Upload folder using huggingface_hub (#3)

- 2df3e59870dbc0695f7a86ab1dd744b8a07834d35b974821b7009ab67629f2ff (b1199095a48d1efbc223f078b975bdcb17f1baba)
- a94e4cb0954eef3f789c18f49dea9b3b884f4f2fb8556d9e4d4e4ac4047ef29f (8e8fde60346ff592eba04b27a1119deddb2b4b78)
- 96a22ce4bf6761b75875466c84877caa471f82db8cbe05a377450c201c0e79e8 (8972c3e401db45cfc8542a3b9bcaed09f4b4d7d9)
- 53936db3e37ff32b45c52432f7400f9404df180b70ca8ebe156f45ef2a683603 (638a931fe871c5139593b1d6287bfb19d0fce478)
- 1cb2033a842b437ded6158751c87e165f865c4ef1e90883c483458cc3ced82e6 (5e0ea75bf5cdbd31f440288bb760c5b702d926f4)
- eb0a778badd703b77da7d94448e3eeb0ac1af7072209c7601e44b7c879631db0 (97afd0c193f57840bf312b1bab517211c5448cf6)
- 418152877997e60c8945fdd8019a5d1dc3effa3c157805a1c06aacec38b306b2 (78411315c2880748dc86c5cc94e2d2d9da8c7149)
- 2fd80e0f1ae7510d46dfa31f7d8ec703d3eb6806c1973fcfc7fa538850d48d1e (c1a6d3adbad76d22491690670272be828782c49b)
- d237d4867a728c7c04e41526c4f3dd189cc2748e96ad2a08fa4137f9f8ad3260 (19e1c0e476fc81e0cbe072834bc231c711b401ef)
- 3de2f74e1fefae16bcc8d592cc1838bfb5d72d45319c22fe6277e8de52b6a0a7 (938a73cdd539d0e7d19d431053b5b868f4761bab)
- 58ccc97c6fc7f5aef6b460f4e78f0d45c76f8c2c99f53775c70e4731ec3f0c29 (421a47f3348f94aca0b1c68d432334734b15fd37)
- d64f05bc32cf1327de79af79e7cd86609a9346ffe8612219914e7ca25495920d (d7b09f46950c33e1a140c8cdba693d6ef4625c74)
- e13eb7077a5848cbfb32028bc59307fa7f877f236137dbe9d9f7f468fffc1239 (39a01a96c8d8b6f322cabb7f98c9811c5c3240a9)
- 71cf14ccf680de48e81e4ab3d83043ca1535b8422b850a8646f1af2a3e41f191 (359d6f8f4fb52f99f467697328bcd21aaaf7cb87)
- a4838c0ec454aadbf9bdd5ce7e5e4f855abbaccef155cda99e394f34cdfcbde3 (248a37f47b44cbf60fe3809e2de474e602bb03c7)
- 2c8f1bdf64eb0fec6ff5b1e50af7525ecbb3a1572fb6807b989ef337f187a259 (ca240149c71a4ec1a5a190d789ceb33bd2ebffcf)
- 1d15e34890cfcf827ee34416131d89bd6d2c0853e7ed3816bc7298e796fd5d97 (bae6deb8dbbf087274686ef5493fc9394798157a)

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "tiiuae/falcon-7b-instruct",
+  "alibi": false,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "RWForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "tiiuae/falcon-7b-instruct--configuration_RW.RWConfig",
+    "AutoModelForCausalLM": "tiiuae/falcon-7b-instruct--modelling_RW.RWForCausalLM"
+  },
+  "bias": false,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4544,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "RefinedWebModel",
+  "multi_query": true,
+  "n_head": 71,
+  "n_layer": 32,
+  "parallel_attn": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0.dev0",
+  "use_cache": true,
+  "vocab_size": 65024
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.31.0.dev0"
+}

push.py

@@ -0,0 +1,10 @@
+from huggingface_hub import HfApi
+
+api = HfApi()
+
+api.upload_folder(
+        repo_id="Trisert/falcon-7b-instruct-sharded",
+        folder_path=".",
+        multi_commits=True,
+        multi_commits_verbose=True,
+        )

pytorch_model-00001-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f713a462ff20e675c62e450a60f51aed6f65430a165f82b4f709b539f4342361
+size 537

