Upload folder using huggingface_hub
#3
by
Trisert
- opened
- config.json +29 -0
- generation_config.json +6 -0
- push.py +10 -0
- pytorch_model-00001-of-00034.bin +3 -0
- pytorch_model-00002-of-00034.bin +3 -0
- pytorch_model-00003-of-00034.bin +3 -0
- pytorch_model-00004-of-00034.bin +3 -0
- pytorch_model-00005-of-00034.bin +3 -0
- pytorch_model-00006-of-00034.bin +3 -0
- pytorch_model-00007-of-00034.bin +3 -0
- pytorch_model-00008-of-00034.bin +3 -0
- pytorch_model-00009-of-00034.bin +3 -0
- pytorch_model-00010-of-00034.bin +3 -0
- pytorch_model-00011-of-00034.bin +3 -0
- pytorch_model-00012-of-00034.bin +3 -0
- pytorch_model-00013-of-00034.bin +3 -0
- pytorch_model-00014-of-00034.bin +3 -0
- pytorch_model-00015-of-00034.bin +3 -0
- pytorch_model-00016-of-00034.bin +3 -0
- pytorch_model-00017-of-00034.bin +3 -0
- pytorch_model-00018-of-00034.bin +3 -0
- pytorch_model-00019-of-00034.bin +3 -0
- pytorch_model-00020-of-00034.bin +3 -0
- pytorch_model-00021-of-00034.bin +3 -0
- pytorch_model-00022-of-00034.bin +3 -0
- pytorch_model-00023-of-00034.bin +3 -0
- pytorch_model-00024-of-00034.bin +3 -0
- pytorch_model-00025-of-00034.bin +3 -0
- pytorch_model-00026-of-00034.bin +3 -0
- pytorch_model-00027-of-00034.bin +3 -0
- pytorch_model-00028-of-00034.bin +3 -0
- pytorch_model-00029-of-00034.bin +3 -0
- pytorch_model-00030-of-00034.bin +3 -0
- pytorch_model-00031-of-00034.bin +3 -0
- pytorch_model-00032-of-00034.bin +3 -0
- pytorch_model-00033-of-00034.bin +3 -0
- pytorch_model-00034-of-00034.bin +3 -0
- pytorch_model.bin.index.json +203 -0
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "tiiuae/falcon-7b-instruct",
|
3 |
+
"alibi": false,
|
4 |
+
"apply_residual_connection_post_layernorm": false,
|
5 |
+
"architectures": [
|
6 |
+
"RWForCausalLM"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"auto_map": {
|
10 |
+
"AutoConfig": "tiiuae/falcon-7b-instruct--configuration_RW.RWConfig",
|
11 |
+
"AutoModelForCausalLM": "tiiuae/falcon-7b-instruct--modelling_RW.RWForCausalLM"
|
12 |
+
},
|
13 |
+
"bias": false,
|
14 |
+
"bos_token_id": 11,
|
15 |
+
"eos_token_id": 11,
|
16 |
+
"hidden_dropout": 0.0,
|
17 |
+
"hidden_size": 4544,
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"layer_norm_epsilon": 1e-05,
|
20 |
+
"model_type": "RefinedWebModel",
|
21 |
+
"multi_query": true,
|
22 |
+
"n_head": 71,
|
23 |
+
"n_layer": 32,
|
24 |
+
"parallel_attn": true,
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.31.0.dev0",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 65024
|
29 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.31.0.dev0"
|
6 |
+
}
|
push.py
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from huggingface_hub import HfApi
|
2 |
+
|
3 |
+
api = HfApi()
|
4 |
+
|
5 |
+
api.upload_folder(
|
6 |
+
repo_id="Trisert/falcon-7b-instruct-sharded",
|
7 |
+
folder_path=".",
|
8 |
+
multi_commits=True,
|
9 |
+
multi_commits_verbose=True,
|
10 |
+
)
|
pytorch_model-00001-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f713a462ff20e675c62e450a60f51aed6f65430a165f82b4f709b539f4342361
|
3 |
+
size 537
|
pytorch_model-00002-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4bd830c110b6519dbe116c07659017a5bc8c0956a22b8081872a9ce5f84649c
|
3 |
+
size 1181877226
|
pytorch_model-00003-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c6b806cca45e0454e7c336a8af3b881d07d386eccf975453019215982d29e9a
|
3 |
+
size 995830467
|
pytorch_model-00004-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08c63aacab7addf366cfc9228dcf33b3fcda1eedd4d51a4de0a94447c10436f3
|
3 |
+
size 828282815
|
pytorch_model-00005-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5a15ea20cbc030662245df3dbdd2842caf67432d606433ef783f0f7e1dcd56a
|
3 |
+
size 828282815
|
pytorch_model-00006-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c104d0639442e3e14d4d833980227a0640630def1c98010cbf14869002d536d4
|
3 |
+
size 828282815
|
pytorch_model-00007-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d1ea08935c3d7208f32b7031333e1fba34f40e11c707be20ca1bc3db0e9e4a7
|
3 |
+
size 828282815
|
pytorch_model-00008-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44710d73f3e90e91abb4d83338429d8c12fed43a23dd51dea9186ba999854201
|
3 |
+
size 828282815
|
pytorch_model-00009-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:873a9dc8cdfc9daf85f7341108dc593719dd1cf3eb1fe37a72e5acf0d981b155
