm__transformer__h__50__self_attention__dense__bias", "transformer.h.50.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__50__post_attention_layernorm__weight", "transformer.h.50.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__50__post_attention_layernorm__bias", "transformer.h.50.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__50__mlp__dense_h_to_4h__weight", "transformer.h.50.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__50__mlp__dense_h_to_4h__bias", "transformer.h.50.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__50__mlp__dense_4h_to_h__weight", "transformer.h.50.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__50__mlp__dense_4h_to_h__bias", "transformer.h.51.input_layernorm.weight": "bloomforcausallm__transformer__h__51__input_layernorm__weight", "transformer.h.51.input_layernorm.bias": "bloomforcausallm__transformer__h__51__input_layernorm__bias", "transformer.h.51.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__51__self_attention__query_key_value__weight", "transformer.h.51.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__51__self_attention__query_key_value__bias", "transformer.h.51.self_attention.dense.weight": "bloomforcausallm__transformer__h__51__self_attention__dense__weight", "transformer.h.51.self_attention.dense.bias": "bloomforcausallm__transformer__h__51__self_attention__dense__bias", "transformer.h.51.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__51__post_attention_layernorm__weight", "transformer.h.51.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__51__post_attention_layernorm__bias", "transformer.h.51.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__51__mlp__dense_h_to_4h__weight", "transformer.h.51.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__51__mlp__dense_h_to_4h__bias", "transformer.h.51.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__51__mlp__dense_4h_to_h__weight", "transformer.h.51.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__51__mlp__dense_4h_to_h__bias", "transformer.h.52.input_layernorm.weight": "bloomforcausallm__transformer__h__52__input_layernorm__weight", "transformer.h.52.input_layernorm.bias": "bloomforcausallm__transformer__h__52__input_layernorm__bias", "transformer.h.52.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__52__self_attention__query_key_value__weight", "transformer.h.52.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__52__self_attention__query_key_value__bias", "transformer.h.52.self_attention.dense.weight": "bloomforcausallm__transformer__h__52__self_attention__dense__weight", "transformer.h.52.self_attention.dense.bias": "bloomforcausallm__transformer__h__52__self_attention__dense__bias", "transformer.h.52.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__52__post_attention_layernorm__weight", "transformer.h.52.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__52__post_attention_layernorm__bias", "transformer.h.52.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__52__mlp__dense_h_to_4h__weight", "transformer.h.52.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__52__mlp__dense_h_to_4h__bias", "transformer.h.52.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__52__mlp__dense_4h_to_h__weight", "transformer.h.52.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__52__mlp__dense_4h_to_h__bias", "transformer.h.53.input_layernorm.weight": "bloomforcausallm__transformer__h__53__input_layernorm__weight", "transformer.h.53.input_layernorm.bias": "bloomforcausallm__transformer__h__53__input_layernorm__bias", "transformer.h.53.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__53__self_attention__query_key_value__weight", "transformer.h.53.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__53__self_attention__query_key_value__bias", "transformer.h.53.self_attention.dense.weight": "bloomforcausallm__transformer__h__53__self_attention__dense__weight", "transformer.h.53.self_attention.dense.bias": "bloomforcausallm__transformer__h__53__self_attention__dense__bias", "transformer.h.53.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__53__post_attention_layernorm__weight", "transformer.h.53.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__53__post_attention_layernorm__bias", "transformer.h.53.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__53__mlp__dense_h_to_4h__weight", "transformer.h.53.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__53__mlp__dense_h_to_4h__bias", "transformer.h.53.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__53__mlp__dense_4h_to_h__weight", "transformer.h.53.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__53__mlp__dense_4h_to_h__bias", "transformer.h.54.input_layernorm.weight": "bloomforcausallm__transformer__h__54__input_layernorm__weight", "transformer.h.54.input_layernorm.bias": "bloomforcausallm__transformer__h__54__input_layernorm__bias", "transformer.h.54.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__54__self_attention__query_key_value__weight", "transformer.h.54.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__54__self_attention__query_key_value__bias", "transformer.h.54.self_attention.dense.weight": "bloomforcausallm__transformer__h__54__self_attention__dense__weight", "transformer.h.54.self_attention.dense.bias": "bloomforcausallm__transformer__h__54__self_attention__dense__bias", "transformer.h.54.