pytorch_model-00002-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4bd830c110b6519dbe116c07659017a5bc8c0956a22b8081872a9ce5f84649c
+size 1181877226

pytorch_model-00003-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c6b806cca45e0454e7c336a8af3b881d07d386eccf975453019215982d29e9a
+size 995830467

pytorch_model-00004-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08c63aacab7addf366cfc9228dcf33b3fcda1eedd4d51a4de0a94447c10436f3
+size 828282815

pytorch_model-00005-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5a15ea20cbc030662245df3dbdd2842caf67432d606433ef783f0f7e1dcd56a
+size 828282815

pytorch_model-00006-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c104d0639442e3e14d4d833980227a0640630def1c98010cbf14869002d536d4
+size 828282815

pytorch_model-00007-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d1ea08935c3d7208f32b7031333e1fba34f40e11c707be20ca1bc3db0e9e4a7
+size 828282815

pytorch_model-00008-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44710d73f3e90e91abb4d83338429d8c12fed43a23dd51dea9186ba999854201
+size 828282815

pytorch_model-00009-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:873a9dc8cdfc9daf85f7341108dc593719dd1cf3eb1fe37a72e5acf0d981b155
+size 828282815

pytorch_model-00010-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d24732c5973d0e1c102a99e017d7faad052c5accb569642d85dd85d7ec5ec65
+size 828282815

pytorch_model-00011-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e887a35b06fe4526d212d6858f863a8dbd8b91a727f66a4fb5e276f4a26ad2fe
+size 828282815

pytorch_model-00012-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:622ecad252da95c0902b9cdb4c1dc2a1e25d8fc455abb0e9984040362415f75e
+size 828282815

pytorch_model-00013-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b33f56099bcce54d88868a0c03490e88f77d5ddd21646f44564f310407e3790e
+size 828282815

pytorch_model-00014-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b432f34080904457ace6d8bb33014f0961bf545d8650501a0830b005fc55a106
+size 828282815

pytorch_model-00015-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c6b11a9f447130bc309d44022b743ea23f6366e7593cdff69aea06676014e3c
+size 828282815

pytorch_model-00016-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7d71171af454993fb6f0dd173893b284010ed0ed5cf4056dbb29a636b77589d
+size 828282815

pytorch_model-00017-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9a934ccb422ae26103dfe6ed5b206a7c3085793da209bf42959eafab872fe3c
+size 828282815

pytorch_model-00018-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82e8c134cb362a44c3b17cbe747995d71aa6e30f82d98e8de7d1c4f6946e675e
+size 828282815

pytorch_model-00019-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a112b9ee7afa032e01f232e0c27beb5be11b50dc3472068bc40a01b8d1b7bf8f
+size 828282815

pytorch_model-00020-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72af340fb5e52d4f865cc05d098de3b3812085ad9415e79dc2a9e5df24533ef6
+size 828282815

pytorch_model-00021-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7040115358e41d014586471fca610e1e0fb3c6cad1f7a136d78aca758f7af4c
+size 828282815

pytorch_model-00022-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e77f00345a8f4abbbb0399e3cbfde2d70038b5cb1571b4ed5e5f846b691a9ab
+size 828282815

pytorch_model-00023-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:562853637d78b8ec53f520390873fd98a2c596815ba14e45da1452e87bf2d482
+size 828282815

pytorch_model-00024-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77efb9164bfa80c31fa9d18549a72c09ec56a65e704630864eb3ff7020d8447e
+size 828282815

pytorch_model-00025-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b396a0b303e9e165d1c2c049561b4942fe9a377fb188dd6038cf314440202e3
+size 828282815

pytorch_model-00026-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbe238593d518f11a0f80aacc97bfc09dec07a255ce53069636ce0b8d8e854e6
+size 828282815

pytorch_model-00027-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:824faea6505ce3c8085a652cd5057ad8b24f6303a3fb6c94b85222842b4a39a7
+size 828282815

pytorch_model-00028-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54d9b9c9b370beb6d785939b2c413ed8d360b102ccfcb27b65524a79527e5838
+size 828282815

pytorch_model-00029-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caa14bf23e2a6c4a3aa4f1ab89e1802f05d8deb20fdb8341b9dad3edaea3f7d2
+size 828282815

pytorch_model-00030-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:503999ce1e3e9bfca7d901a9fb350965cab524e0395aed727ab6339753e0944a
+size 828282815