|
3 |
+
size 828282815
|
pytorch_model-00010-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d24732c5973d0e1c102a99e017d7faad052c5accb569642d85dd85d7ec5ec65
|
3 |
+
size 828282815
|
pytorch_model-00011-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e887a35b06fe4526d212d6858f863a8dbd8b91a727f66a4fb5e276f4a26ad2fe
|
3 |
+
size 828282815
|
pytorch_model-00012-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:622ecad252da95c0902b9cdb4c1dc2a1e25d8fc455abb0e9984040362415f75e
|
3 |
+
size 828282815
|
pytorch_model-00013-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b33f56099bcce54d88868a0c03490e88f77d5ddd21646f44564f310407e3790e
|
3 |
+
size 828282815
|
pytorch_model-00014-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b432f34080904457ace6d8bb33014f0961bf545d8650501a0830b005fc55a106
|
3 |
+
size 828282815
|
pytorch_model-00015-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c6b11a9f447130bc309d44022b743ea23f6366e7593cdff69aea06676014e3c
|
3 |
+
size 828282815
|
pytorch_model-00016-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7d71171af454993fb6f0dd173893b284010ed0ed5cf4056dbb29a636b77589d
|
3 |
+
size 828282815
|
pytorch_model-00017-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9a934ccb422ae26103dfe6ed5b206a7c3085793da209bf42959eafab872fe3c
|
3 |
+
size 828282815
|
pytorch_model-00018-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82e8c134cb362a44c3b17cbe747995d71aa6e30f82d98e8de7d1c4f6946e675e
|
3 |
+
size 828282815
|
pytorch_model-00019-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a112b9ee7afa032e01f232e0c27beb5be11b50dc3472068bc40a01b8d1b7bf8f
|
3 |
+
size 828282815
|
pytorch_model-00020-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72af340fb5e52d4f865cc05d098de3b3812085ad9415e79dc2a9e5df24533ef6
|
3 |
+
size 828282815
|
pytorch_model-00021-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7040115358e41d014586471fca610e1e0fb3c6cad1f7a136d78aca758f7af4c
|
3 |
+
size 828282815
|
pytorch_model-00022-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e77f00345a8f4abbbb0399e3cbfde2d70038b5cb1571b4ed5e5f846b691a9ab
|
3 |
+
size 828282815
|
pytorch_model-00023-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:562853637d78b8ec53f520390873fd98a2c596815ba14e45da1452e87bf2d482
|
3 |
+
size 828282815
|
pytorch_model-00024-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77efb9164bfa80c31fa9d18549a72c09ec56a65e704630864eb3ff7020d8447e
|
3 |
+
size 828282815
|
pytorch_model-00025-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b396a0b303e9e165d1c2c049561b4942fe9a377fb188dd6038cf314440202e3
|
3 |
+
size 828282815
|
pytorch_model-00026-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fbe238593d518f11a0f80aacc97bfc09dec07a255ce53069636ce0b8d8e854e6
|
3 |
+
size 828282815
|
pytorch_model-00027-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:824faea6505ce3c8085a652cd5057ad8b24f6303a3fb6c94b85222842b4a39a7
|
3 |
+
size 828282815
|
pytorch_model-00028-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54d9b9c9b370beb6d785939b2c413ed8d360b102ccfcb27b65524a79527e5838
|
3 |
+
size 828282815
|
pytorch_model-00029-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:caa14bf23e2a6c4a3aa4f1ab89e1802f05d8deb20fdb8341b9dad3edaea3f7d2
|
3 |
+
size 828282815
|
pytorch_model-00030-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:503999ce1e3e9bfca7d901a9fb350965cab524e0395aed727ab6339753e0944a
|
3 |
+
size 828282815
|
pytorch_model-00031-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f673e53d87d48f6c4dc3be546db990f67c48301d8696791b8ae2c25156fd0b8
|
3 |
+
size 828282815
|
pytorch_model-00032-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd7e53b3f4918780ccdc0b56ad72542ceee58ae4baf80b7a4b2a814bf2fb22ca
|
3 |
+
size 828282815
|
pytorch_model-00033-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce6a8d9c92624e65730753fe62e53df2a38fbe603fe9ded21da2ec31b29dcf6c
|
3 |
+
size 828282815
|
pytorch_model-00034-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21da34bb9a155574461e25f7d2ded82b15c2db23d66771760205fa43a18ca31e
|
3 |
+
size 660772125
|
pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,203 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 27686882816