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__54__post_attention_layernorm__weight", "transformer.h.54.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__54__post_attention_layernorm__bias", "transformer.h.54.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__54__mlp__dense_h_to_4h__weight", "transformer.h.54.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__54__mlp__dense_h_to_4h__bias", "transformer.h.54.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__54__mlp__dense_4h_to_h__weight", "transformer.h.54.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__54__mlp__dense_4h_to_h__bias", "transformer.h.55.input_layernorm.weight": "bloomforcausallm__transformer__h__55__input_layernorm__weight", "transformer.h.55.input_layernorm.bias": "bloomforcausallm__transformer__h__55__input_layernorm__bias", "transformer.h.55.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__55__self_attention__query_key_value__weight", "transformer.h.55.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__55__self_attention__query_key_value__bias", "transformer.h.55.self_attention.dense.weight": "bloomforcausallm__transformer__h__55__self_attention__dense__weight", "transformer.h.55.self_attention.dense.bias": "bloomforcausallm__transformer__h__55__self_attention__dense__bias", "transformer.h.55.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__55__post_attention_layernorm__weight", "transformer.h.55.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__55__post_attention_layernorm__bias", "transformer.h.55.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__55__mlp__dense_h_to_4h__weight", "transformer.h.55.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__55__mlp__dense_h_to_4h__bias", "transformer.h.55.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__55__mlp__dense_4h_to_h__weight", "transformer.h.55.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__55__mlp__dense_4h_to_h__bias", "transformer.h.56.input_layernorm.weight": "bloomforcausallm__transformer__h__56__input_layernorm__weight", "transformer.h.56.input_layernorm.bias": "bloomforcausallm__transformer__h__56__input_layernorm__bias", "transformer.h.56.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__56__self_attention__query_key_value__weight", "transformer.h.56.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__56__self_attention__query_key_value__bias", "transformer.h.56.self_attention.dense.weight": "bloomforcausallm__transformer__h__56__self_attention__dense__weight", "transformer.h.56.self_attention.dense.bias": "bloomforcausallm__transformer__h__56__self_attention__dense__bias", "transformer.h.56.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__56__post_attention_layernorm__weight", "transformer.h.56.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__56__post_attention_layernorm__bias", "transformer.h.56.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__56__mlp__dense_h_to_4h__weight", "transformer.h.56.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__56__mlp__dense_h_to_4h__bias", "transformer.h.56.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__56__mlp__dense_4h_to_h__weight", "transformer.h.56.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__56__mlp__dense_4h_to_h__bias", "transformer.h.57.input_layernorm.weight": "bloomforcausallm__transformer__h__57__input_layernorm__weight", "transformer.h.57.input_layernorm.bias": "bloomforcausallm__transformer__h__57__input_layernorm__bias", "transformer.h.57.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__57__self_attention__query_key_value__weight", "transformer.h.57.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__57__self_attention__query_key_value__bias", "transformer.h.57.self_attention.dense.weight": "bloomforcausallm__transformer__h__57__self_attention__dense__weight", "transformer.h.57.self_attention.dense.bias": "bloomforcausallm__transformer__h__57__self_attention__dense__bias", "transformer.h.57.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__57__post_attention_layernorm__weight", "transformer.h.57.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__57__post_attention_layernorm__bias", "transformer.h.57.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__57__mlp__dense_h_to_4h__weight", "transformer.h.57.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__57__mlp__dense_h_to_4h__bias", "transformer.h.57.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__57__mlp__dense_4h_to_h__weight", "transformer.h.57.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__57__mlp__dense_4h_to_h__bias", "transformer.h.58.input_layernorm.weight": "bloomforcausallm__transformer__h__58__input_layernorm__weight", "transformer.h.58.input_layernorm.bias": "bloomforcausallm__transformer__h__58__input_layernorm__bias", "transformer.h.58.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__58__self_attention__query_key_value__weight", "transformer.h.58.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__58__self_attention__query_key_value__bias", "transformer.h.58.self_attention.dense.weight": "bloomforcausallm__transformer__h__58__self_attention__dense__weight", "transformer.h.58.self_attention.dense.bias": "bloomforcausallm__transformer__h__58__self_attention__dense__bias", "transformer.h.58.