Upload folder using huggingface_hub

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "malteos/bloom-6b4-clp-german",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "bloom",
+  "n_head": 32,
+  "n_layer": 30,
+  "pretraining_tp": 1,
+  "slow_but_exact": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.28.1"
+}

pytorch_model-00001-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10f795bc1b0392a20c7548df7092bd5897e8f6fd51bfb013a471fdf018374082
+size 537

pytorch_model-00002-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c519059dd7c2c6f13c22c9e41cfbd6e826704a25f09c0a2eeaf20d4dea9acd9f
+size 412091306

pytorch_model-00003-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae021b284155c38a7327af0ad221f51c66b8a0c42d39ed1224f1924ec5ffa813
+size 268554663

pytorch_model-00004-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f66e496f84977e31e06b967400346a30baf9980bf34e641ee1d02b47355450f
+size 268513027

pytorch_model-00005-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7acb6aa2fb7f3ccac940e0598ccb1582506e8d69b57b975007307da832160be
+size 369183905

pytorch_model-00006-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2a2e72b9df2059aa69aa7ad061a3c3bbc4719262d29a5ea908539846fff8ca8
+size 302075651

pytorch_model-00007-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97514f1d9fb24f70c627e6a723e468643f5d3d1f8701850c9a95d0caa7e80fdd
+size 268520609

pytorch_model-00008-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08ba9e52a8fc1a6258974022aed625ca633452d4044753309f74f489af5ebc52
+size 268513027

pytorch_model-00009-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e59306b960cb4a960b99c89b14243f354040a5eca31d3a18c49fc3c206249fdf
+size 369183905

pytorch_model-00010-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5867ded283d6083c67367448cc12bab5b75d5c1db2ce99e35ead5509db4454ff
+size 302075651

pytorch_model-00011-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:655e52560a60b862c19c1e37c1e59952dba77b073358549e21dbffc8212ab0e5
+size 268520609

pytorch_model-00012-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ce1b69f801a3136a418d8bfa8606b14841bd42eec71b3d6a1a600db593674df
+size 268513027

pytorch_model-00013-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d74b23c7041fdc3e34a7f21b6beece5c5f857d13f1f5a05cbc6652f8532dae3
+size 369183905

pytorch_model-00014-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7f0e481bf0bea4033c77b0d8e066540f7d7c7bf093a5cab94c88f1ac944bb96
+size 302075651

pytorch_model-00015-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc14243483003d99509bea4535c4aa45975e30e79a2680c90e8b73fd677b98fa
+size 268520609

pytorch_model-00016-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:696ec393eaee59dfa2bac34ab969fc40cebd651c242a2cc8bde4a197763b4d42
+size 268513027

pytorch_model-00017-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:332170fdd6ffe406709907e17c7136236ff049ae90ea568ef3d0342969be9276
+size 369183905

pytorch_model-00018-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c572ef8dfcf5869be5972ea2cf7249df51a11bb02646943864c5f38739bddb4f
+size 302075651

pytorch_model-00019-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8156c8dd41d4123a7bf9cf036ed64e17ca56dae964a0ff229e572e106d627d90
+size 268520609

pytorch_model-00020-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96168a15fb671a0518086f74335fe0e2b58ff7874e3226d0140b258128025835
+size 268513027

pytorch_model-00021-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90e8969b30d37d570c14a1b70776874e9d8d1a84032494cfe3e442f8a826189b
+size 369183905

pytorch_model-00022-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95e887f4ce8f8e655fed7347ecb7414f062b9a93373cb63d21cae00fd3ead1c
+size 302075651

pytorch_model-00023-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29981bab2b5e4a06574cf9cae9c6861a6516b9e0ea8dfbf9357474164d8d8498
+size 268520609

pytorch_model-00024-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:118c562d797431da4ee279e47915e3fdf44373b155bf6a556d2aa54a2376542f
+size 268513027

pytorch_model-00025-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07c97b8884b73fe2b8bb2e3832417e2a7e9e35695edac6e5f47161064a94ac35
+size 369183905

pytorch_model-00026-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50bea9ac715948f3a2ea74d1d9e1f2f2efc8b13cae285b56107c7ac26334fb4b
+size 302075651

pytorch_model-00027-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed12977ad8dd3b1a735eb95dda74d41c6d7879f59155d62740c934fde33c7a18
+size 268520609