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "pytorch_model-00002-of-00034.bin",
|
7 |
+
"transformer.h.0.input_layernorm.bias": "pytorch_model-00003-of-00034.bin",
|
8 |
+
"transformer.h.0.input_layernorm.weight": "pytorch_model-00003-of-00034.bin",
|
9 |
+
"transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00034.bin",
|
10 |
+
"transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00034.bin",
|
11 |
+
"transformer.h.0.self_attention.dense.weight": "pytorch_model-00003-of-00034.bin",
|
12 |
+
"transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00003-of-00034.bin",
|
13 |
+
"transformer.h.1.input_layernorm.bias": "pytorch_model-00003-of-00034.bin",
|
14 |
+
"transformer.h.1.input_layernorm.weight": "pytorch_model-00003-of-00034.bin",
|
15 |
+
"transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00034.bin",
|
16 |
+
"transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00034.bin",
|
17 |
+
"transformer.h.1.self_attention.dense.weight": "pytorch_model-00003-of-00034.bin",
|
18 |
+
"transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00003-of-00034.bin",
|
19 |
+
"transformer.h.10.input_layernorm.bias": "pytorch_model-00012-of-00034.bin",
|
20 |
+
"transformer.h.10.input_layernorm.weight": "pytorch_model-00012-of-00034.bin",
|
21 |
+
"transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00034.bin",
|
22 |
+
"transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00034.bin",
|
23 |
+
"transformer.h.10.self_attention.dense.weight": "pytorch_model-00012-of-00034.bin",
|
24 |
+
"transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00012-of-00034.bin",
|
25 |
+
"transformer.h.11.input_layernorm.bias": "pytorch_model-00013-of-00034.bin",
|
26 |
+
"transformer.h.11.input_layernorm.weight": "pytorch_model-00013-of-00034.bin",
|
27 |
+
"transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00034.bin",
|
28 |
+
"transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00034.bin",
|
29 |
+
"transformer.h.11.self_attention.dense.weight": "pytorch_model-00013-of-00034.bin",
|
30 |
+
"transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00013-of-00034.bin",
|
31 |
+
"transformer.h.12.input_layernorm.bias": "pytorch_model-00014-of-00034.bin",
|
32 |
+
"transformer.h.12.input_layernorm.weight": "pytorch_model-00014-of-00034.bin",
|
33 |
+
"transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00015-of-00034.bin",
|
34 |
+
"transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00015-of-00034.bin",
|
35 |
+
"transformer.h.12.self_attention.dense.weight": "pytorch_model-00014-of-00034.bin",
|
36 |
+
"transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00014-of-00034.bin",
|
37 |
+
"transformer.h.13.input_layernorm.bias": "pytorch_model-00015-of-00034.bin",
|
38 |
+
"transformer.h.13.input_layernorm.weight": "pytorch_model-00015-of-00034.bin",
|
39 |
+
"transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00016-of-00034.bin",
|
40 |
+
"transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00016-of-00034.bin",
|
41 |
+
"transformer.h.13.self_attention.dense.weight": "pytorch_model-00015-of-00034.bin",
|
42 |
+
"transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00015-of-00034.bin",
|
43 |
+
"transformer.h.14.input_layernorm.bias": "pytorch_model-00016-of-00034.bin",
|
44 |
+
"transformer.h.14.input_layernorm.weight": "pytorch_model-00016-of-00034.bin",
|
45 |
+
"transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00017-of-00034.bin",
|
46 |
+
"transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00017-of-00034.bin",
|
47 |
+
"transformer.h.14.self_attention.dense.weight": "pytorch_model-00016-of-00034.bin",
|
48 |
+
"transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00016-of-00034.bin",
|
49 |
+
"transformer.h.15.input_layernorm.bias": "pytorch_model-00017-of-00034.bin",
|
50 |
+
"transformer.h.15.input_layernorm.weight": "pytorch_model-00017-of-00034.bin",
|
51 |
+
"transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00018-of-00034.bin",
|
52 |
+
"transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00018-of-00034.bin",
|
53 |
+
"transformer.h.15.self_attention.dense.weight": "pytorch_model-00017-of-00034.bin",
|
54 |
+
"transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00017-of-00034.bin",
|
55 |
+
"transformer.h.16.input_layernorm.bias": "pytorch_model-00018-of-00034.bin",