pytorch_model-00031-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f673e53d87d48f6c4dc3be546db990f67c48301d8696791b8ae2c25156fd0b8
+size 828282815

pytorch_model-00032-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd7e53b3f4918780ccdc0b56ad72542ceee58ae4baf80b7a4b2a814bf2fb22ca
+size 828282815

pytorch_model-00033-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce6a8d9c92624e65730753fe62e53df2a38fbe603fe9ded21da2ec31b29dcf6c
+size 828282815

pytorch_model-00034-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21da34bb9a155574461e25f7d2ded82b15c2db23d66771760205fa43a18ca31e
+size 660772125

pytorch_model.bin.index.json

@@ -0,0 +1,203 @@
+{
+  "metadata": {
+    "total_size": 27686882816
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00002-of-00034.bin",
+    "transformer.h.0.input_layernorm.bias": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.0.input_layernorm.weight": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.0.self_attention.dense.weight": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.1.input_layernorm.bias": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.1.input_layernorm.weight": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.1.self_attention.dense.weight": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.10.input_layernorm.bias": "pytorch_model-00012-of-00034.bin",
+    "transformer.h.10.input_layernorm.weight": "pytorch_model-00012-of-00034.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00034.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00034.bin",
+    "transformer.h.10.self_attention.dense.weight": "pytorch_model-00012-of-00034.bin",
+    "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00012-of-00034.bin",
+    "transformer.h.11.input_layernorm.bias": "pytorch_model-00013-of-00034.bin",
+    "transformer.h.11.input_layernorm.weight": "pytorch_model-00013-of-00034.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00034.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00034.bin",
+    "transformer.h.11.self_attention.dense.weight": "pytorch_model-00013-of-00034.bin",
+    "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00013-of-00034.bin",
+    "transformer.h.12.input_layernorm.bias": "pytorch_model-00014-of-00034.bin",
+    "transformer.h.12.input_layernorm.weight": "pytorch_model-00014-of-00034.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00015-of-00034.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00015-of-00034.bin",
+    "transformer.h.12.self_attention.dense.weight": "pytorch_model-00014-of-00034.bin",
+    "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00014-of-00034.bin",
+    "transformer.h.13.input_layernorm.bias": "pytorch_model-00015-of-00034.bin",
+    "transformer.h.13.input_layernorm.weight": "pytorch_model-00015-of-00034.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00016-of-00034.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00016-of-00034.bin",
+    "transformer.h.13.self_attention.dense.weight": "pytorch_model-00015-of-00034.bin",
+    "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00015-of-00034.bin",
+    "transformer.h.14.input_layernorm.bias": "pytorch_model-00016-of-00034.bin",
+    "transformer.h.14.input_layernorm.weight": "pytorch_model-00016-of-00034.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00017-of-00034.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00017-of-00034.bin",
+    "transformer.h.14.self_attention.dense.weight": "pytorch_model-00016-of-00034.bin",
+    "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00016-of-00034.bin",
+    "transformer.h.15.input_layernorm.bias": "pytorch_model-00017-of-00034.bin",
+    "transformer.h.15.input_layernorm.weight": "pytorch_model-00017-of-00034.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00018-of-00034.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00018-of-00034.bin",
+    "transformer.h.15.self_attention.dense.weight": "pytorch_model-00017-of-00034.bin",
+    "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00017-of-00034.bin",
+    "transformer.h.16.input_layernorm.bias": "pytorch_model-00018-of-00034.bin",
+    "transformer.h.16.input_layernorm.weight": "pytorch_model-00018-of-00034.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00019-of-00034.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00019-of-00034.bin",
+    "transformer.h.16.self_attention.dense.weight": "pytorch_model-00018-of-00034.bin",
+    "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00018-of-00034.bin",
+    "transformer.h.17.input_layernorm.bias": "pytorch_model-00019-of-00034.bin",
+    "transformer.h.17.input_layernorm.weight": "pytorch_model-00019-of-00034.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00020-of-00034.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00020-of-00034.bin",
+    "transformer.h.17.self_attention.dense.weight": "pytorch_model-00019-of-00034.bin",
+    "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00019-of-00034.bin",
+    "transformer.h.18.input_layernorm.bias": "pytorch_model-00020-of-00034.bin",