pytorch_model-00028-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ae52228c4dada0cea2de6ca115f8c7e0a1640f5ae124d16f5e49e4425830ecd
+size 268513027

pytorch_model-00029-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:761570a653a40c8ad5c0c807a8aebab99276a691ba41d0b7f415b01ab1cada97
+size 369183905

pytorch_model-00030-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b57a61173870152a1367030f3e920f9dad99890662ea34c5fa0aca0954e91da
+size 302075651

pytorch_model-00031-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:812bae41819fc3e66a28dfebe0cea8ef0ef84d3fba411d38e57e3437949181b6
+size 268520609

pytorch_model-00032-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f5e4034e6db50ed71b34ed7e546004cd2ea283c8713d9959d6cf19583775b00
+size 268513027

pytorch_model-00033-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84bbc50ad487f72fd1c34e72cfe9239544c0e0ad49d568a793938d2faa64520d
+size 369183905

pytorch_model-00034-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62694dec220a5698738bd575dd23809c275c6d6a980b769a5e35ce11ca19a8c0
+size 302075651

pytorch_model-00035-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:348d220474cbd170a0ed2226dcaafe2fdc5436e1cdc98068257bd15229b5c947
+size 268520609

pytorch_model-00036-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03ee5e1c365accf307e25d4b44a8c3e1b7321edce0fe585cd09b8ea7a6974628
+size 268513027

pytorch_model-00037-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9055689be8378c246f8315d8d3c00e0797f9e0ba17792d09186dccef304e92cd
+size 369183905

pytorch_model-00038-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b41552b668a8e2beffc72918663ff293afa06c0f96b10271f0d98e6980ba3549
+size 302075651

pytorch_model-00039-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70d8ef84476d2a9e22c6b21ac259519664ba529aac8d15e7fddac137559fe084
+size 268520609

pytorch_model-00040-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:879885963937aaa10f98212a0b85482383eaabade613f06115e7906f8be70ef6
+size 268513027

pytorch_model-00041-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a396bdc4295029031cdca5d73de1bc317c067fc322704e95d5d922c9d0db3387
+size 369183905

pytorch_model-00042-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b07611d921970fcc0cc2bb069f7f5b55321a304fb3a5c06fa9a19d173f944278
+size 302075587

pytorch_model-00043-of-00043.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b87e3fab2a5fbdd66e0cb54ce3eaa0c073996aa5d04abd6a3e65325cad7215d3
+size 412091306