|
56 |
+
"transformer.h.16.input_layernorm.weight": "pytorch_model-00018-of-00034.bin",
|
57 |
+
"transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00019-of-00034.bin",
|
58 |
+
"transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00019-of-00034.bin",
|
59 |
+
"transformer.h.16.self_attention.dense.weight": "pytorch_model-00018-of-00034.bin",
|
60 |
+
"transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00018-of-00034.bin",
|
61 |
+
"transformer.h.17.input_layernorm.bias": "pytorch_model-00019-of-00034.bin",
|
62 |
+
"transformer.h.17.input_layernorm.weight": "pytorch_model-00019-of-00034.bin",
|
63 |
+
"transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00020-of-00034.bin",
|
64 |
+
"transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00020-of-00034.bin",
|
65 |
+
"transformer.h.17.self_attention.dense.weight": "pytorch_model-00019-of-00034.bin",
|
66 |
+
"transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00019-of-00034.bin",
|
67 |
+
"transformer.h.18.input_layernorm.bias": "pytorch_model-00020-of-00034.bin",
|
68 |
+
"transformer.h.18.input_layernorm.weight": "pytorch_model-00020-of-00034.bin",
|
69 |
+
"transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00021-of-00034.bin",
|
70 |
+
"transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00021-of-00034.bin",
|
71 |
+
"transformer.h.18.self_attention.dense.weight": "pytorch_model-00020-of-00034.bin",
|
72 |
+
"transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00020-of-00034.bin",
|
73 |
+
"transformer.h.19.input_layernorm.bias": "pytorch_model-00021-of-00034.bin",
|
74 |
+
"transformer.h.19.input_layernorm.weight": "pytorch_model-00021-of-00034.bin",
|
75 |
+
"transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00022-of-00034.bin",
|
76 |
+
"transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00022-of-00034.bin",
|
77 |
+
"transformer.h.19.self_attention.dense.weight": "pytorch_model-00021-of-00034.bin",
|
78 |
+
"transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00021-of-00034.bin",
|
79 |
+
"transformer.h.2.input_layernorm.bias": "pytorch_model-00004-of-00034.bin",
|
80 |
+
"transformer.h.2.input_layernorm.weight": "pytorch_model-00004-of-00034.bin",
|
81 |
+
"transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00034.bin",
|
82 |
+
"transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00034.bin",
|
83 |
+
"transformer.h.2.self_attention.dense.weight": "pytorch_model-00004-of-00034.bin",
|
84 |
+
"transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00004-of-00034.bin",
|
85 |
+
"transformer.h.20.input_layernorm.bias": "pytorch_model-00022-of-00034.bin",
|
86 |
+
"transformer.h.20.input_layernorm.weight": "pytorch_model-00022-of-00034.bin",
|
87 |
+
"transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00023-of-00034.bin",
|
88 |
+
"transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00023-of-00034.bin",
|
89 |
+
"transformer.h.20.self_attention.dense.weight": "pytorch_model-00022-of-00034.bin",
|
90 |
+
"transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00022-of-00034.bin",
|
91 |
+
"transformer.h.21.input_layernorm.bias": "pytorch_model-00023-of-00034.bin",
|
92 |
+
"transformer.h.21.input_layernorm.weight": "pytorch_model-00023-of-00034.bin",
|
93 |
+
"transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00024-of-00034.bin",
|
94 |
+
"transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00024-of-00034.bin",
|
95 |
+
"transformer.h.21.self_attention.dense.weight": "pytorch_model-00023-of-00034.bin",
|
96 |
+
"transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00023-of-00034.bin",
|
97 |
+
"transformer.h.22.input_layernorm.bias": "pytorch_model-00024-of-00034.bin",
|
98 |
+
"transformer.h.22.input_layernorm.weight": "pytorch_model-00024-of-00034.bin",
|
99 |
+
"transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00025-of-00034.bin",
|
100 |
+
"transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00025-of-00034.bin",
|
101 |
+
"transformer.h.22.self_attention.dense.weight": "pytorch_model-00024-of-00034.bin",
|
102 |
+
"transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00024-of-00034.bin",
|
103 |
+
"transformer.h.23.input_layernorm.bias": "pytorch_model-00025-of-00034.bin",
|
104 |
+