+    "transformer.h.18.input_layernorm.weight": "pytorch_model-00020-of-00034.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00021-of-00034.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00021-of-00034.bin",
+    "transformer.h.18.self_attention.dense.weight": "pytorch_model-00020-of-00034.bin",
+    "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00020-of-00034.bin",
+    "transformer.h.19.input_layernorm.bias": "pytorch_model-00021-of-00034.bin",
+    "transformer.h.19.input_layernorm.weight": "pytorch_model-00021-of-00034.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00022-of-00034.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00022-of-00034.bin",
+    "transformer.h.19.self_attention.dense.weight": "pytorch_model-00021-of-00034.bin",
+    "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00021-of-00034.bin",
+    "transformer.h.2.input_layernorm.bias": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.2.input_layernorm.weight": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00034.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00034.bin",
+    "transformer.h.2.self_attention.dense.weight": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.20.input_layernorm.bias": "pytorch_model-00022-of-00034.bin",
+    "transformer.h.20.input_layernorm.weight": "pytorch_model-00022-of-00034.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00023-of-00034.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00023-of-00034.bin",
+    "transformer.h.20.self_attention.dense.weight": "pytorch_model-00022-of-00034.bin",
+    "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00022-of-00034.bin",
+    "transformer.h.21.input_layernorm.bias": "pytorch_model-00023-of-00034.bin",
+    "transformer.h.21.input_layernorm.weight": "pytorch_model-00023-of-00034.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00024-of-00034.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00024-of-00034.bin",
+    "transformer.h.21.self_attention.dense.weight": "pytorch_model-00023-of-00034.bin",
+    "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00023-of-00034.bin",
+    "transformer.h.22.input_layernorm.bias": "pytorch_model-00024-of-00034.bin",
+    "transformer.h.22.input_layernorm.weight": "pytorch_model-00024-of-00034.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00025-of-00034.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00025-of-00034.bin",
+    "transformer.h.22.self_attention.dense.weight": "pytorch_model-00024-of-00034.bin",
+    "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00024-of-00034.bin",
+    "transformer.h.23.input_layernorm.bias": "pytorch_model-00025-of-00034.bin",
+    "transformer.h.23.input_layernorm.weight": "pytorch_model-00025-of-00034.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00026-of-00034.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00026-of-00034.bin",
+    "transformer.h.23.self_attention.dense.weight": "pytorch_model-00025-of-00034.bin",
+    "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00025-of-00034.bin",
+    "transformer.h.24.input_layernorm.bias": "pytorch_model-00026-of-00034.bin",
+    "transformer.h.24.input_layernorm.weight": "pytorch_model-00026-of-00034.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00027-of-00034.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00027-of-00034.bin",
+    "transformer.h.24.self_attention.dense.weight": "pytorch_model-00026-of-00034.bin",
+    "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00026-of-00034.bin",
+    "transformer.h.25.input_layernorm.bias": "pytorch_model-00027-of-00034.bin",
+    "transformer.h.25.input_layernorm.weight": "pytorch_model-00027-of-00034.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00028-of-00034.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00028-of-00034.bin",
+    "transformer.h.25.self_attention.dense.weight": "pytorch_model-00027-of-00034.bin",
+    "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00027-of-00034.bin",
+    "transformer.h.26.input_layernorm.bias": "pytorch_model-00028-of-00034.bin",
+    "transformer.h.26.input_layernorm.weight": "pytorch_model-00028-of-00034.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00029-of-00034.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00029-of-00034.bin",
+    "transformer.h.26.self_attention.dense.weight": "pytorch_model-00028-of-00034.bin",
+    "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00028-of-00034.bin",
+    "transformer.h.27.input_layernorm.bias": "pytorch_model-00029-of-00034.bin",
+    "transformer.h.27.input_layernorm.weight": "pytorch_model-00029-of-00034.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00030-of-00034.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00030-of-00034.bin",
+    "transformer.h.27.self_attention.dense.weight": "pytorch_model-00029-of-00034.bin",
+    "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00029-of-00034.bin",
+    "transformer.h.28.input_layernorm.bias": "pytorch_model-00030-of-00034.bin",
+    "transformer.h.28.input_layernorm.weight": "pytorch_model-00030-of-00034.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00031-of-00034.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00031-of-00034.bin",