pytorch_model.bin.index.json

@@ -0,0 +1,373 @@
+{
+  "metadata": {
+    "total_size": 12907003904
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00043-of-00043.bin",
+    "transformer.h.0.input_layernorm.bias": "pytorch_model-00003-of-00043.bin",
+    "transformer.h.0.input_layernorm.weight": "pytorch_model-00003-of-00043.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00043.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00043.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00043.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00043.bin",
+    "transformer.h.0.post_attention_layernorm.bias": "pytorch_model-00003-of-00043.bin",
+    "transformer.h.0.post_attention_layernorm.weight": "pytorch_model-00003-of-00043.bin",
+    "transformer.h.0.self_attention.dense.bias": "pytorch_model-00003-of-00043.bin",
+    "transformer.h.0.self_attention.dense.weight": "pytorch_model-00003-of-00043.bin",
+    "transformer.h.0.self_attention.query_key_value.bias": "pytorch_model-00003-of-00043.bin",
+    "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00003-of-00043.bin",
+    "transformer.h.1.input_layernorm.bias": "pytorch_model-00004-of-00043.bin",
+    "transformer.h.1.input_layernorm.weight": "pytorch_model-00004-of-00043.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00043.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00043.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00043.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00043.bin",
+    "transformer.h.1.post_attention_layernorm.bias": "pytorch_model-00004-of-00043.bin",
+    "transformer.h.1.post_attention_layernorm.weight": "pytorch_model-00004-of-00043.bin",
+    "transformer.h.1.self_attention.dense.bias": "pytorch_model-00004-of-00043.bin",
+    "transformer.h.1.self_attention.dense.weight": "pytorch_model-00004-of-00043.bin",
+    "transformer.h.1.self_attention.query_key_value.bias": "pytorch_model-00004-of-00043.bin",
+    "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00004-of-00043.bin",
+    "transformer.h.10.input_layernorm.bias": "pytorch_model-00016-of-00043.bin",
+    "transformer.h.10.input_layernorm.weight": "pytorch_model-00016-of-00043.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.bias": "pytorch_model-00017-of-00043.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00017-of-00043.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.bias": "pytorch_model-00017-of-00043.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00017-of-00043.bin",
+    "transformer.h.10.post_attention_layernorm.bias": "pytorch_model-00016-of-00043.bin",
+    "transformer.h.10.post_attention_layernorm.weight": "pytorch_model-00016-of-00043.bin",
+    "transformer.h.10.self_attention.dense.bias": "pytorch_model-00016-of-00043.bin",
+    "transformer.h.10.self_attention.dense.weight": "pytorch_model-00016-of-00043.bin",
+    "transformer.h.10.self_attention.query_key_value.bias": "pytorch_model-00016-of-00043.bin",
+    "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00016-of-00043.bin",
+    "transformer.h.11.input_layernorm.bias": "pytorch_model-00017-of-00043.bin",
+    "transformer.h.11.input_layernorm.weight": "pytorch_model-00017-of-00043.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.bias": "pytorch_model-00018-of-00043.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00018-of-00043.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.bias": "pytorch_model-00018-of-00043.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00018-of-00043.bin",
+    "transformer.h.11.post_attention_layernorm.bias": "pytorch_model-00018-of-00043.bin",
+    "transformer.h.11.post_attention_layernorm.weight": "pytorch_model-00018-of-00043.bin",
+    "transformer.h.11.self_attention.dense.bias": "pytorch_model-00018-of-00043.bin",
+    "transformer.h.11.self_attention.dense.weight": "pytorch_model-00018-of-00043.bin",
+    "transformer.h.11.self_attention.query_key_value.bias": "pytorch_model-00017-of-00043.bin",
+    "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00017-of-00043.bin",
+    "transformer.h.12.input_layernorm.bias": "pytorch_model-00018-of-00043.bin",
+    "transformer.h.12.input_layernorm.weight": "pytorch_model-00018-of-00043.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.bias": "pytorch_model-00020-of-00043.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00020-of-00043.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.bias": "pytorch_model-00019-of-00043.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00019-of-00043.bin",
+    "transformer.h.12.post_attention_layernorm.bias": "pytorch_model-00019-of-00043.bin",
+    "transformer.h.12.post_attention_layernorm.weight": "pytorch_model-00019-of-00043.bin",
+    "transformer.h.12.self_attention.dense.bias": "pytorch_model-00019-of-00043.bin",
+    "transformer.h.12.self_attention.dense.weight": "pytorch_model-00019-of-00043.bin",
+    "transformer.h.12.self_attention.query_key_value.bias": "pytorch_model-00019-of-00043.bin",
+    "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00019-of-00043.bin",