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__58__post_attention_layernorm__weight", "transformer.h.58.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__58__post_attention_layernorm__bias", "transformer.h.58.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__58__mlp__dense_h_to_4h__weight", "transformer.h.58.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__58__mlp__dense_h_to_4h__bias", "transformer.h.58.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__58__mlp__dense_4h_to_h__weight", "transformer.h.58.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__58__mlp__dense_4h_to_h__bias", "transformer.h.59.input_layernorm.weight": "bloomforcausallm__transformer__h__59__input_layernorm__weight", "transformer.h.59.input_layernorm.bias": "bloomforcausallm__transformer__h__59__input_layernorm__bias", "transformer.h.59.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__59__self_attention__query_key_value__weight", "transformer.h.59.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__59__self_attention__query_key_value__bias", "transformer.h.59.self_attention.dense.weight": "bloomforcausallm__transformer__h__59__self_attention__dense__weight", "transformer.h.59.self_attention.dense.bias": "bloomforcausallm__transformer__h__59__self_attention__dense__bias", "transformer.h.59.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__59__post_attention_layernorm__weight", "transformer.h.59.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__59__post_attention_layernorm__bias", "transformer.h.59.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__59__mlp__dense_h_to_4h__weight", "transformer.h.59.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__59__mlp__dense_h_to_4h__bias", "transformer.h.59.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__59__mlp__dense_4h_to_h__weight", "transformer.h.59.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__59__mlp__dense_4h_to_h__bias", "transformer.h.60.input_layernorm.weight": "bloomforcausallm__transformer__h__60__input_layernorm__weight", "transformer.h.60.input_layernorm.bias": "bloomforcausallm__transformer__h__60__input_layernorm__bias", "transformer.h.60.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__60__self_attention__query_key_value__weight", "transformer.h.60.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__60__self_attention__query_key_value__bias", "transformer.h.60.self_attention.dense.weight": "bloomforcausallm__transformer__h__60__self_attention__dense__weight", "transformer.h.60.self_attention.dense.bias": "bloomforcausallm__transformer__h__60__self_attention__dense__bias", "transformer.h.60.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__60__post_attention_layernorm__weight", "transformer.h.60.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__60__post_attention_layernorm__bias", "transformer.h.60.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__60__mlp__dense_h_to_4h__weight", "transformer.h.60.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__60__mlp__dense_h_to_4h__bias", "transformer.h.60.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__60__mlp__dense_4h_to_h__weight", "transformer.h.60.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__60__mlp__dense_4h_to_h__bias", "transformer.h.61.input_layernorm.weight": "bloomforcausallm__transformer__h__61__input_layernorm__weight", "transformer.h.61.input_layernorm.bias": "bloomforcausallm__transformer__h__61__input_layernorm__bias", "transformer.h.61.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__61__self_attention__query_key_value__weight", "transformer.h.61.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__61__self_attention__query_key_value__bias", "transformer.h.61.self_attention.dense.weight": "bloomforcausallm__transformer__h__61__self_attention__dense__weight", "transformer.h.61.self_attention.dense.bias": "bloomforcausallm__transformer__h__61__self_attention__dense__bias", "transformer.h.61.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__61__post_attention_layernorm__weight", "transformer.h.61.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__61__post_attention_layernorm__bias", "transformer.h.61.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__61__mlp__dense_h_to_4h__weight", "transformer.h.61.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__61__mlp__dense_h_to_4h__bias", "transformer.h.61.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__61__mlp__dense_4h_to_h__weight", "transformer.h.61.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__61__mlp__dense_4h_to_h__bias", "transformer.h.62.input_layernorm.weight": "bloomforcausallm__transformer__h__62__input_layernorm__weight", "transformer.h.62.input_layernorm.bias": "bloomforcausallm__transformer__h__62__input_layernorm__bias", "transformer.h.62.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__62__self_attention__query_key_value__weight", "transformer.h.62.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__62__self_attention__query_key_value__bias", "transformer.h.62.self_attention.dense.weight": "bloomforcausallm__transformer__h__62__self_attention__dense__weight", "transformer.h.62.self_attention.dense.bias": "bloomforcausallm__transformer__h__62__self_attention__dense__bias", "transformer.h.62.