Upload folder using huggingface_hub
Browse files- Evaluation.txt +0 -0
- config.json +29 -0
- generation_config.json +6 -0
- pytorch_model-00001-of-00041.bin +3 -0
- pytorch_model-00002-of-00041.bin +3 -0
- pytorch_model-00003-of-00041.bin +3 -0
- pytorch_model-00004-of-00041.bin +3 -0
- pytorch_model-00005-of-00041.bin +3 -0
- pytorch_model-00006-of-00041.bin +3 -0
- pytorch_model-00007-of-00041.bin +3 -0
- pytorch_model-00008-of-00041.bin +3 -0
- pytorch_model-00009-of-00041.bin +3 -0
- pytorch_model-00010-of-00041.bin +3 -0
- pytorch_model-00011-of-00041.bin +3 -0
- pytorch_model-00012-of-00041.bin +3 -0
- pytorch_model-00013-of-00041.bin +3 -0
- pytorch_model-00014-of-00041.bin +3 -0
- pytorch_model-00015-of-00041.bin +3 -0
- pytorch_model-00016-of-00041.bin +3 -0
- pytorch_model-00017-of-00041.bin +3 -0
- pytorch_model-00018-of-00041.bin +3 -0
- pytorch_model-00019-of-00041.bin +3 -0
- pytorch_model-00020-of-00041.bin +3 -0
- pytorch_model-00021-of-00041.bin +3 -0
- pytorch_model-00022-of-00041.bin +3 -0
- pytorch_model-00023-of-00041.bin +3 -0
- pytorch_model-00024-of-00041.bin +3 -0
- pytorch_model-00025-of-00041.bin +3 -0
- pytorch_model-00026-of-00041.bin +3 -0
- pytorch_model-00027-of-00041.bin +3 -0
- pytorch_model-00028-of-00041.bin +3 -0
- pytorch_model-00029-of-00041.bin +3 -0
- pytorch_model-00030-of-00041.bin +3 -0
- pytorch_model-00031-of-00041.bin +3 -0
- pytorch_model-00032-of-00041.bin +3 -0
- pytorch_model-00033-of-00041.bin +3 -0
- pytorch_model-00034-of-00041.bin +3 -0
- pytorch_model-00035-of-00041.bin +3 -0
- pytorch_model-00036-of-00041.bin +3 -0
- pytorch_model-00037-of-00041.bin +3 -0
- pytorch_model-00038-of-00041.bin +3 -0
- pytorch_model-00039-of-00041.bin +3 -0
- pytorch_model-00040-of-00041.bin +3 -0
- pytorch_model-00041-of-00041.bin +3 -0
- pytorch_model.bin.index.json +651 -0
- special_tokens_map.json +16 -0
- tokenizer.json +0 -0
- tokenizer_config.json +7 -0
Evaluation.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openbuddy-falcon-180b-v13-preview1",
|
3 |
+
"alibi": false,
|
4 |
+
"architectures": [
|
5 |
+
"FalconForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bias": false,
|
9 |
+
"bos_token_id": 11,
|
10 |
+
"eos_token_id": 11,
|
11 |
+
"hidden_dropout": 0.0,
|
12 |
+
"hidden_size": 14848,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"layer_norm_epsilon": 1e-05,
|
15 |
+
"max_position_embeddings": 2048,
|
16 |
+
"model_type": "falcon",
|
17 |
+
"multi_query": true,
|
18 |
+
"new_decoder_architecture": true,
|
19 |
+
"num_attention_heads": 232,
|
20 |
+
"num_hidden_layers": 80,
|
21 |
+
"num_kv_heads": 8,
|
22 |
+
"parallel_attn": true,
|
23 |
+
"rope_scaling": null,
|
24 |
+
"rope_theta": 10000.0,
|
25 |
+
"torch_dtype": "bfloat16",
|
26 |
+
"transformers_version": "4.35.0.dev0",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 70656
|
29 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 11,
|
4 |
+
"eos_token_id": 11,
|
5 |
+
"transformers_version": "4.35.0.dev0"
|
6 |
+
}
|
pytorch_model-00001-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d68607b9b80261b74dc638156834ab57ae6dc996bae771e78510b1306fbbbaa
|
3 |
+
size 9213960603
|
pytorch_model-00002-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5885fd2fc9b2b6861cd6d984018ba0696a442b05c7b20b8a7a7bee25bc4c532
|
3 |
+
size 8879584803
|
pytorch_model-00003-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5138682e8736f612f7e85f6d5860b4e7bdf213cea3692e5c6366ab60c08731cf
|
3 |
+
size 8879584803
|
pytorch_model-00004-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef4e7401e7ff8563b50cf8c3b91cc76db1645f07beb555137600ee6a33ec1921
|
3 |
+
size 8879584803
|
pytorch_model-00005-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab475292cbe502e4c75ab9a937f344063fd598d8e1dd7b3fb0cc34d46dbd4808
|
3 |
+
size 8879584803
|
pytorch_model-00006-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bcfb89963d02589647c4f3a0607607a58eb1271969969ed411aa90bfa659015
|
3 |
+
size 8879584803
|
pytorch_model-00007-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c2f6de4add3586ba89d25f6278a69338f9fc13fa513f016806b3f0c6d550d09
|
3 |
+
size 8879584803
|
pytorch_model-00008-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ee0110815ca87db674f0c876c1d5b88d90f552c6494a7a9dffc0df58b54ffa6
|
3 |
+
size 8879584803
|
pytorch_model-00009-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b93e913b154e436f028c019fd3a6760c47f675520c52cf1b9b9a06c613c4e92
|
3 |
+
size 8879584803
|
pytorch_model-00010-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6074b7bc0bf78aaf86042d16943e449049d64dba9ab405b71776e0fabd060b95
|
3 |
+
size 8879584803
|
pytorch_model-00011-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa90ec9118059b7482d7eb3061da3b4e50a5d01fe5b1c9ff3e63a10415997e9a
|
3 |
+
size 8879584803
|
pytorch_model-00012-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eaeb3cff49166411a5cfe37254f92052b3943914af74232ee6c3b369360cdb61
|
3 |
+
size 8879584803
|
pytorch_model-00013-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7caf022bf5e4a71302968c082e2b0073a2ece8342dd30e9e316504a45f0fac0e
|
3 |
+
size 8879584803
|
pytorch_model-00014-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a996458358a7188a893f11aadf2c0d1b54f6c424e20162c72d2a7ce6c7e83575
|
3 |
+
size 8879584803
|
pytorch_model-00015-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2539082b6009ae5ea75146712c8c8485fc36dfe3589802eb1590ecbb9e29c3e9
|
3 |
+
size 8879584803
|
pytorch_model-00016-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01361e426eeca370696925f8b24582a9395411dcb23a60f746449ac8da6bc503
|
3 |
+
size 8879584803
|
pytorch_model-00017-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70c17b80d2feaab19b5a6f466367c6b32a95e03a47d718fb2793af6fcbbe3d1f
|
3 |
+
size 8879584803
|
pytorch_model-00018-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c09247b11139c9f1f25ef538b97a4b9fc388b6da91146aecf2bfb9d0dd47f366
|
3 |
+
size 8879584803
|
pytorch_model-00019-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:779f96795840026c70dfe127b89813084585e99843efadcd40712b881abad5f8
|
3 |
+
size 8879584803
|
pytorch_model-00020-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30ab55830f524fa81df3bd46ccdade32283eaf36f51855b6e982146c7aacb339
|
3 |
+
size 8879584803
|
pytorch_model-00021-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6524c0b1114f2eeb1fc16bc13d38eafdd93b866967093c3c5a9929398fcb0c7
|
3 |
+
size 8879584803
|
pytorch_model-00022-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da666af65e105e3595b8ed65f9f11304137b37a8d97f8f300e763cec8cc128da
|
3 |
+
size 8879584803
|
pytorch_model-00023-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2506cdcd45c183cfe8c539aa29ec5c5fb5b58dbb741675b8cfc6acbe830e2df3
|
3 |
+
size 8879584803
|
pytorch_model-00024-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f168c6bc1a2fa6154ae8065962e7c8d13d512b6160f329761ea056a53cbd9c4
|
3 |
+
size 8879584803
|
pytorch_model-00025-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44475f754ced99f18182a6db633ed302a0cc485728d0e180d3dcf5885ef75175
|
3 |
+
size 8879584803
|