+    "transformer.h.13.input_layernorm.bias": "pytorch_model-00020-of-00043.bin",
+    "transformer.h.13.input_layernorm.weight": "pytorch_model-00020-of-00043.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.bias": "pytorch_model-00021-of-00043.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00021-of-00043.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.bias": "pytorch_model-00021-of-00043.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00021-of-00043.bin",
+    "transformer.h.13.post_attention_layernorm.bias": "pytorch_model-00020-of-00043.bin",
+    "transformer.h.13.post_attention_layernorm.weight": "pytorch_model-00020-of-00043.bin",
+    "transformer.h.13.self_attention.dense.bias": "pytorch_model-00020-of-00043.bin",
+    "transformer.h.13.self_attention.dense.weight": "pytorch_model-00020-of-00043.bin",
+    "transformer.h.13.self_attention.query_key_value.bias": "pytorch_model-00020-of-00043.bin",
+    "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00020-of-00043.bin",
+    "transformer.h.14.input_layernorm.bias": "pytorch_model-00021-of-00043.bin",
+    "transformer.h.14.input_layernorm.weight": "pytorch_model-00021-of-00043.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.bias": "pytorch_model-00022-of-00043.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00022-of-00043.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.bias": "pytorch_model-00022-of-00043.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00022-of-00043.bin",
+    "transformer.h.14.post_attention_layernorm.bias": "pytorch_model-00022-of-00043.bin",
+    "transformer.h.14.post_attention_layernorm.weight": "pytorch_model-00022-of-00043.bin",
+    "transformer.h.14.self_attention.dense.bias": "pytorch_model-00022-of-00043.bin",
+    "transformer.h.14.self_attention.dense.weight": "pytorch_model-00022-of-00043.bin",
+    "transformer.h.14.self_attention.query_key_value.bias": "pytorch_model-00021-of-00043.bin",
+    "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00021-of-00043.bin",
+    "transformer.h.15.input_layernorm.bias": "pytorch_model-00022-of-00043.bin",
+    "transformer.h.15.input_layernorm.weight": "pytorch_model-00022-of-00043.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.bias": "pytorch_model-00024-of-00043.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00024-of-00043.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.bias": "pytorch_model-00023-of-00043.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00023-of-00043.bin",
+    "transformer.h.15.post_attention_layernorm.bias": "pytorch_model-00023-of-00043.bin",
+    "transformer.h.15.post_attention_layernorm.weight": "pytorch_model-00023-of-00043.bin",
+    "transformer.h.15.self_attention.dense.bias": "pytorch_model-00023-of-00043.bin",
+    "transformer.h.15.self_attention.dense.weight": "pytorch_model-00023-of-00043.bin",
+    "transformer.h.15.self_attention.query_key_value.bias": "pytorch_model-00023-of-00043.bin",
+    "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00023-of-00043.bin",
+    "transformer.h.16.input_layernorm.bias": "pytorch_model-00024-of-00043.bin",
+    "transformer.h.16.input_layernorm.weight": "pytorch_model-00024-of-00043.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.bias": "pytorch_model-00025-of-00043.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00025-of-00043.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.bias": "pytorch_model-00025-of-00043.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00025-of-00043.bin",
+    "transformer.h.16.post_attention_layernorm.bias": "pytorch_model-00024-of-00043.bin",
+    "transformer.h.16.post_attention_layernorm.weight": "pytorch_model-00024-of-00043.bin",
+    "transformer.h.16.self_attention.dense.bias": "pytorch_model-00024-of-00043.bin",
+    "transformer.h.16.self_attention.dense.weight": "pytorch_model-00024-of-00043.bin",
+    "transformer.h.16.self_attention.query_key_value.bias": "pytorch_model-00024-of-00043.bin",
+    "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00024-of-00043.bin",
+    "transformer.h.17.input_layernorm.bias": "pytorch_model-00025-of-00043.bin",
+    "transformer.h.17.input_layernorm.weight": "pytorch_model-00025-of-00043.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.bias": "pytorch_model-00026-of-00043.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00026-of-00043.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.bias": "pytorch_model-00026-of-00043.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00026-of-00043.bin",
+    "transformer.h.17.post_attention_layernorm.bias": "pytorch_model-00026-of-00043.bin",
+    "transformer.h.17.post_attention_layernorm.weight": "pytorch_model-00026-of-00043.bin",
+    "transformer.h.17.self_attention.dense.bias": "pytorch_model-00026-of-00043.bin",
+    "transformer.h.17.self_attention.dense.weight": "pytorch_model-00026-of-00043.bin",
+    "transformer.h.17.self_attention.query_key_value.bias": "pytorch_model-00025-of-00043.bin",
+    "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00025-of-00043.bin",