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__62__post_attention_layernorm__weight", "transformer.h.62.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__62__post_attention_layernorm__bias", "transformer.h.62.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__62__mlp__dense_h_to_4h__weight", "transformer.h.62.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__62__mlp__dense_h_to_4h__bias", "transformer.h.62.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__62__mlp__dense_4h_to_h__weight", "transformer.h.62.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__62__mlp__dense_4h_to_h__bias", "transformer.h.63.input_layernorm.weight": "bloomforcausallm__transformer__h__63__input_layernorm__weight", "transformer.h.63.input_layernorm.bias": "bloomforcausallm__transformer__h__63__input_layernorm__bias", "transformer.h.63.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__63__self_attention__query_key_value__weight", "transformer.h.63.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__63__self_attention__query_key_value__bias", "transformer.h.63.self_attention.dense.weight": "bloomforcausallm__transformer__h__63__self_attention__dense__weight", "transformer.h.63.self_attention.dense.bias": "bloomforcausallm__transformer__h__63__self_attention__dense__bias", "transformer.h.63.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__63__post_attention_layernorm__weight", "transformer.h.63.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__63__post_attention_layernorm__bias", "transformer.h.63.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__63__mlp__dense_h_to_4h__weight", "transformer.h.63.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__63__mlp__dense_h_to_4h__bias", "transformer.h.63.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__63__mlp__dense_4h_to_h__weight", "transformer.h.63.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__63__mlp__dense_4h_to_h__bias", "transformer.h.64.input_layernorm.weight": "bloomforcausallm__transformer__h__64__input_layernorm__weight", "transformer.h.64.input_layernorm.bias": "bloomforcausallm__transformer__h__64__input_layernorm__bias", "transformer.h.64.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__64__self_attention__query_key_value__weight", "transformer.h.64.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__64__self_attention__query_key_value__bias", "transformer.h.64.self_attention.dense.weight": "bloomforcausallm__transformer__h__64__self_attention__dense__weight", "transformer.h.64.self_attention.dense.bias": "bloomforcausallm__transformer__h__64__self_attention__dense__bias", "transformer.h.64.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__64__post_attention_layernorm__weight", "transformer.h.64.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__64__post_attention_layernorm__bias", "transformer.h.64.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__64__mlp__dense_h_to_4h__weight", "transformer.h.64.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__64__mlp__dense_h_to_4h__bias", "transformer.h.64.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__64__mlp__dense_4h_to_h__weight", "transformer.h.64.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__64__mlp__dense_4h_to_h__bias", "transformer.h.65.input_layernorm.weight": "bloomforcausallm__transformer__h__65__input_layernorm__weight", "transformer.h.65.input_layernorm.bias": "bloomforcausallm__transformer__h__65__input_layernorm__bias", "transformer.h.65.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__65__self_attention__query_key_value__weight", "transformer.h.65.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__65__self_attention__query_key_value__bias", "transformer.h.65.self_attention.dense.weight": "bloomforcausallm__transformer__h__65__self_attention__dense__weight", "transformer.h.65.self_attention.dense.bias": "bloomforcausallm__transformer__h__65__self_attention__dense__bias", "transformer.h.65.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__65__post_attention_layernorm__weight", "transformer.h.65.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__65__post_attention_layernorm__bias", "transformer.h.65.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__65__mlp__dense_h_to_4h__weight", "transformer.h.65.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__65__mlp__dense_h_to_4h__bias", "transformer.h.65.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__65__mlp__dense_4h_to_h__weight", "transformer.h.65.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__65__mlp__dense_4h_to_h__bias", "transformer.h.66.input_layernorm.weight": "bloomforcausallm__transformer__h__66__input_layernorm__weight", "transformer.h.66.input_layernorm.bias": "bloomforcausallm__transformer__h__66__input_layernorm__bias", "transformer.h.66.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__66__self_attention__query_key_value__weight", "transformer.h.66.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__66__self_attention__query_key_value__bias", "transformer.h.66.self_attention.dense.weight": "bloomforcausallm__transformer__h__66__self_attention__dense__weight", "transformer.h.66.self_attention.dense.bias": "bloomforcausallm__transformer__h__66__self_attention__dense__bias", "transformer.h.66.