pytorch_model-00026-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fa2b08b845f5a12c5ca65c1a5ed7b3dec70e30a2bc435f2a79db10ebf00c300
|
3 |
+
size 8879584803
|
pytorch_model-00027-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1976b339136b311791106fa594d7ed1171754b33f6c25af4196da155974785ba
|
3 |
+
size 8879584803
|
pytorch_model-00028-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32ffe5a51e1d311c1b22ba7c52a502e3fab9cd38bd2238b7634626e0c1a9cc3f
|
3 |
+
size 8879584803
|
pytorch_model-00029-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9299e258ed9d69c345b9af3a4bfc77c3324c445b0772a2dc5d178497f2f30f8
|
3 |
+
size 8879584803
|
pytorch_model-00030-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9c81d84b3df975fb22f85c708a38f9f1b1e92ed7fe5491ebcad93b9af565ae0
|
3 |
+
size 8879584803
|
pytorch_model-00031-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5357fbd859b884bc611375093cb1cc9ea8d73c62d79334b654a2c339840a291e
|
3 |
+
size 8879584803
|
pytorch_model-00032-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90b97afef6a502cfa02be2664e0d8fd99d73e116963535edf4e542debf35597c
|
3 |
+
size 8879584803
|
pytorch_model-00033-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55fba07682639b078bdd89c9bb5bea7d2f8dbe561a96e18bf638c31d640ce5f5
|
3 |
+
size 8879584803
|
pytorch_model-00034-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38b06d651dd276c0e83a1789f5b10edec6a75952a8bd37bb1efd977a769f17f2
|
3 |
+
size 8879584803
|
pytorch_model-00035-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f912140e778e50de4743e0ac0ede11d5df36a48f498d15d1eaf9dfa886ccff9
|
3 |
+
size 8879584803
|
pytorch_model-00036-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f458ff0754e2db42059685efcf075c512bcc5730dbe3262885458ca47df870b7
|
3 |
+
size 8879584803
|
pytorch_model-00037-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ea1a48f035a29840e9522ae64014f50b3f6381233efd7bf1d6130c771f3020c
|
3 |
+
size 8879584803
|
pytorch_model-00038-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5304c5ccbaf945bc9ee2857ef4e69de06eb5740206df18d11d5a771da4e5aa4
|
3 |
+
size 8879584803
|
pytorch_model-00039-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59167e9a986099acd02d5c709e8a9faae5d1c18cc2e9a407178d5ef05552661d
|
3 |
+
size 8879584803
|
pytorch_model-00040-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca80a744593763d3f1cc86d7a400ba1395b61b1be46ba207246af5f63aea8e20
|
3 |
+
size 8879584803
|
pytorch_model-00041-of-00041.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a28398491ebcace3f9a204c3678deee7ab916f5bfed7a28c5c033590bef1eb26
|
3 |
+
size 1763885712
|
pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,651 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 357281425408
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "pytorch_model-00001-of-00041.bin",
|
7 |
+
"transformer.h.0.ln_attn.bias": "pytorch_model-00001-of-00041.bin",
|
8 |
+
"transformer.h.0.ln_attn.weight": "pytorch_model-00001-of-00041.bin",
|
9 |
+
"transformer.h.0.ln_mlp.bias": "pytorch_model-00001-of-00041.bin",
|
10 |
+
"transformer.h.0.ln_mlp.weight": "pytorch_model-00001-of-00041.bin",
|
11 |
+
"transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00041.bin",
|
12 |
+
"transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00041.bin",
|
13 |
+
"transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00041.bin",
|
14 |
+
"transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00041.bin",
|
15 |
+
"transformer.h.1.ln_attn.bias": "pytorch_model-00002-of-00041.bin",
|
16 |
+
"transformer.h.1.ln_attn.weight": "pytorch_model-00002-of-00041.bin",
|
17 |
+
"transformer.h.1.ln_mlp.bias": "pytorch_model-00002-of-00041.bin",
|
18 |
+
"transformer.h.1.ln_mlp.weight": "pytorch_model-00002-of-00041.bin",
|
19 |
+
"transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00041.bin",
|
20 |
+
"transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00041.bin",
|
21 |
+
"transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00041.bin",
|
22 |
+
"transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00041.bin",
|
23 |
+
"transformer.h.10.ln_attn.bias": "pytorch_model-00006-of-00041.bin",
|
24 |
+
"transformer.h.10.ln_attn.weight": "pytorch_model-00006-of-00041.bin",
|
25 |
+
"transformer.h.10.ln_mlp.bias": "pytorch_model-00006-of-00041.bin",
|
26 |
+
"transformer.h.10.ln_mlp.weight": "pytorch_model-00006-of-00041.bin",
|
27 |
+
"transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00041.bin",
|
28 |
+
"transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00041.bin",
|
29 |
+
"transformer.h.10.self_attention.dense.weight": "pytorch_model-00006-of-00041.bin",
|
30 |
+
"transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00006-of-00041.bin",
|
31 |
+
"transformer.h.11.ln_attn.bias": "pytorch_model-00007-of-00041.bin",
|
32 |
+
"transformer.h.11.ln_attn.weight": "pytorch_model-00007-of-00041.bin",
|
33 |
+
"transformer.h.11.ln_mlp.bias": "pytorch_model-00007-of-00041.bin",
|
34 |
+
"transformer.h.11.ln_mlp.weight": "pytorch_model-00007-of-00041.bin",
|
35 |
+
"transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00041.bin",
|
36 |
+
"transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00041.bin",
|
37 |
+
"transformer.h.11.self_attention.dense.weight": "pytorch_model-00006-of-00041.bin",
|
38 |
+
"transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00006-of-00041.bin",
|
39 |
+
"transformer.h.12.ln_attn.bias": "pytorch_model-00007-of-00041.bin",
|
40 |
+
"transformer.h.12.ln_attn.weight": "pytorch_model-00007-of-00041.bin",
|
41 |
+
"transformer.h.12.ln_mlp.bias": "pytorch_model-00007-of-00041.bin",
|
42 |
+
"transformer.h.12.ln_mlp.weight": "pytorch_model-00007-of-00041.bin",
|
43 |
+
"transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00041.bin",
|
44 |
+
"transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00041.bin",
|
45 |
+
"transformer.h.12.self_attention.dense.weight": "pytorch_model-00007-of-00041.bin",
|
46 |
+
"transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00007-of-00041.bin",
|
47 |
+
"transformer.h.13.ln_attn.bias": "pytorch_model-00008-of-00041.bin",
|
48 |
+
"transformer.h.13.ln_attn.weight": "pytorch_model-00008-of-00041.bin",
|
49 |
+
"transformer.h.13.ln_mlp.bias": "pytorch_model-00008-of-00041.bin",
|
50 |
+
"transformer.h.13.ln_mlp.weight": "pytorch_model-00008-of-00041.bin",
|
51 |
+
"transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00041.bin",
|
52 |
+
"transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00041.bin",
|
53 |
+
"transformer.h.13.self_attention.dense.weight": "pytorch_model-00007-of-00041.bin",
|
54 |
+
"transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00007-of-00041.bin",
|
55 |
+
"transformer.h.14.ln_attn.bias": "pytorch_model-00008-of-00041.bin",
|
56 |
+
"transformer.h.14.ln_attn.weight": "pytorch_model-00008-of-00041.bin",
|
57 |
+
"transformer.h.14.ln_mlp.bias": "pytorch_model-00008-of-00041.bin",
|
58 |
+
"transformer.h.14.ln_mlp.weight": "pytorch_model-00008-of-00041.bin",
|
59 |
+
"transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00041.bin",
|
60 |
+
"transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00041.bin",
|
61 |
+
"transformer.h.14.self_attention.dense.weight": "pytorch_model-00008-of-00041.bin",
|
62 |
+
"transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00008-of-00041.bin",
|
63 |
+
"transformer.h.15.ln_attn.bias": "pytorch_model-00009-of-00041.bin",
|
64 |
+
"transformer.h.15.ln_attn.weight": "pytorch_model-00009-of-00041.bin",
|
65 |
+
"transformer.h.15.ln_mlp.bias": "pytorch_model-00009-of-00041.bin",
|
66 |
+
"transformer.h.15.ln_mlp.weight": "pytorch_model-00009-of-00041.bin",
|
67 |
+
"transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00041.bin",
|
68 |
+
"transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00041.bin",
|
69 |
+
"transformer.h.15.self_attention.dense.weight": "pytorch_model-00008-of-00041.bin",
|
70 |
+
"transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00008-of-00041.bin",
|
71 |
+
"transformer.h.16.ln_attn.bias": "pytorch_model-00009-of-00041.bin",
|
72 |
+
"transformer.h.16.ln_attn.weight": "pytorch_model-00009-of-00041.bin",
|
73 |
+
"transformer.h.16.ln_mlp.bias": "pytorch_model-00009-of-00041.bin",
|
74 |
+
"transformer.h.16.ln_mlp.weight": "pytorch_model-00009-of-00041.bin",
|
75 |
+
"transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00041.bin",
|
76 |
+
"transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00041.bin",
|
77 |
+
"transformer.h.16.self_attention.dense.weight": "pytorch_model-00009-of-00041.bin",
|
78 |
+
"transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00009-of-00041.bin",
|
79 |
+
"transformer.h.17.ln_attn.bias": "pytorch_model-00010-of-00041.bin",
|
80 |
+
"transformer.h.17.ln_attn.weight": "pytorch_model-00010-of-00041.bin",
|
81 |
+
"transformer.h.17.ln_mlp.bias": "pytorch_model-00010-of-00041.bin",
|
82 |
+
"transformer.h.17.ln_mlp.weight": "pytorch_model-00010-of-00041.bin",
|
83 |
+
"transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00041.bin",
|
84 |
+
"transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00041.bin",
|
85 |
+
"transformer.h.17.self_attention.dense.weight": "pytorch_model-00009-of-00041.bin",
|
86 |
+
"transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00009-of-00041.bin",
|
87 |
+
"transformer.h.18.ln_attn.bias": "pytorch_model-00010-of-00041.bin",
|
88 |
+
"transformer.h.18.ln_attn.weight": "pytorch_model-00010-of-00041.bin",
|
89 |
+
"transformer.h.18.ln_mlp.bias": "pytorch_model-00010-of-00041.bin",
|
90 |
+
"transformer.h.18.ln_mlp.weight": "pytorch_model-00010-of-00041.bin",
|
91 |
+
"transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00041.bin",
|
92 |
+
"transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00041.bin",
|
93 |
+
"transformer.h.18.self_attention.dense.weight": "pytorch_model-00010-of-00041.bin",
|
94 |
+
"transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00010-of-00041.bin",
|
95 |
+
"transformer.h.19.ln_attn.bias": "pytorch_model-00011-of-00041.bin",
|
96 |
+
"transformer.h.19.ln_attn.weight": "pytorch_model-00011-of-00041.bin",
|
97 |
+
"transformer.h.19.ln_mlp.bias": "pytorch_model-00011-of-00041.bin",
|
98 |
+
"transformer.h.19.ln_mlp.weight": "pytorch_model-00011-of-00041.bin",
|
99 |
+
"transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00041.bin",
|
100 |
+
"transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00041.bin",
|
101 |
+
"transformer.h.19.self_attention.dense.weight": "pytorch_model-00010-of-00041.bin",
|
102 |
+
"transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00010-of-00041.bin",
|
103 |
+
"transformer.h.2.ln_attn.bias": "pytorch_model-00002-of-00041.bin",
|
104 |
+
"transformer.h.2.ln_attn.weight": "pytorch_model-00002-of-00041.bin",
|
105 |
+
"transformer.h.2.ln_mlp.bias": "pytorch_model-00002-of-00041.bin",
|
106 |
+
"transformer.h.2.ln_mlp.weight": "pytorch_model-00002-of-00041.bin",
|
107 |
+
"transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00041.bin",
|
108 |
+
"transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00041.bin",
|
109 |
+
"transformer.h.2.self_attention.dense.weight": "pytorch_model-00002-of-00041.bin",
|
110 |
+
"transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00002-of-00041.bin",
|
111 |
+
"transformer.h.20.ln_attn.bias": "pytorch_model-00011-of-00041.bin",
|
112 |
+
"transformer.h.20.ln_attn.weight": "pytorch_model-00011-of-00041.bin",
|
113 |
+
"transformer.h.20.ln_mlp.bias": "pytorch_model-00011-of-00041.bin",
|
114 |
+
"transformer.h.20.ln_mlp.weight": "pytorch_model-00011-of-00041.bin",
|
115 |
+
"transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00041.bin",
|
116 |
+
"transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00041.bin",
|
117 |
+
"transformer.h.20.self_attention.dense.weight": "pytorch_model-00011-of-00041.bin",
|
118 |
+
"transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00011-of-00041.bin",
|
119 |
+
"transformer.h.21.ln_attn.bias": "pytorch_model-00012-of-00041.bin",
|
120 |
+
"transformer.h.21.ln_attn.weight": "pytorch_model-00012-of-00041.bin",
|
121 |
+
"transformer.h.21.ln_mlp.bias": "pytorch_model-00012-of-00041.bin",
|
122 |
+
"transformer.h.21.ln_mlp.weight": "pytorch_model-00012-of-00041.bin",
|
123 |
+
"transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00041.bin",
|
124 |
+
"transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00041.bin",
|
125 |
+
"transformer.h.21.self_attention.dense.weight": "pytorch_model-00011-of-00041.bin",
|
126 |
+
"transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00011-of-00041.bin",
|
127 |
+
"transformer.h.22.ln_attn.bias": "pytorch_model-00012-of-00041.bin",
|
128 |
+
"transformer.h.22.ln_attn.weight": "pytorch_model-00012-of-00041.bin",
|
129 |
+
"transformer.h.22.ln_mlp.bias": "pytorch_model-00012-of-00041.bin",
|
130 |
+
"transformer.h.22.ln_mlp.weight": "pytorch_model-00012-of-00041.bin",
|
131 |
+
"transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00041.bin",
|
132 |
+
"transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00041.bin",
|
133 |
+
"transformer.h.22.self_attention.dense.weight": "pytorch_model-00012-of-00041.bin",
|
134 |
+
"transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00012-of-00041.bin",
|
135 |
+
"transformer.h.23.ln_attn.bias": "pytorch_model-00013-of-00041.bin",
|
136 |
+
"transformer.h.23.ln_attn.weight": "pytorch_model-00013-of-00041.bin",
|
137 |
+
"transformer.h.23.ln_mlp.bias": "pytorch_model-00013-of-00041.bin",
|
138 |
+
"transformer.h.23.ln_mlp.weight": "pytorch_model-00013-of-00041.bin",
|
139 |
+
"transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00041.bin",
|
140 |
+
"transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00041.bin",
|
141 |
+
"transformer.h.23.self_attention.dense.weight": "pytorch_model-00012-of-00041.bin",
|
142 |
+
"transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00012-of-00041.bin",
|
143 |
+
"transformer.h.24.ln_attn.bias": "pytorch_model-00013-of-00041.bin",
|
144 |
+
"transformer.h.24.ln_attn.weight": "pytorch_model-00013-of-00041.bin",
|
145 |
+
"transformer.h.24.ln_mlp.bias": "pytorch_model-00013-of-00041.bin",
|
146 |
+
"transformer.h.24.ln_mlp.weight": "pytorch_model-00013-of-00041.bin",