+    "transformer.h.18.input_layernorm.bias": "pytorch_model-00026-of-00043.bin",
+    "transformer.h.18.input_layernorm.weight": "pytorch_model-00026-of-00043.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.bias": "pytorch_model-00028-of-00043.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00028-of-00043.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.bias": "pytorch_model-00027-of-00043.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00027-of-00043.bin",
+    "transformer.h.18.post_attention_layernorm.bias": "pytorch_model-00027-of-00043.bin",
+    "transformer.h.18.post_attention_layernorm.weight": "pytorch_model-00027-of-00043.bin",
+    "transformer.h.18.self_attention.dense.bias": "pytorch_model-00027-of-00043.bin",
+    "transformer.h.18.self_attention.dense.weight": "pytorch_model-00027-of-00043.bin",
+    "transformer.h.18.self_attention.query_key_value.bias": "pytorch_model-00027-of-00043.bin",
+    "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00027-of-00043.bin",
+    "transformer.h.19.input_layernorm.bias": "pytorch_model-00028-of-00043.bin",
+    "transformer.h.19.input_layernorm.weight": "pytorch_model-00028-of-00043.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.bias": "pytorch_model-00029-of-00043.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00029-of-00043.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.bias": "pytorch_model-00029-of-00043.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00029-of-00043.bin",
+    "transformer.h.19.post_attention_layernorm.bias": "pytorch_model-00028-of-00043.bin",
+    "transformer.h.19.post_attention_layernorm.weight": "pytorch_model-00028-of-00043.bin",
+    "transformer.h.19.self_attention.dense.bias": "pytorch_model-00028-of-00043.bin",
+    "transformer.h.19.self_attention.dense.weight": "pytorch_model-00028-of-00043.bin",
+    "transformer.h.19.self_attention.query_key_value.bias": "pytorch_model-00028-of-00043.bin",
+    "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00028-of-00043.bin",
+    "transformer.h.2.input_layernorm.bias": "pytorch_model-00005-of-00043.bin",
+    "transformer.h.2.input_layernorm.weight": "pytorch_model-00005-of-00043.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00043.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00043.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00043.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00043.bin",
+    "transformer.h.2.post_attention_layernorm.bias": "pytorch_model-00006-of-00043.bin",
+    "transformer.h.2.post_attention_layernorm.weight": "pytorch_model-00006-of-00043.bin",
+    "transformer.h.2.self_attention.dense.bias": "pytorch_model-00006-of-00043.bin",
+    "transformer.h.2.self_attention.dense.weight": "pytorch_model-00006-of-00043.bin",
+    "transformer.h.2.self_attention.query_key_value.bias": "pytorch_model-00005-of-00043.bin",
+    "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00005-of-00043.bin",
+    "transformer.h.20.input_layernorm.bias": "pytorch_model-00029-of-00043.bin",
+    "transformer.h.20.input_layernorm.weight": "pytorch_model-00029-of-00043.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.bias": "pytorch_model-00030-of-00043.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00030-of-00043.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.bias": "pytorch_model-00030-of-00043.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00030-of-00043.bin",
+    "transformer.h.20.post_attention_layernorm.bias": "pytorch_model-00030-of-00043.bin",
+    "transformer.h.20.post_attention_layernorm.weight": "pytorch_model-00030-of-00043.bin",
+    "transformer.h.20.self_attention.dense.bias": "pytorch_model-00030-of-00043.bin",
+    "transformer.h.20.self_attention.dense.weight": "pytorch_model-00030-of-00043.bin",
+    "transformer.h.20.self_attention.query_key_value.bias": "pytorch_model-00029-of-00043.bin",
+    "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00029-of-00043.bin",
+    "transformer.h.21.input_layernorm.bias": "pytorch_model-00030-of-00043.bin",
+    "transformer.h.21.input_layernorm.weight": "pytorch_model-00030-of-00043.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.bias": "pytorch_model-00032-of-00043.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00032-of-00043.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.bias": "pytorch_model-00031-of-00043.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00031-of-00043.bin",
+    "transformer.h.21.post_attention_layernorm.bias": "pytorch_model-00031-of-00043.bin",
+    "transformer.h.21.post_attention_layernorm.weight": "pytorch_model-00031-of-00043.bin",
+    "transformer.h.21.self_attention.dense.bias": "pytorch_model-00031-of-00043.bin",
+    "transformer.h.21.self_attention.dense.weight": "pytorch_model-00031-of-00043.bin",
+    "transformer.h.21.self_attention.query_key_value.bias": "pytorch_model-00031-of-00043.bin",
+    "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00031-of-00043.bin",
+    "transformer.h.22.input_layernorm.bias": "pytorch_model-00032-of-00043.bin",