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__66__post_attention_layernorm__weight", "transformer.h.66.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__66__post_attention_layernorm__bias", "transformer.h.66.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__66__mlp__dense_h_to_4h__weight", "transformer.h.66.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__66__mlp__dense_h_to_4h__bias", "transformer.h.66.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__66__mlp__dense_4h_to_h__weight", "transformer.h.66.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__66__mlp__dense_4h_to_h__bias", "transformer.h.67.input_layernorm.weight": "bloomforcausallm__transformer__h__67__input_layernorm__weight", "transformer.h.67.input_layernorm.bias": "bloomforcausallm__transformer__h__67__input_layernorm__bias", "transformer.h.67.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__67__self_attention__query_key_value__weight", "transformer.h.67.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__67__self_attention__query_key_value__bias", "transformer.h.67.self_attention.dense.weight": "bloomforcausallm__transformer__h__67__self_attention__dense__weight", "transformer.h.67.self_attention.dense.bias": "bloomforcausallm__transformer__h__67__self_attention__dense__bias", "transformer.h.67.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__67__post_attention_layernorm__weight", "transformer.h.67.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__67__post_attention_layernorm__bias", "transformer.h.67.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__67__mlp__dense_h_to_4h__weight", "transformer.h.67.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__67__mlp__dense_h_to_4h__bias", "transformer.h.67.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__67__mlp__dense_4h_to_h__weight", "transformer.h.67.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__67__mlp__dense_4h_to_h__bias", "transformer.h.68.input_layernorm.weight": "bloomforcausallm__transformer__h__68__input_layernorm__weight", "transformer.h.68.input_layernorm.bias": "bloomforcausallm__transformer__h__68__input_layernorm__bias", "transformer.h.68.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__68__self_attention__query_key_value__weight", "transformer.h.68.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__68__self_attention__query_key_value__bias", "transformer.h.68.self_attention.dense.weight": "bloomforcausallm__transformer__h__68__self_attention__dense__weight", "transformer.h.68.self_attention.dense.bias": "bloomforcausallm__transformer__h__68__self_attention__dense__bias", "transformer.h.68.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__68__post_attention_layernorm__weight", "transformer.h.68.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__68__post_attention_layernorm__bias", "transformer.h.68.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__68__mlp__dense_h_to_4h__weight", "transformer.h.68.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__68__mlp__dense_h_to_4h__bias", "transformer.h.68.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__68__mlp__dense_4h_to_h__weight", "transformer.h.68.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__68__mlp__dense_4h_to_h__bias", "transformer.h.69.input_layernorm.weight": "bloomforcausallm__transformer__h__69__input_layernorm__weight", "transformer.h.69.input_layernorm.bias": "bloomforcausallm__transformer__h__69__input_layernorm__bias", "transformer.h.69.self_attention.query_key_value.weight": "bloomforcausallm__transformer__h__69__self_attention__query_key_value__weight", "transformer.h.69.self_attention.query_key_value.bias": "bloomforcausallm__transformer__h__69__self_attention__query_key_value__bias", "transformer.h.69.self_attention.dense.weight": "bloomforcausallm__transformer__h__69__self_attention__dense__weight", "transformer.h.69.self_attention.dense.bias": "bloomforcausallm__transformer__h__69__self_attention__dense__bias", "transformer.h.69.post_attention_layernorm.weight": "bloomforcausallm__transformer__h__69__post_attention_layernorm__weight", "transformer.h.69.post_attention_layernorm.bias": "bloomforcausallm__transformer__h__69__post_attention_layernorm__bias", "transformer.h.69.mlp.dense_h_to_4h.weight": "bloomforcausallm__transformer__h__69__mlp__dense_h_to_4h__weight", "transformer.h.69.mlp.dense_h_to_4h.bias": "bloomforcausallm__transformer__h__69__mlp__dense_h_to_4h__bias", "transformer.h.69.mlp.dense_4h_to_h.weight": "bloomforcausallm__transformer__h__69__mlp__dense_4h_to_h__weight", "transformer.h.69.mlp.dense_4h_to_h.bias": "bloomforcausallm__transformer__h__69__mlp__dense_4h_to_h__bias", "transformer.ln_f.weight": "bloomforcausallm__transformer__ln_f__weight", "transformer.ln_f.bias": "bloomforcausallm__transformer__ln_f__bias", "lm_head.weight": "bloomforcausallm__transformer__word_embeddings__weight"}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f6efc66e73f1fd69da4f436e48befb519fdff3fe18910850c1d41bd862293a5
+size 14500443

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "bigscience/bloom",
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>"
+}