|
147 |
+
"transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00041.bin",
|
148 |
+
"transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00041.bin",
|
149 |
+
"transformer.h.24.self_attention.dense.weight": "pytorch_model-00013-of-00041.bin",
|
150 |
+
"transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00013-of-00041.bin",
|
151 |
+
"transformer.h.25.ln_attn.bias": "pytorch_model-00014-of-00041.bin",
|
152 |
+
"transformer.h.25.ln_attn.weight": "pytorch_model-00014-of-00041.bin",
|
153 |
+
"transformer.h.25.ln_mlp.bias": "pytorch_model-00014-of-00041.bin",
|
154 |
+
"transformer.h.25.ln_mlp.weight": "pytorch_model-00014-of-00041.bin",
|
155 |
+
"transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00041.bin",
|
156 |
+
"transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00041.bin",
|
157 |
+
"transformer.h.25.self_attention.dense.weight": "pytorch_model-00013-of-00041.bin",
|
158 |
+
"transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00013-of-00041.bin",
|
159 |
+
"transformer.h.26.ln_attn.bias": "pytorch_model-00014-of-00041.bin",
|
160 |
+
"transformer.h.26.ln_attn.weight": "pytorch_model-00014-of-00041.bin",
|
161 |
+
"transformer.h.26.ln_mlp.bias": "pytorch_model-00014-of-00041.bin",
|
162 |
+
"transformer.h.26.ln_mlp.weight": "pytorch_model-00014-of-00041.bin",
|
163 |
+
"transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00041.bin",
|
164 |
+
"transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00041.bin",
|
165 |
+
"transformer.h.26.self_attention.dense.weight": "pytorch_model-00014-of-00041.bin",
|
166 |
+
"transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00014-of-00041.bin",
|
167 |
+
"transformer.h.27.ln_attn.bias": "pytorch_model-00015-of-00041.bin",
|
168 |
+
"transformer.h.27.ln_attn.weight": "pytorch_model-00015-of-00041.bin",
|
169 |
+
"transformer.h.27.ln_mlp.bias": "pytorch_model-00015-of-00041.bin",
|
170 |
+
"transformer.h.27.ln_mlp.weight": "pytorch_model-00015-of-00041.bin",
|
171 |
+
"transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00015-of-00041.bin",
|
172 |
+
"transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00041.bin",
|
173 |
+
"transformer.h.27.self_attention.dense.weight": "pytorch_model-00014-of-00041.bin",
|
174 |
+
"transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00014-of-00041.bin",
|
175 |
+
"transformer.h.28.ln_attn.bias": "pytorch_model-00015-of-00041.bin",
|
176 |
+
"transformer.h.28.ln_attn.weight": "pytorch_model-00015-of-00041.bin",
|
177 |
+
"transformer.h.28.ln_mlp.bias": "pytorch_model-00015-of-00041.bin",
|
178 |
+
"transformer.h.28.ln_mlp.weight": "pytorch_model-00015-of-00041.bin",
|
179 |
+
"transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00015-of-00041.bin",
|
180 |
+
"transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00015-of-00041.bin",
|
181 |
+
"transformer.h.28.self_attention.dense.weight": "pytorch_model-00015-of-00041.bin",
|
182 |
+
"transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00015-of-00041.bin",
|
183 |
+
"transformer.h.29.ln_attn.bias": "pytorch_model-00016-of-00041.bin",
|
184 |
+
"transformer.h.29.ln_attn.weight": "pytorch_model-00016-of-00041.bin",
|
185 |
+
"transformer.h.29.ln_mlp.bias": "pytorch_model-00016-of-00041.bin",
|
186 |
+
"transformer.h.29.ln_mlp.weight": "pytorch_model-00016-of-00041.bin",
|
187 |
+
"transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00016-of-00041.bin",
|
188 |
+
"transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00015-of-00041.bin",
|
189 |
+
"transformer.h.29.self_attention.dense.weight": "pytorch_model-00015-of-00041.bin",
|
190 |
+
"transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00015-of-00041.bin",
|
191 |
+
"transformer.h.3.ln_attn.bias": "pytorch_model-00003-of-00041.bin",
|
192 |
+
"transformer.h.3.ln_attn.weight": "pytorch_model-00003-of-00041.bin",
|
193 |
+
"transformer.h.3.ln_mlp.bias": "pytorch_model-00003-of-00041.bin",
|
194 |
+
"transformer.h.3.ln_mlp.weight": "pytorch_model-00003-of-00041.bin",
|
195 |
+
"transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00041.bin",
|
196 |
+
"transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00041.bin",
|
197 |
+
"transformer.h.3.self_attention.dense.weight": "pytorch_model-00002-of-00041.bin",
|
198 |
+
"transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00002-of-00041.bin",
|
199 |
+
"transformer.h.30.ln_attn.bias": "pytorch_model-00016-of-00041.bin",
|
200 |
+
"transformer.h.30.ln_attn.weight": "pytorch_model-00016-of-00041.bin",
|
201 |
+
"transformer.h.30.ln_mlp.bias": "pytorch_model-00016-of-00041.bin",
|
202 |
+
"transformer.h.30.ln_mlp.weight": "pytorch_model-00016-of-00041.bin",
|
203 |
+
"transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00016-of-00041.bin",
|
204 |
+
"transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00016-of-00041.bin",
|
205 |
+
"transformer.h.30.self_attention.dense.weight": "pytorch_model-00016-of-00041.bin",
|
206 |
+
"transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00016-of-00041.bin",
|
207 |
+
"transformer.h.31.ln_attn.bias": "pytorch_model-00017-of-00041.bin",
|
208 |
+
"transformer.h.31.ln_attn.weight": "pytorch_model-00017-of-00041.bin",
|
209 |
+
"transformer.h.31.ln_mlp.bias": "pytorch_model-00017-of-00041.bin",
|
210 |
+
"transformer.h.31.ln_mlp.weight": "pytorch_model-00017-of-00041.bin",
|
211 |
+
"transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00017-of-00041.bin",
|
212 |
+
"transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00016-of-00041.bin",
|
213 |
+
"transformer.h.31.self_attention.dense.weight": "pytorch_model-00016-of-00041.bin",
|
214 |
+
"transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00016-of-00041.bin",
|
215 |
+
"transformer.h.32.ln_attn.bias": "pytorch_model-00017-of-00041.bin",
|
216 |
+
"transformer.h.32.ln_attn.weight": "pytorch_model-00017-of-00041.bin",
|
217 |
+
"transformer.h.32.ln_mlp.bias": "pytorch_model-00017-of-00041.bin",
|
218 |
+
"transformer.h.32.ln_mlp.weight": "pytorch_model-00017-of-00041.bin",
|
219 |
+
"transformer.h.32.mlp.dense_4h_to_h.weight": "pytorch_model-00017-of-00041.bin",
|
220 |
+
"transformer.h.32.mlp.dense_h_to_4h.weight": "pytorch_model-00017-of-00041.bin",
|
221 |
+
"transformer.h.32.self_attention.dense.weight": "pytorch_model-00017-of-00041.bin",
|
222 |
+
"transformer.h.32.self_attention.query_key_value.weight": "pytorch_model-00017-of-00041.bin",
|
223 |
+
"transformer.h.33.ln_attn.bias": "pytorch_model-00018-of-00041.bin",
|
224 |
+
"transformer.h.33.ln_attn.weight": "pytorch_model-00018-of-00041.bin",
|
225 |
+
"transformer.h.33.ln_mlp.bias": "pytorch_model-00018-of-00041.bin",
|
226 |
+
"transformer.h.33.ln_mlp.weight": "pytorch_model-00018-of-00041.bin",
|
227 |
+
"transformer.h.33.mlp.dense_4h_to_h.weight": "pytorch_model-00018-of-00041.bin",
|
228 |
+
"transformer.h.33.mlp.dense_h_to_4h.weight": "pytorch_model-00017-of-00041.bin",
|
229 |
+
"transformer.h.33.self_attention.dense.weight": "pytorch_model-00017-of-00041.bin",
|
230 |
+
"transformer.h.33.self_attention.query_key_value.weight": "pytorch_model-00017-of-00041.bin",