+    "transformer.h.22.input_layernorm.weight": "pytorch_model-00032-of-00043.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.bias": "pytorch_model-00033-of-00043.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00033-of-00043.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.bias": "pytorch_model-00033-of-00043.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00033-of-00043.bin",
+    "transformer.h.22.post_attention_layernorm.bias": "pytorch_model-00032-of-00043.bin",
+    "transformer.h.22.post_attention_layernorm.weight": "pytorch_model-00032-of-00043.bin",
+    "transformer.h.22.self_attention.dense.bias": "pytorch_model-00032-of-00043.bin",
+    "transformer.h.22.self_attention.dense.weight": "pytorch_model-00032-of-00043.bin",
+    "transformer.h.22.self_attention.query_key_value.bias": "pytorch_model-00032-of-00043.bin",
+    "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00032-of-00043.bin",
+    "transformer.h.23.input_layernorm.bias": "pytorch_model-00033-of-00043.bin",
+    "transformer.h.23.input_layernorm.weight": "pytorch_model-00033-of-00043.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.bias": "pytorch_model-00034-of-00043.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00034-of-00043.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.bias": "pytorch_model-00034-of-00043.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00034-of-00043.bin",
+    "transformer.h.23.post_attention_layernorm.bias": "pytorch_model-00034-of-00043.bin",
+    "transformer.h.23.post_attention_layernorm.weight": "pytorch_model-00034-of-00043.bin",
+    "transformer.h.23.self_attention.dense.bias": "pytorch_model-00034-of-00043.bin",
+    "transformer.h.23.self_attention.dense.weight": "pytorch_model-00034-of-00043.bin",
+    "transformer.h.23.self_attention.query_key_value.bias": "pytorch_model-00033-of-00043.bin",
+    "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00033-of-00043.bin",
+    "transformer.h.24.input_layernorm.bias": "pytorch_model-00034-of-00043.bin",
+    "transformer.h.24.input_layernorm.weight": "pytorch_model-00034-of-00043.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.bias": "pytorch_model-00036-of-00043.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00036-of-00043.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.bias": "pytorch_model-00035-of-00043.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00035-of-00043.bin",
+    "transformer.h.24.post_attention_layernorm.bias": "pytorch_model-00035-of-00043.bin",
+    "transformer.h.24.post_attention_layernorm.weight": "pytorch_model-00035-of-00043.bin",
+    "transformer.h.24.self_attention.dense.bias": "pytorch_model-00035-of-00043.bin",
+    "transformer.h.24.self_attention.dense.weight": "pytorch_model-00035-of-00043.bin",
+    "transformer.h.24.self_attention.query_key_value.bias": "pytorch_model-00035-of-00043.bin",
+    "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00035-of-00043.bin",
+    "transformer.h.25.input_layernorm.bias": "pytorch_model-00036-of-00043.bin",
+    "transformer.h.25.input_layernorm.weight": "pytorch_model-00036-of-00043.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.bias": "pytorch_model-00037-of-00043.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00037-of-00043.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.bias": "pytorch_model-00037-of-00043.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00037-of-00043.bin",
+    "transformer.h.25.post_attention_layernorm.bias": "pytorch_model-00036-of-00043.bin",
+    "transformer.h.25.post_attention_layernorm.weight": "pytorch_model-00036-of-00043.bin",
+    "transformer.h.25.self_attention.dense.bias": "pytorch_model-00036-of-00043.bin",
+    "transformer.h.25.self_attention.dense.weight": "pytorch_model-00036-of-00043.bin",
+    "transformer.h.25.self_attention.query_key_value.bias": "pytorch_model-00036-of-00043.bin",
+    "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00036-of-00043.bin",
+    "transformer.h.26.input_layernorm.bias": "pytorch_model-00037-of-00043.bin",
+    "transformer.h.26.input_layernorm.weight": "pytorch_model-00037-of-00043.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.bias": "pytorch_model-00038-of-00043.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00038-of-00043.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.bias": "pytorch_model-00038-of-00043.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00038-of-00043.bin",
+    "transformer.h.26.post_attention_layernorm.bias": "pytorch_model-00038-of-00043.bin",
+    "transformer.h.26.post_attention_layernorm.weight": "pytorch_model-00038-of-00043.bin",
+    "transformer.h.26.self_attention.dense.bias": "pytorch_model-00038-of-00043.bin",
+    "transformer.h.26.self_attention.dense.weight": "pytorch_model-00038-of-00043.bin",
+    "transformer.h.26.self_attention.query_key_value.bias": "pytorch_model-00037-of-00043.bin",
+    "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00037-of-00043.bin",
+    "transformer.h.27.input_layernorm.bias": "pytorch_model-00038-of-00043.bin",