"transformer.h.23.input_layernorm.weight": "pytorch_model-00025-of-00034.bin",
|
105 |
+
"transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00026-of-00034.bin",
|
106 |
+
"transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00026-of-00034.bin",
|
107 |
+
"transformer.h.23.self_attention.dense.weight": "pytorch_model-00025-of-00034.bin",
|
108 |
+
"transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00025-of-00034.bin",
|
109 |
+
"transformer.h.24.input_layernorm.bias": "pytorch_model-00026-of-00034.bin",
|
110 |
+
"transformer.h.24.input_layernorm.weight": "pytorch_model-00026-of-00034.bin",
|
111 |
+
"transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00027-of-00034.bin",
|
112 |
+
"transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00027-of-00034.bin",
|
113 |
+
"transformer.h.24.self_attention.dense.weight": "pytorch_model-00026-of-00034.bin",
|
114 |
+
"transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00026-of-00034.bin",
|
115 |
+
"transformer.h.25.input_layernorm.bias": "pytorch_model-00027-of-00034.bin",
|
116 |
+
"transformer.h.25.input_layernorm.weight": "pytorch_model-00027-of-00034.bin",
|
117 |
+
"transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00028-of-00034.bin",
|
118 |
+
"transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00028-of-00034.bin",
|
119 |
+
"transformer.h.25.self_attention.dense.weight": "pytorch_model-00027-of-00034.bin",
|
120 |
+
"transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00027-of-00034.bin",
|
121 |
+
"transformer.h.26.input_layernorm.bias": "pytorch_model-00028-of-00034.bin",
|
122 |
+
"transformer.h.26.input_layernorm.weight": "pytorch_model-00028-of-00034.bin",
|
123 |
+
"transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00029-of-00034.bin",
|
124 |
+
"transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00029-of-00034.bin",
|
125 |
+
"transformer.h.26.self_attention.dense.weight": "pytorch_model-00028-of-00034.bin",
|
126 |
+
"transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00028-of-00034.bin",
|
127 |
+
"transformer.h.27.input_layernorm.bias": "pytorch_model-00029-of-00034.bin",
|
128 |
+
"transformer.h.27.input_layernorm.weight": "pytorch_model-00029-of-00034.bin",
|
129 |
+
"transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00030-of-00034.bin",
|
130 |
+
"transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00030-of-00034.bin",
|
131 |
+
"transformer.h.27.self_attention.dense.weight": "pytorch_model-00029-of-00034.bin",
|
132 |
+
"transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00029-of-00034.bin",
|
133 |
+
"transformer.h.28.input_layernorm.bias": "pytorch_model-00030-of-00034.bin",
|
134 |
+
"transformer.h.28.input_layernorm.weight": "pytorch_model-00030-of-00034.bin",
|
135 |
+
"transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00031-of-00034.bin",
|
136 |
+
"transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00031-of-00034.bin",
|
137 |
+
"transformer.h.28.self_attention.dense.weight": "pytorch_model-00030-of-00034.bin",
|
138 |
+
"transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00030-of-00034.bin",
|
139 |
+
"transformer.h.29.input_layernorm.bias": "pytorch_model-00031-of-00034.bin",
|
140 |
+
"transformer.h.29.input_layernorm.weight": "pytorch_model-00031-of-00034.bin",
|
141 |
+
"transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00032-of-00034.bin",
|
142 |
+
"transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00032-of-00034.bin",
|
143 |
+
"transformer.h.29.self_attention.dense.weight": "pytorch_model-00031-of-00034.bin",
|
144 |
+
"transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00031-of-00034.bin",
|
145 |
+
"transformer.h.3.input_layernorm.bias": "pytorch_model-00005-of-00034.bin",
|
146 |
+
"transformer.h.3.input_layernorm.weight": "pytorch_model-00005-of-00034.bin",
|
147 |
+
"transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00034.bin",
|
148 |
+
"transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00034.bin",
|
149 |
+
"transformer.h.3.self_attention.dense.weight": "pytorch_model-00005-of-00034.bin",
|
150 |
+
"transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00005-of-00034.bin",
|
151 |
+
"transformer.h.30.input_layernorm.bias": "pytorch_model-00032-of-00034.bin",
|
152 |
+