|
231 |
+
"transformer.h.34.ln_attn.bias": "pytorch_model-00018-of-00041.bin",
|
232 |
+
"transformer.h.34.ln_attn.weight": "pytorch_model-00018-of-00041.bin",
|
233 |
+
"transformer.h.34.ln_mlp.bias": "pytorch_model-00018-of-00041.bin",
|
234 |
+
"transformer.h.34.ln_mlp.weight": "pytorch_model-00018-of-00041.bin",
|
235 |
+
"transformer.h.34.mlp.dense_4h_to_h.weight": "pytorch_model-00018-of-00041.bin",
|
236 |
+
"transformer.h.34.mlp.dense_h_to_4h.weight": "pytorch_model-00018-of-00041.bin",
|
237 |
+
"transformer.h.34.self_attention.dense.weight": "pytorch_model-00018-of-00041.bin",
|
238 |
+
"transformer.h.34.self_attention.query_key_value.weight": "pytorch_model-00018-of-00041.bin",
|
239 |
+
"transformer.h.35.ln_attn.bias": "pytorch_model-00019-of-00041.bin",
|
240 |
+
"transformer.h.35.ln_attn.weight": "pytorch_model-00019-of-00041.bin",
|
241 |
+
"transformer.h.35.ln_mlp.bias": "pytorch_model-00019-of-00041.bin",
|
242 |
+
"transformer.h.35.ln_mlp.weight": "pytorch_model-00019-of-00041.bin",
|
243 |
+
"transformer.h.35.mlp.dense_4h_to_h.weight": "pytorch_model-00019-of-00041.bin",
|
244 |
+
"transformer.h.35.mlp.dense_h_to_4h.weight": "pytorch_model-00018-of-00041.bin",
|
245 |
+
"transformer.h.35.self_attention.dense.weight": "pytorch_model-00018-of-00041.bin",
|
246 |
+
"transformer.h.35.self_attention.query_key_value.weight": "pytorch_model-00018-of-00041.bin",
|
247 |
+
"transformer.h.36.ln_attn.bias": "pytorch_model-00019-of-00041.bin",
|
248 |
+
"transformer.h.36.ln_attn.weight": "pytorch_model-00019-of-00041.bin",
|
249 |
+
"transformer.h.36.ln_mlp.bias": "pytorch_model-00019-of-00041.bin",
|
250 |
+
"transformer.h.36.ln_mlp.weight": "pytorch_model-00019-of-00041.bin",
|
251 |
+
"transformer.h.36.mlp.dense_4h_to_h.weight": "pytorch_model-00019-of-00041.bin",
|
252 |
+
"transformer.h.36.mlp.dense_h_to_4h.weight": "pytorch_model-00019-of-00041.bin",
|
253 |
+
"transformer.h.36.self_attention.dense.weight": "pytorch_model-00019-of-00041.bin",
|
254 |
+
"transformer.h.36.self_attention.query_key_value.weight": "pytorch_model-00019-of-00041.bin",
|
255 |
+
"transformer.h.37.ln_attn.bias": "pytorch_model-00020-of-00041.bin",
|
256 |
+
"transformer.h.37.ln_attn.weight": "pytorch_model-00020-of-00041.bin",
|
257 |
+
"transformer.h.37.ln_mlp.bias": "pytorch_model-00020-of-00041.bin",
|
258 |
+
"transformer.h.37.ln_mlp.weight": "pytorch_model-00020-of-00041.bin",
|
259 |
+
"transformer.h.37.mlp.dense_4h_to_h.weight": "pytorch_model-00020-of-00041.bin",
|
260 |
+
"transformer.h.37.mlp.dense_h_to_4h.weight": "pytorch_model-00019-of-00041.bin",
|
261 |
+
"transformer.h.37.self_attention.dense.weight": "pytorch_model-00019-of-00041.bin",
|
262 |
+
"transformer.h.37.self_attention.query_key_value.weight": "pytorch_model-00019-of-00041.bin",
|
263 |
+
"transformer.h.38.ln_attn.bias": "pytorch_model-00020-of-00041.bin",
|
264 |
+
"transformer.h.38.ln_attn.weight": "pytorch_model-00020-of-00041.bin",
|
265 |
+
"transformer.h.38.ln_mlp.bias": "pytorch_model-00020-of-00041.bin",
|
266 |
+
"transformer.h.38.ln_mlp.weight": "pytorch_model-00020-of-00041.bin",
|
267 |
+
"transformer.h.38.mlp.dense_4h_to_h.weight": "pytorch_model-00020-of-00041.bin",
|
268 |
+
"transformer.h.38.mlp.dense_h_to_4h.weight": "pytorch_model-00020-of-00041.bin",
|
269 |
+
"transformer.h.38.self_attention.dense.weight": "pytorch_model-00020-of-00041.bin",
|
270 |
+
"transformer.h.38.self_attention.query_key_value.weight": "pytorch_model-00020-of-00041.bin",
|
271 |
+
"transformer.h.39.ln_attn.bias": "pytorch_model-00021-of-00041.bin",
|
272 |
+
"transformer.h.39.ln_attn.weight": "pytorch_model-00021-of-00041.bin",
|
273 |
+
"transformer.h.39.ln_mlp.bias": "pytorch_model-00021-of-00041.bin",
|
274 |
+
"transformer.h.39.ln_mlp.weight": "pytorch_model-00021-of-00041.bin",
|
275 |
+
"transformer.h.39.mlp.dense_4h_to_h.weight": "pytorch_model-00021-of-00041.bin",
|
276 |
+
"transformer.h.39.mlp.dense_h_to_4h.weight": "pytorch_model-00020-of-00041.bin",
|
277 |
+
"transformer.h.39.self_attention.dense.weight": "pytorch_model-00020-of-00041.bin",
|
278 |
+
"transformer.h.39.self_attention.query_key_value.weight": "pytorch_model-00020-of-00041.bin",
|
279 |
+
"transformer.h.4.ln_attn.bias": "pytorch_model-00003-of-00041.bin",
|
280 |
+
"transformer.h.4.ln_attn.weight": "pytorch_model-00003-of-00041.bin",
|
281 |
+
"transformer.h.4.ln_mlp.bias": "pytorch_model-00003-of-00041.bin",
|
282 |
+
"transformer.h.4.ln_mlp.weight": "pytorch_model-00003-of-00041.bin",
|
283 |
+
"transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00041.bin",
|
284 |
+
"transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00041.bin",
|
285 |
+
"transformer.h.4.self_attention.dense.weight": "pytorch_model-00003-of-00041.bin",
|
286 |
+
"transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00003-of-00041.bin",
|
287 |
+
"transformer.h.40.ln_attn.bias": "pytorch_model-00021-of-00041.bin",
|
288 |
+
"transformer.h.40.ln_attn.weight": "pytorch_model-00021-of-00041.bin",
|
289 |
+
"transformer.h.40.ln_mlp.bias": "pytorch_model-00021-of-00041.bin",
|
290 |
+
"transformer.h.40.ln_mlp.weight": "pytorch_model-00021-of-00041.bin",
|
291 |
+
"transformer.h.40.mlp.dense_4h_to_h.weight": "pytorch_model-00021-of-00041.bin",
|
292 |
+
"transformer.h.40.mlp.dense_h_to_4h.weight": "pytorch_model-00021-of-00041.bin",
|
293 |
+
"transformer.h.40.self_attention.dense.weight": "pytorch_model-00021-of-00041.bin",
|
294 |
+
"transformer.h.40.self_attention.query_key_value.weight": "pytorch_model-00021-of-00041.bin",
|
295 |
+
"transformer.h.41.ln_attn.bias": "pytorch_model-00022-of-00041.bin",
|
296 |
+
"transformer.h.41.ln_attn.weight": "pytorch_model-00022-of-00041.bin",
|
297 |
+
"transformer.h.41.ln_mlp.bias": "pytorch_model-00022-of-00041.bin",
|
298 |
+
"transformer.h.41.ln_mlp.weight": "pytorch_model-00022-of-00041.bin",
|
299 |
+
"transformer.h.41.mlp.dense_4h_to_h.weight": "pytorch_model-00022-of-00041.bin",
|
300 |
+
"transformer.h.41.mlp.dense_h_to_4h.weight": "pytorch_model-00021-of-00041.bin",
|
301 |
+
"transformer.h.41.self_attention.dense.weight": "pytorch_model-00021-of-00041.bin",
|
302 |
+
"transformer.h.41.self_attention.query_key_value.weight": "pytorch_model-00021-of-00041.bin",
|
303 |
+
"transformer.h.42.ln_attn.bias": "pytorch_model-00022-of-00041.bin",
|
304 |
+
"transformer.h.42.ln_attn.weight": "pytorch_model-00022-of-00041.bin",
|
305 |
+
"transformer.h.42.ln_mlp.bias": "pytorch_model-00022-of-00041.bin",
|
306 |
+
"transformer.h.42.ln_mlp.weight": "pytorch_model-00022-of-00041.bin",
|
307 |
+
"transformer.h.42.mlp.dense_4h_to_h.weight": "pytorch_model-00022-of-00041.bin",
|
308 |
+
"transformer.h.42.mlp.dense_h_to_4h.weight": "pytorch_model-00022-of-00041.bin",
|
309 |
+
"transformer.h.42.self_attention.dense.weight": "pytorch_model-00022-of-00041.bin",
|
310 |
+
"transformer.h.42.self_attention.query_key_value.weight": "pytorch_model-00022-of-00041.bin",
|
311 |
+
"transformer.h.43.ln_attn.bias": "pytorch_model-00023-of-00041.bin",
|
312 |
+
"transformer.h.43.ln_attn.weight": "pytorch_model-00023-of-00041.bin",