+    "transformer.h.27.input_layernorm.weight": "pytorch_model-00038-of-00043.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.bias": "pytorch_model-00040-of-00043.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00040-of-00043.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.bias": "pytorch_model-00039-of-00043.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00039-of-00043.bin",
+    "transformer.h.27.post_attention_layernorm.bias": "pytorch_model-00039-of-00043.bin",
+    "transformer.h.27.post_attention_layernorm.weight": "pytorch_model-00039-of-00043.bin",
+    "transformer.h.27.self_attention.dense.bias": "pytorch_model-00039-of-00043.bin",
+    "transformer.h.27.self_attention.dense.weight": "pytorch_model-00039-of-00043.bin",
+    "transformer.h.27.self_attention.query_key_value.bias": "pytorch_model-00039-of-00043.bin",
+    "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00039-of-00043.bin",
+    "transformer.h.28.input_layernorm.bias": "pytorch_model-00040-of-00043.bin",
+    "transformer.h.28.input_layernorm.weight": "pytorch_model-00040-of-00043.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.bias": "pytorch_model-00041-of-00043.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00041-of-00043.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.bias": "pytorch_model-00041-of-00043.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00041-of-00043.bin",
+    "transformer.h.28.post_attention_layernorm.bias": "pytorch_model-00040-of-00043.bin",
+    "transformer.h.28.post_attention_layernorm.weight": "pytorch_model-00040-of-00043.bin",
+    "transformer.h.28.self_attention.dense.bias": "pytorch_model-00040-of-00043.bin",
+    "transformer.h.28.self_attention.dense.weight": "pytorch_model-00040-of-00043.bin",
+    "transformer.h.28.self_attention.query_key_value.bias": "pytorch_model-00040-of-00043.bin",
+    "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00040-of-00043.bin",
+    "transformer.h.29.input_layernorm.bias": "pytorch_model-00041-of-00043.bin",
+    "transformer.h.29.input_layernorm.weight": "pytorch_model-00041-of-00043.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.bias": "pytorch_model-00042-of-00043.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00042-of-00043.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.bias": "pytorch_model-00042-of-00043.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00042-of-00043.bin",
+    "transformer.h.29.post_attention_layernorm.bias": "pytorch_model-00042-of-00043.bin",
+    "transformer.h.29.post_attention_layernorm.weight": "pytorch_model-00042-of-00043.bin",
+    "transformer.h.29.self_attention.dense.bias": "pytorch_model-00042-of-00043.bin",
+    "transformer.h.29.self_attention.dense.weight": "pytorch_model-00042-of-00043.bin",
+    "transformer.h.29.self_attention.query_key_value.bias": "pytorch_model-00041-of-00043.bin",
+    "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00041-of-00043.bin",
+    "transformer.h.3.input_layernorm.bias": "pytorch_model-00006-of-00043.bin",
+    "transformer.h.3.input_layernorm.weight": "pytorch_model-00006-of-00043.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00043.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00043.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00043.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00043.bin",
+    "transformer.h.3.post_attention_layernorm.bias": "pytorch_model-00007-of-00043.bin",
+    "transformer.h.3.post_attention_layernorm.weight": "pytorch_model-00007-of-00043.bin",
+    "transformer.h.3.self_attention.dense.bias": "pytorch_model-00007-of-00043.bin",
+    "transformer.h.3.self_attention.dense.weight": "pytorch_model-00007-of-00043.bin",
+    "transformer.h.3.self_attention.query_key_value.bias": "pytorch_model-00007-of-00043.bin",
+    "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00007-of-00043.bin",
+    "transformer.h.4.input_layernorm.bias": "pytorch_model-00008-of-00043.bin",
+    "transformer.h.4.input_layernorm.weight": "pytorch_model-00008-of-00043.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00043.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00043.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00043.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00043.bin",
+    "transformer.h.4.post_attention_layernorm.bias": "pytorch_model-00008-of-00043.bin",
+    "transformer.h.4.post_attention_layernorm.weight": "pytorch_model-00008-of-00043.bin",
+    "transformer.h.4.self_attention.dense.bias": "pytorch_model-00008-of-00043.bin",
+    "transformer.h.4.self_attention.dense.weight": "pytorch_model-00008-of-00043.bin",
+    "transformer.h.4.self_attention.query_key_value.bias": "pytorch_model-00008-of-00043.bin",
+    "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00008-of-00043.bin",
+    "transformer.h.5.input_layernorm.bias": "pytorch_model-00009-of-00043.bin",
+    "transformer.h.5.input_layernorm.weight": "pytorch_model-00009-of-00043.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.bias": "pytorch_model-00010-of-00043.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00043.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.bias": "pytorch_model-00010-of-00043.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00043.bin",