+    "transformer.h.28.self_attention.dense.weight": "pytorch_model-00030-of-00034.bin",
+    "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00030-of-00034.bin",
+    "transformer.h.29.input_layernorm.bias": "pytorch_model-00031-of-00034.bin",
+    "transformer.h.29.input_layernorm.weight": "pytorch_model-00031-of-00034.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00032-of-00034.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00032-of-00034.bin",
+    "transformer.h.29.self_attention.dense.weight": "pytorch_model-00031-of-00034.bin",
+    "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00031-of-00034.bin",
+    "transformer.h.3.input_layernorm.bias": "pytorch_model-00005-of-00034.bin",
+    "transformer.h.3.input_layernorm.weight": "pytorch_model-00005-of-00034.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00034.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00034.bin",
+    "transformer.h.3.self_attention.dense.weight": "pytorch_model-00005-of-00034.bin",
+    "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00005-of-00034.bin",
+    "transformer.h.30.input_layernorm.bias": "pytorch_model-00032-of-00034.bin",
+    "transformer.h.30.input_layernorm.weight": "pytorch_model-00032-of-00034.bin",
+    "transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00033-of-00034.bin",
+    "transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00033-of-00034.bin",
+    "transformer.h.30.self_attention.dense.weight": "pytorch_model-00032-of-00034.bin",
+    "transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00032-of-00034.bin",
+    "transformer.h.31.input_layernorm.bias": "pytorch_model-00033-of-00034.bin",
+    "transformer.h.31.input_layernorm.weight": "pytorch_model-00033-of-00034.bin",
+    "transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00034-of-00034.bin",
+    "transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00034-of-00034.bin",
+    "transformer.h.31.self_attention.dense.weight": "pytorch_model-00033-of-00034.bin",
+    "transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00033-of-00034.bin",
+    "transformer.h.4.input_layernorm.bias": "pytorch_model-00006-of-00034.bin",
+    "transformer.h.4.input_layernorm.weight": "pytorch_model-00006-of-00034.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00034.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00034.bin",
+    "transformer.h.4.self_attention.dense.weight": "pytorch_model-00006-of-00034.bin",
+    "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00006-of-00034.bin",
+    "transformer.h.5.input_layernorm.bias": "pytorch_model-00007-of-00034.bin",
+    "transformer.h.5.input_layernorm.weight": "pytorch_model-00007-of-00034.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00034.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00034.bin",
+    "transformer.h.5.self_attention.dense.weight": "pytorch_model-00007-of-00034.bin",
+    "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00007-of-00034.bin",
+    "transformer.h.6.input_layernorm.bias": "pytorch_model-00008-of-00034.bin",
+    "transformer.h.6.input_layernorm.weight": "pytorch_model-00008-of-00034.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00034.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00034.bin",
+    "transformer.h.6.self_attention.dense.weight": "pytorch_model-00008-of-00034.bin",
+    "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00008-of-00034.bin",
+    "transformer.h.7.input_layernorm.bias": "pytorch_model-00009-of-00034.bin",
+    "transformer.h.7.input_layernorm.weight": "pytorch_model-00009-of-00034.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00034.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00034.bin",
+    "transformer.h.7.self_attention.dense.weight": "pytorch_model-00009-of-00034.bin",
+    "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00009-of-00034.bin",
+    "transformer.h.8.input_layernorm.bias": "pytorch_model-00010-of-00034.bin",
+    "transformer.h.8.input_layernorm.weight": "pytorch_model-00010-of-00034.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00034.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00034.bin",
+    "transformer.h.8.self_attention.dense.weight": "pytorch_model-00010-of-00034.bin",
+    "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00010-of-00034.bin",
+    "transformer.h.9.input_layernorm.bias": "pytorch_model-00011-of-00034.bin",
+    "transformer.h.9.input_layernorm.weight": "pytorch_model-00011-of-00034.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00034.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00034.bin",
+    "transformer.h.9.self_attention.dense.weight": "pytorch_model-00011-of-00034.bin",
+    "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00011-of-00034.bin",
+    "transformer.ln_f.bias": "pytorch_model-00034-of-00034.bin",
+    "transformer.ln_f.weight": "pytorch_model-00034-of-00034.bin",
+    "transformer.word_embeddings.weight": "pytorch_model-00002-of-00034.bin"
+  }
+}