|
313 |
+
"transformer.h.43.ln_mlp.bias": "pytorch_model-00023-of-00041.bin",
|
314 |
+
"transformer.h.43.ln_mlp.weight": "pytorch_model-00023-of-00041.bin",
|
315 |
+
"transformer.h.43.mlp.dense_4h_to_h.weight": "pytorch_model-00023-of-00041.bin",
|
316 |
+
"transformer.h.43.mlp.dense_h_to_4h.weight": "pytorch_model-00022-of-00041.bin",
|
317 |
+
"transformer.h.43.self_attention.dense.weight": "pytorch_model-00022-of-00041.bin",
|
318 |
+
"transformer.h.43.self_attention.query_key_value.weight": "pytorch_model-00022-of-00041.bin",
|
319 |
+
"transformer.h.44.ln_attn.bias": "pytorch_model-00023-of-00041.bin",
|
320 |
+
"transformer.h.44.ln_attn.weight": "pytorch_model-00023-of-00041.bin",
|
321 |
+
"transformer.h.44.ln_mlp.bias": "pytorch_model-00023-of-00041.bin",
|
322 |
+
"transformer.h.44.ln_mlp.weight": "pytorch_model-00023-of-00041.bin",
|
323 |
+
"transformer.h.44.mlp.dense_4h_to_h.weight": "pytorch_model-00023-of-00041.bin",
|
324 |
+
"transformer.h.44.mlp.dense_h_to_4h.weight": "pytorch_model-00023-of-00041.bin",
|
325 |
+
"transformer.h.44.self_attention.dense.weight": "pytorch_model-00023-of-00041.bin",
|
326 |
+
"transformer.h.44.self_attention.query_key_value.weight": "pytorch_model-00023-of-00041.bin",
|
327 |
+
"transformer.h.45.ln_attn.bias": "pytorch_model-00024-of-00041.bin",
|
328 |
+
"transformer.h.45.ln_attn.weight": "pytorch_model-00024-of-00041.bin",
|
329 |
+
"transformer.h.45.ln_mlp.bias": "pytorch_model-00024-of-00041.bin",
|
330 |
+
"transformer.h.45.ln_mlp.weight": "pytorch_model-00024-of-00041.bin",
|
331 |
+
"transformer.h.45.mlp.dense_4h_to_h.weight": "pytorch_model-00024-of-00041.bin",
|
332 |
+
"transformer.h.45.mlp.dense_h_to_4h.weight": "pytorch_model-00023-of-00041.bin",
|
333 |
+
"transformer.h.45.self_attention.dense.weight": "pytorch_model-00023-of-00041.bin",
|
334 |
+
"transformer.h.45.self_attention.query_key_value.weight": "pytorch_model-00023-of-00041.bin",
|
335 |
+
"transformer.h.46.ln_attn.bias": "pytorch_model-00024-of-00041.bin",
|
336 |
+
"transformer.h.46.ln_attn.weight": "pytorch_model-00024-of-00041.bin",
|
337 |
+
"transformer.h.46.ln_mlp.bias": "pytorch_model-00024-of-00041.bin",
|
338 |
+
"transformer.h.46.ln_mlp.weight": "pytorch_model-00024-of-00041.bin",
|
339 |
+
"transformer.h.46.mlp.dense_4h_to_h.weight": "pytorch_model-00024-of-00041.bin",
|
340 |
+
"transformer.h.46.mlp.dense_h_to_4h.weight": "pytorch_model-00024-of-00041.bin",
|
341 |
+
"transformer.h.46.self_attention.dense.weight": "pytorch_model-00024-of-00041.bin",
|
342 |
+
"transformer.h.46.self_attention.query_key_value.weight": "pytorch_model-00024-of-00041.bin",
|
343 |
+
"transformer.h.47.ln_attn.bias": "pytorch_model-00025-of-00041.bin",
|
344 |
+
"transformer.h.47.ln_attn.weight": "pytorch_model-00025-of-00041.bin",
|
345 |
+
"transformer.h.47.ln_mlp.bias": "pytorch_model-00025-of-00041.bin",
|
346 |
+
"transformer.h.47.ln_mlp.weight": "pytorch_model-00025-of-00041.bin",
|
347 |
+
"transformer.h.47.mlp.dense_4h_to_h.weight": "pytorch_model-00025-of-00041.bin",
|
348 |
+
"transformer.h.47.mlp.dense_h_to_4h.weight": "pytorch_model-00024-of-00041.bin",
|
349 |
+
"transformer.h.47.self_attention.dense.weight": "pytorch_model-00024-of-00041.bin",
|
350 |
+
"transformer.h.47.self_attention.query_key_value.weight": "pytorch_model-00024-of-00041.bin",
|
351 |
+
"transformer.h.48.ln_attn.bias": "pytorch_model-00025-of-00041.bin",
|
352 |
+
"transformer.h.48.ln_attn.weight": "pytorch_model-00025-of-00041.bin",
|
353 |
+
"transformer.h.48.ln_mlp.bias": "pytorch_model-00025-of-00041.bin",
|
354 |
+
"transformer.h.48.ln_mlp.weight": "pytorch_model-00025-of-00041.bin",
|
355 |
+
"transformer.h.48.mlp.dense_4h_to_h.weight": "pytorch_model-00025-of-00041.bin",
|
356 |
+
"transformer.h.48.mlp.dense_h_to_4h.weight": "pytorch_model-00025-of-00041.bin",
|
357 |
+
"transformer.h.48.self_attention.dense.weight": "pytorch_model-00025-of-00041.bin",
|
358 |
+
"transformer.h.48.self_attention.query_key_value.weight": "pytorch_model-00025-of-00041.bin",
|
359 |
+
"transformer.h.49.ln_attn.bias": "pytorch_model-00026-of-00041.bin",
|
360 |
+
"transformer.h.49.ln_attn.weight": "pytorch_model-00026-of-00041.bin",
|
361 |
+
"transformer.h.49.ln_mlp.bias": "pytorch_model-00026-of-00041.bin",
|
362 |
+
"transformer.h.49.ln_mlp.weight": "pytorch_model-00026-of-00041.bin",
|
363 |
+
"transformer.h.49.mlp.dense_4h_to_h.weight": "pytorch_model-00026-of-00041.bin",
|
364 |
+
"transformer.h.49.mlp.dense_h_to_4h.weight": "pytorch_model-00025-of-00041.bin",
|
365 |
+
"transformer.h.49.self_attention.dense.weight": "pytorch_model-00025-of-00041.bin",
|
366 |
+
"transformer.h.49.self_attention.query_key_value.weight": "pytorch_model-00025-of-00041.bin",
|
367 |
+
"transformer.h.5.ln_attn.bias": "pytorch_model-00004-of-00041.bin",
|
368 |
+
"transformer.h.5.ln_attn.weight": "pytorch_model-00004-of-00041.bin",
|
369 |
+
"transformer.h.5.ln_mlp.bias": "pytorch_model-00004-of-00041.bin",
|
370 |
+
"transformer.h.5.ln_mlp.weight": "pytorch_model-00004-of-00041.bin",
|
371 |
+
"transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00041.bin",
|
372 |
+
"transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00041.bin",
|
373 |
+
"transformer.h.5.self_attention.dense.weight": "pytorch_model-00003-of-00041.bin",
|
374 |
+
"transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00003-of-00041.bin",
|
375 |
+
"transformer.h.50.ln_attn.bias": "pytorch_model-00026-of-00041.bin",
|
376 |
+
"transformer.h.50.ln_attn.weight": "pytorch_model-00026-of-00041.bin",
|
377 |
+
"transformer.h.50.ln_mlp.bias": "pytorch_model-00026-of-00041.bin",
|
378 |
+
"transformer.h.50.ln_mlp.weight": "pytorch_model-00026-of-00041.bin",
|
379 |
+
"transformer.h.50.mlp.dense_4h_to_h.weight": "pytorch_model-00026-of-00041.bin",
|
380 |
+
"transformer.h.50.mlp.dense_h_to_4h.weight": "pytorch_model-00026-of-00041.bin",
|
381 |
+
"transformer.h.50.self_attention.dense.weight": "pytorch_model-00026-of-00041.bin",
|
382 |
+
"transformer.h.50.self_attention.query_key_value.weight": "pytorch_model-00026-of-00041.bin",
|
383 |
+
"transformer.h.51.ln_attn.bias": "pytorch_model-00027-of-00041.bin",
|
384 |
+
"transformer.h.51.ln_attn.weight": "pytorch_model-00027-of-00041.bin",
|
385 |
+
"transformer.h.51.ln_mlp.bias": "pytorch_model-00027-of-00041.bin",
|
386 |
+
"transformer.h.51.ln_mlp.weight": "pytorch_model-00027-of-00041.bin",
|
387 |
+
"transformer.h.51.mlp.dense_4h_to_h.weight": "pytorch_model-00027-of-00041.bin",
|
388 |
+
"transformer.h.51.mlp.dense_h_to_4h.weight": "pytorch_model-00026-of-00041.bin",
|
389 |
+
"transformer.h.51.self_attention.dense.weight": "pytorch_model-00026-of-00041.bin",
|
390 |
+
"transformer.h.51.self_attention.query_key_value.weight": "pytorch_model-00026-of-00041.bin",
|
391 |
+
"transformer.h.52.ln_attn.bias": "pytorch_model-00027-of-00041.bin",
|
392 |
+
"transformer.h.52.ln_attn.weight": "pytorch_model-00027-of-00041.bin",
|
393 |
+
"transformer.h.52.ln_mlp.bias": "pytorch_model-00027-of-00041.bin",
|
394 |
+
"transformer.h.52.ln_mlp.weight": "pytorch_model-00027-of-00041.bin",
|
395 |
+