+    "transformer.h.5.post_attention_layernorm.bias": "pytorch_model-00010-of-00043.bin",
+    "transformer.h.5.post_attention_layernorm.weight": "pytorch_model-00010-of-00043.bin",
+    "transformer.h.5.self_attention.dense.bias": "pytorch_model-00010-of-00043.bin",
+    "transformer.h.5.self_attention.dense.weight": "pytorch_model-00010-of-00043.bin",
+    "transformer.h.5.self_attention.query_key_value.bias": "pytorch_model-00009-of-00043.bin",
+    "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00009-of-00043.bin",
+    "transformer.h.6.input_layernorm.bias": "pytorch_model-00010-of-00043.bin",
+    "transformer.h.6.input_layernorm.weight": "pytorch_model-00010-of-00043.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.bias": "pytorch_model-00012-of-00043.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00043.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.bias": "pytorch_model-00011-of-00043.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00043.bin",
+    "transformer.h.6.post_attention_layernorm.bias": "pytorch_model-00011-of-00043.bin",
+    "transformer.h.6.post_attention_layernorm.weight": "pytorch_model-00011-of-00043.bin",
+    "transformer.h.6.self_attention.dense.bias": "pytorch_model-00011-of-00043.bin",
+    "transformer.h.6.self_attention.dense.weight": "pytorch_model-00011-of-00043.bin",
+    "transformer.h.6.self_attention.query_key_value.bias": "pytorch_model-00011-of-00043.bin",
+    "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00011-of-00043.bin",
+    "transformer.h.7.input_layernorm.bias": "pytorch_model-00012-of-00043.bin",
+    "transformer.h.7.input_layernorm.weight": "pytorch_model-00012-of-00043.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.bias": "pytorch_model-00013-of-00043.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00043.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.bias": "pytorch_model-00013-of-00043.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00043.bin",
+    "transformer.h.7.post_attention_layernorm.bias": "pytorch_model-00012-of-00043.bin",
+    "transformer.h.7.post_attention_layernorm.weight": "pytorch_model-00012-of-00043.bin",
+    "transformer.h.7.self_attention.dense.bias": "pytorch_model-00012-of-00043.bin",
+    "transformer.h.7.self_attention.dense.weight": "pytorch_model-00012-of-00043.bin",
+    "transformer.h.7.self_attention.query_key_value.bias": "pytorch_model-00012-of-00043.bin",
+    "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00012-of-00043.bin",
+    "transformer.h.8.input_layernorm.bias": "pytorch_model-00013-of-00043.bin",
+    "transformer.h.8.input_layernorm.weight": "pytorch_model-00013-of-00043.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.bias": "pytorch_model-00014-of-00043.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00043.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.bias": "pytorch_model-00014-of-00043.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00043.bin",
+    "transformer.h.8.post_attention_layernorm.bias": "pytorch_model-00014-of-00043.bin",
+    "transformer.h.8.post_attention_layernorm.weight": "pytorch_model-00014-of-00043.bin",
+    "transformer.h.8.self_attention.dense.bias": "pytorch_model-00014-of-00043.bin",
+    "transformer.h.8.self_attention.dense.weight": "pytorch_model-00014-of-00043.bin",
+    "transformer.h.8.self_attention.query_key_value.bias": "pytorch_model-00013-of-00043.bin",
+    "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00013-of-00043.bin",
+    "transformer.h.9.input_layernorm.bias": "pytorch_model-00014-of-00043.bin",
+    "transformer.h.9.input_layernorm.weight": "pytorch_model-00014-of-00043.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.bias": "pytorch_model-00016-of-00043.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00016-of-00043.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.bias": "pytorch_model-00015-of-00043.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00015-of-00043.bin",
+    "transformer.h.9.post_attention_layernorm.bias": "pytorch_model-00015-of-00043.bin",
+    "transformer.h.9.post_attention_layernorm.weight": "pytorch_model-00015-of-00043.bin",
+    "transformer.h.9.self_attention.dense.bias": "pytorch_model-00015-of-00043.bin",
+    "transformer.h.9.self_attention.dense.weight": "pytorch_model-00015-of-00043.bin",
+    "transformer.h.9.self_attention.query_key_value.bias": "pytorch_model-00015-of-00043.bin",
+    "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00015-of-00043.bin",
+    "transformer.ln_f.bias": "pytorch_model-00042-of-00043.bin",
+    "transformer.ln_f.weight": "pytorch_model-00042-of-00043.bin",
+    "transformer.word_embeddings.weight": "pytorch_model-00002-of-00043.bin",
+    "transformer.word_embeddings_layernorm.bias": "pytorch_model-00003-of-00043.bin",
+    "transformer.word_embeddings_layernorm.weight": "pytorch_model-00003-of-00043.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}