"transformer.h.30.input_layernorm.weight": "pytorch_model-00032-of-00034.bin",
|
153 |
+
"transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00033-of-00034.bin",
|
154 |
+
"transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00033-of-00034.bin",
|
155 |
+
"transformer.h.30.self_attention.dense.weight": "pytorch_model-00032-of-00034.bin",
|
156 |
+
"transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00032-of-00034.bin",
|
157 |
+
"transformer.h.31.input_layernorm.bias": "pytorch_model-00033-of-00034.bin",
|
158 |
+
"transformer.h.31.input_layernorm.weight": "pytorch_model-00033-of-00034.bin",
|
159 |
+
"transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00034-of-00034.bin",
|
160 |
+
"transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00034-of-00034.bin",
|
161 |
+
"transformer.h.31.self_attention.dense.weight": "pytorch_model-00033-of-00034.bin",
|
162 |
+
"transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00033-of-00034.bin",
|
163 |
+
"transformer.h.4.input_layernorm.bias": "pytorch_model-00006-of-00034.bin",
|
164 |
+
"transformer.h.4.input_layernorm.weight": "pytorch_model-00006-of-00034.bin",
|
165 |
+
"transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00034.bin",
|
166 |
+
"transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00034.bin",
|
167 |
+
"transformer.h.4.self_attention.dense.weight": "pytorch_model-00006-of-00034.bin",
|
168 |
+
"transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00006-of-00034.bin",
|
169 |
+
"transformer.h.5.input_layernorm.bias": "pytorch_model-00007-of-00034.bin",
|
170 |
+
"transformer.h.5.input_layernorm.weight": "pytorch_model-00007-of-00034.bin",
|
171 |
+
"transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00034.bin",
|
172 |
+
"transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00034.bin",
|
173 |
+
"transformer.h.5.self_attention.dense.weight": "pytorch_model-00007-of-00034.bin",
|
174 |
+
"transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00007-of-00034.bin",
|
175 |
+
"transformer.h.6.input_layernorm.bias": "pytorch_model-00008-of-00034.bin",
|
176 |
+
"transformer.h.6.input_layernorm.weight": "pytorch_model-00008-of-00034.bin",
|
177 |
+
"transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00034.bin",
|
178 |
+
"transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00034.bin",
|
179 |
+
"transformer.h.6.self_attention.dense.weight": "pytorch_model-00008-of-00034.bin",
|
180 |
+
"transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00008-of-00034.bin",
|
181 |
+
"transformer.h.7.input_layernorm.bias": "pytorch_model-00009-of-00034.bin",
|
182 |
+
"transformer.h.7.input_layernorm.weight": "pytorch_model-00009-of-00034.bin",
|
183 |
+
"transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00034.bin",
|
184 |
+
"transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00034.bin",
|
185 |
+
"transformer.h.7.self_attention.dense.weight": "pytorch_model-00009-of-00034.bin",
|
186 |
+
"transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00009-of-00034.bin",
|
187 |
+
"transformer.h.8.input_layernorm.bias": "pytorch_model-00010-of-00034.bin",
|
188 |
+
"transformer.h.8.input_layernorm.weight": "pytorch_model-00010-of-00034.bin",
|
189 |
+
"transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00034.bin",
|
190 |
+
"transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00034.bin",
|
191 |
+
"transformer.h.8.self_attention.dense.weight": "pytorch_model-00010-of-00034.bin",
|
192 |
+
"transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00010-of-00034.bin",
|
193 |
+
"transformer.h.9.input_layernorm.bias": "pytorch_model-00011-of-00034.bin",
|
194 |
+
"transformer.h.9.input_layernorm.weight": "pytorch_model-00011-of-00034.bin",
|
195 |
+
"transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00034.bin",
|
196 |
+
"transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00034.bin",
|
197 |
+
"transformer.h.9.self_attention.dense.weight": "pytorch_model-00011-of-00034.bin",
|
198 |
+
"transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00011-of-00034.bin",
|
199 |
+
"transformer.ln_f.bias": "pytorch_model-00034-of-00034.bin",
|
200 |
+
"transformer.ln_f.weight": "pytorch_model-00034-of-00034.bin",
|
201 |
+
"transformer.word_embeddings.weight": "pytorch_model-00002-of-00034.bin"
|
202 |
+
}
|
203 |
+
}
|