"transformer.h.52.mlp.dense_4h_to_h.weight": "pytorch_model-00027-of-00041.bin",
|
396 |
+
"transformer.h.52.mlp.dense_h_to_4h.weight": "pytorch_model-00027-of-00041.bin",
|
397 |
+
"transformer.h.52.self_attention.dense.weight": "pytorch_model-00027-of-00041.bin",
|
398 |
+
"transformer.h.52.self_attention.query_key_value.weight": "pytorch_model-00027-of-00041.bin",
|
399 |
+
"transformer.h.53.ln_attn.bias": "pytorch_model-00028-of-00041.bin",
|
400 |
+
"transformer.h.53.ln_attn.weight": "pytorch_model-00028-of-00041.bin",
|
401 |
+
"transformer.h.53.ln_mlp.bias": "pytorch_model-00028-of-00041.bin",
|
402 |
+
"transformer.h.53.ln_mlp.weight": "pytorch_model-00028-of-00041.bin",
|
403 |
+
"transformer.h.53.mlp.dense_4h_to_h.weight": "pytorch_model-00028-of-00041.bin",
|
404 |
+
"transformer.h.53.mlp.dense_h_to_4h.weight": "pytorch_model-00027-of-00041.bin",
|
405 |
+
"transformer.h.53.self_attention.dense.weight": "pytorch_model-00027-of-00041.bin",
|
406 |
+
"transformer.h.53.self_attention.query_key_value.weight": "pytorch_model-00027-of-00041.bin",
|
407 |
+
"transformer.h.54.ln_attn.bias": "pytorch_model-00028-of-00041.bin",
|
408 |
+
"transformer.h.54.ln_attn.weight": "pytorch_model-00028-of-00041.bin",
|
409 |
+
"transformer.h.54.ln_mlp.bias": "pytorch_model-00028-of-00041.bin",
|
410 |
+
"transformer.h.54.ln_mlp.weight": "pytorch_model-00028-of-00041.bin",
|
411 |
+
"transformer.h.54.mlp.dense_4h_to_h.weight": "pytorch_model-00028-of-00041.bin",
|
412 |
+
"transformer.h.54.mlp.dense_h_to_4h.weight": "pytorch_model-00028-of-00041.bin",
|
413 |
+
"transformer.h.54.self_attention.dense.weight": "pytorch_model-00028-of-00041.bin",
|
414 |
+
"transformer.h.54.self_attention.query_key_value.weight": "pytorch_model-00028-of-00041.bin",
|
415 |
+
"transformer.h.55.ln_attn.bias": "pytorch_model-00029-of-00041.bin",
|
416 |
+
"transformer.h.55.ln_attn.weight": "pytorch_model-00029-of-00041.bin",
|
417 |
+
"transformer.h.55.ln_mlp.bias": "pytorch_model-00029-of-00041.bin",
|
418 |
+
"transformer.h.55.ln_mlp.weight": "pytorch_model-00029-of-00041.bin",
|
419 |
+
"transformer.h.55.mlp.dense_4h_to_h.weight": "pytorch_model-00029-of-00041.bin",
|
420 |
+
"transformer.h.55.mlp.dense_h_to_4h.weight": "pytorch_model-00028-of-00041.bin",
|
421 |
+
"transformer.h.55.self_attention.dense.weight": "pytorch_model-00028-of-00041.bin",
|
422 |
+
"transformer.h.55.self_attention.query_key_value.weight": "pytorch_model-00028-of-00041.bin",
|
423 |
+
"transformer.h.56.ln_attn.bias": "pytorch_model-00029-of-00041.bin",
|
424 |
+
"transformer.h.56.ln_attn.weight": "pytorch_model-00029-of-00041.bin",
|
425 |
+
"transformer.h.56.ln_mlp.bias": "pytorch_model-00029-of-00041.bin",
|
426 |
+
"transformer.h.56.ln_mlp.weight": "pytorch_model-00029-of-00041.bin",
|
427 |
+
"transformer.h.56.mlp.dense_4h_to_h.weight": "pytorch_model-00029-of-00041.bin",
|
428 |
+
"transformer.h.56.mlp.dense_h_to_4h.weight": "pytorch_model-00029-of-00041.bin",
|
429 |
+
"transformer.h.56.self_attention.dense.weight": "pytorch_model-00029-of-00041.bin",
|
430 |
+
"transformer.h.56.self_attention.query_key_value.weight": "pytorch_model-00029-of-00041.bin",
|
431 |
+
"transformer.h.57.ln_attn.bias": "pytorch_model-00030-of-00041.bin",
|
432 |
+
"transformer.h.57.ln_attn.weight": "pytorch_model-00030-of-00041.bin",
|
433 |
+
"transformer.h.57.ln_mlp.bias": "pytorch_model-00030-of-00041.bin",
|
434 |
+
"transformer.h.57.ln_mlp.weight": "pytorch_model-00030-of-00041.bin",
|
435 |
+
"transformer.h.57.mlp.dense_4h_to_h.weight": "pytorch_model-00030-of-00041.bin",
|
436 |
+
"transformer.h.57.mlp.dense_h_to_4h.weight": "pytorch_model-00029-of-00041.bin",
|
437 |
+
"transformer.h.57.self_attention.dense.weight": "pytorch_model-00029-of-00041.bin",
|
438 |
+
"transformer.h.57.self_attention.query_key_value.weight": "pytorch_model-00029-of-00041.bin",
|
439 |
+
"transformer.h.58.ln_attn.bias": "pytorch_model-00030-of-00041.bin",
|
440 |
+
"transformer.h.58.ln_attn.weight": "pytorch_model-00030-of-00041.bin",
|
441 |
+
"transformer.h.58.ln_mlp.bias": "pytorch_model-00030-of-00041.bin",
|
442 |
+
"transformer.h.58.ln_mlp.weight": "pytorch_model-00030-of-00041.bin",
|
443 |
+
"transformer.h.58.mlp.dense_4h_to_h.weight": "pytorch_model-00030-of-00041.bin",
|
444 |
+
"transformer.h.58.mlp.dense_h_to_4h.weight": "pytorch_model-00030-of-00041.bin",
|
445 |
+
"transformer.h.58.self_attention.dense.weight": "pytorch_model-00030-of-00041.bin",
|
446 |
+
"transformer.h.58.self_attention.query_key_value.weight": "pytorch_model-00030-of-00041.bin",
|
447 |
+
"transformer.h.59.ln_attn.bias": "pytorch_model-00031-of-00041.bin",
|
448 |
+
"transformer.h.59.ln_attn.weight": "pytorch_model-00031-of-00041.bin",
|
449 |
+
"transformer.h.59.ln_mlp.bias": "pytorch_model-00031-of-00041.bin",
|
450 |
+
"transformer.h.59.ln_mlp.weight": "pytorch_model-00031-of-00041.bin",
|
451 |
+
"transformer.h.59.mlp.dense_4h_to_h.weight": "pytorch_model-00031-of-00041.bin",
|
452 |
+
"transformer.h.59.mlp.dense_h_to_4h.weight": "pytorch_model-00030-of-00041.bin",
|
453 |
+
"transformer.h.59.self_attention.dense.weight": "pytorch_model-00030-of-00041.bin",
|
454 |
+
"transformer.h.59.self_attention.query_key_value.weight": "pytorch_model-00030-of-00041.bin",
|
455 |
+
"transformer.h.6.ln_attn.bias": "pytorch_model-00004-of-00041.bin",
|
456 |
+
"transformer.h.6.ln_attn.weight": "pytorch_model-00004-of-00041.bin",
|
457 |
+
"transformer.h.6.ln_mlp.bias": "pytorch_model-00004-of-00041.bin",
|
458 |
+
"transformer.h.6.ln_mlp.weight": "pytorch_model-00004-of-00041.bin",
|
459 |
+
"transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00041.bin",
|
460 |
+
"transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00041.bin",
|
461 |
+
"transformer.h.6.self_attention.dense.weight": "pytorch_model-00004-of-00041.bin",
|
462 |
+
"transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00004-of-00041.bin",
|
463 |
+
"transformer.h.60.ln_attn.bias": "pytorch_model-00031-of-00041.bin",
|
464 |
+
"transformer.h.60.ln_attn.weight": "pytorch_model-00031-of-00041.bin",
|
465 |
+
"transformer.h.60.ln_mlp.bias": "pytorch_model-00031-of-00041.bin",
|
466 |
+
"transformer.h.60.ln_mlp.weight": "pytorch_model-00031-of-00041.bin",
|
467 |
+
"transformer.h.60.mlp.dense_4h_to_h.weight": "pytorch_model-00031-of-00041.bin",
|
468 |
+
"transformer.h.60.mlp.dense_h_to_4h.weight": "pytorch_model-00031-of-00041.bin",
|
469 |
+
"transformer.h.60.self_attention.dense.weight": "pytorch_model-00031-of-00041.bin",
|
470 |
+
"transformer.h.60.self_attention.query_key_value.weight": "pytorch_model-00031-of-00041.bin",
|
471 |
+
"transformer.h.61.ln_attn.bias": "pytorch_model-00032-of-00041.bin",
|
472 |
+
"transformer.h.61.ln_attn.weight": "pytorch_model-00032-of-00041.bin",
|
473 |
+
"transformer.h.61.ln_mlp.bias": "pytorch_model-00032-of-00041.bin",
|
474 |
+
"transformer.h.61.ln_mlp.weight": "pytorch_model-00032-of-00041.bin",
|
475 |
+
"transformer.h.61.mlp.dense_4h_to_h.weight": "pytorch_model-00032-of-00041.bin",
|
476 |
+
"transformer.h.61.mlp.dense_h_to_4h.weight": "pytorch_model-00031-of-00041.bin",
|
477 |
+
"transformer.h.61.self_attention.dense.weight": "pytorch_model-00031-of-00041.bin",
|
478 |
+
"transformer.h.61.self_attention.query_key_value.weight": "pytorch_model-00031-of-00041.bin",
|
479 |
+
"transformer.h.62.ln_attn.bias": "pytorch_model-00032-of-00041.bin",
|
480 |
+
"transformer.h.62.ln_attn.weight": "pytorch_model-00032-of-00041.bin",
|
481 |
+
"transformer.h.62.ln_mlp.bias": "pytorch_model-00032-of-00041.bin",
|
482 |
+
"transformer.h.62.ln_mlp.weight": "pytorch_model-00032-of-00041.bin",
|
483 |
+
"transformer.h.62.mlp.dense_4h_to_h.weight": "pytorch_model-00032-of-00041.bin",
|
484 |
+
"transformer.h.62.mlp.dense_h_to_4h.weight": "pytorch_model-00032-of-00041.bin",
|
485 |
+
"transformer.h.62.self_attention.dense.weight": "pytorch_model-00032-of-00041.bin",
|
486 |
+
"transformer.h.62.self_attention.query_key_value.weight": "pytorch_model-00032-of-00041.bin",
|
487 |
+
"transformer.h.63.ln_attn.bias": "pytorch_model-00033-of-00041.bin",
|
488 |
+
"transformer.h.63.ln_attn.weight": "pytorch_model-00033-of-00041.bin",
|
489 |
+
"transformer.h.63.ln_mlp.bias": "pytorch_model-00033-of-00041.bin",
|
490 |
+
"transformer.h.63.ln_mlp.weight": "pytorch_model-00033-of-00041.bin",
|
491 |
+
"transformer.h.63.mlp.dense_4h_to_h.weight": "pytorch_model-00033-of-00041.bin",
|
492 |
+
"transformer.h.63.mlp.dense_h_to_4h.weight": "pytorch_model-00032-of-00041.bin",
|
493 |
+
"transformer.h.63.self_attention.dense.weight": "pytorch_model-00032-of-00041.bin",
|
494 |
+
"transformer.h.63.self_attention.query_key_value.weight": "pytorch_model-00032-of-00041.bin",
|
495 |
+
"transformer.h.64.ln_attn.bias": "pytorch_model-00033-of-00041.bin",
|
496 |
+
"transformer.h.64.ln_attn.weight": "pytorch_model-00033-of-00041.bin",
|
497 |
+
"transformer.h.64.ln_mlp.bias": "pytorch_model-00033-of-00041.bin",
|
498 |
+
"transformer.h.64.ln_mlp.weight": "pytorch_model-00033-of-00041.bin",
|
499 |
+
"transformer.h.64.mlp.dense_4h_to_h.weight": "pytorch_model-00033-of-00041.bin",
|
500 |
+
"transformer.h.64.mlp.dense_h_to_4h.weight": "pytorch_model-00033-of-00041.bin",
|
501 |
+
"transformer.h.64.self_attention.dense.weight": "pytorch_model-00033-of-00041.bin",
|
502 |
+
"transformer.h.64.self_attention.query_key_value.weight": "pytorch_model-00033-of-00041.bin",
|
503 |
+
"transformer.h.65.ln_attn.bias": "pytorch_model-00034-of-00041.bin",
|
504 |
+
"transformer.h.65.ln_attn.weight": "pytorch_model-00034-of-00041.bin",
|
505 |
+
"transformer.h.65.ln_mlp.bias": "pytorch_model-00034-of-00041.bin",
|
506 |
+
"transformer.h.65.ln_mlp.weight": "pytorch_model-00034-of-00041.bin",
|
507 |
+
"transformer.h.65.mlp.dense_4h_to_h.weight": "pytorch_model-00034-of-00041.bin",
|
508 |
+
"transformer.h.65.mlp.dense_h_to_4h.weight": "pytorch_model-00033-of-00041.bin",
|
509 |
+
"transformer.h.65.self_attention.dense.weight": "pytorch_model-00033-of-00041.bin",
|
510 |
+
"transformer.h.65.self_attention.query_key_value.weight": "pytorch_model-00033-of-00041.bin",
|
511 |
+
"transformer.h.66.ln_attn.bias": "pytorch_model-00034-of-00041.bin",
|
512 |
+
"transformer.h.66.ln_attn.weight": "pytorch_model-00034-of-00041.bin",
|
513 |
+
"transformer.h.66.ln_mlp.bias": "pytorch_model-00034-of-00041.bin",
|
514 |
+
"transformer.h.66.ln_mlp.weight": "pytorch_model-00034-of-00041.bin",
|
515 |
+
"transformer.h.66.mlp.dense_4h_to_h.weight": "pytorch_model-00034-of-00041.bin",
|
516 |
+
"transformer.h.66.mlp.dense_h_to_4h.weight": "pytorch_model-00034-of-00041.bin",
|
517 |
+
"transformer.h.66.self_attention.dense.weight": "pytorch_model-00034-of-00041.bin",
|
518 |
+
"transformer.h.66.self_attention.query_key_value.weight": "pytorch_model-00034-of-00041.bin",
|
519 |
+
"transformer.h.67.ln_attn.bias": "pytorch_model-00035-of-00041.bin",
|
520 |
+
"transformer.h.67.ln_attn.weight": "pytorch_model-00035-of-00041.bin",
|
521 |
+
"transformer.h.67.ln_mlp.bias": "pytorch_model-00035-of-00041.bin",
|
522 |
+
"transformer.h.67.ln_mlp.weight": "pytorch_model-00035-of-00041.bin",
|
523 |
+
"transformer.h.67.mlp.dense_4h_to_h.weight": "pytorch_model-00035-of-00041.bin",
|
524 |
+
"transformer.h.67.mlp.dense_h_to_4h.weight": "pytorch_model-00034-of-00041.bin",
|
525 |
+
"transformer.h.67.self_attention.dense.weight": "pytorch_model-00034-of-00041.bin",
|
526 |
+
"transformer.h.67.self_attention.query_key_value.weight": "pytorch_model-00034-of-00041.bin",
|
527 |
+
"transformer.h.68.ln_attn.bias": "pytorch_model-00035-of-00041.bin",
|
528 |
+
"transformer.h.68.ln_attn.weight": "pytorch_model-00035-of-00041.bin",
|
529 |
+
"transformer.h.68.ln_mlp.bias": "pytorch_model-00035-of-00041.bin",
|
530 |
+
"transformer.h.68.ln_mlp.weight": "pytorch_model-00035-of-00041.bin",
|
531 |
+
"transformer.h.68.mlp.dense_4h_to_h.weight": "pytorch_model-00035-of-00041.bin",
|
532 |
+
"transformer.h.68.mlp.dense_h_to_4h.weight": "pytorch_model-00035-of-00041.bin",
|
533 |
+
"transformer.h.68.self_attention.dense.weight": "pytorch_model-00035-of-00041.bin",
|
534 |
+
"transformer.h.68.self_attention.query_key_value.weight": "pytorch_model-00035-of-00041.bin",
|
535 |
+
"transformer.h.69.ln_attn.bias": "pytorch_model-00036-of-00041.bin",
|
536 |
+
"transformer.h.69.ln_attn.weight": "pytorch_model-00036-of-00041.bin",
|
537 |
+
"transformer.h.69.ln_mlp.bias": "pytorch_model-00036-of-00041.bin",
|
538 |
+
"transformer.h.69.ln_mlp.weight": "pytorch_model-00036-of-00041.bin",
|
539 |
+
"transformer.h.69.mlp.dense_4h_to_h.weight": "pytorch_model-00036-of-00041.bin",
|
540 |
+
"transformer.h.69.mlp.dense_h_to_4h.weight": "pytorch_model-00035-of-00041.bin",
|
541 |
+
"transformer.h.69.self_attention.dense.weight": "pytorch_model-00035-of-00041.bin",
|
542 |
+
"transformer.h.69.self_attention.query_key_value.weight": "pytorch_model-00035-of-00041.bin",
|
543 |
+
"transformer.h.7.ln_attn.bias": "pytorch_model-00005-of-00041.bin",
|
544 |
+
"transformer.h.7.ln_attn.weight": "pytorch_model-00005-of-00041.bin",
|
545 |
+
"transformer.h.7.ln_mlp.bias": "pytorch_model-00005-of-00041.bin",
|
546 |
+
"transformer.h.7.ln_mlp.weight": "pytorch_model-00005-of-00041.bin",
|
547 |
+
"transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00041.bin",
|
548 |
+
"transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00041.bin",
|
549 |
+
"transformer.h.7.self_attention.dense.weight": "pytorch_model-00004-of-00041.bin",
|
550 |
+
"transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00004-of-00041.bin",
|
551 |
+
"transformer.h.70.ln_attn.bias": "pytorch_model-00036-of-00041.bin",
|
552 |
+
"transformer.h.70.ln_attn.weight": "pytorch_model-00036-of-00041.bin",
|
553 |
+
"transformer.h.70.ln_mlp.bias": "pytorch_model-00036-of-00041.bin",
|
554 |
+
"transformer.h.70.ln_mlp.weight": "pytorch_model-00036-of-00041.bin",
|
555 |
+
"transformer.h.70.mlp.dense_4h_to_h.weight": "pytorch_model-00036-of-00041.bin",
|
556 |
+
"transformer.h.70.mlp.dense_h_to_4h.weight": "pytorch_model-00036-of-00041.bin",
|
557 |
+
"transformer.h.70.self_attention.dense.weight": "pytorch_model-00036-of-00041.bin",
|
558 |
+
"transformer.h.70.self_attention.query_key_value.weight": "pytorch_model-00036-of-00041.bin",
|
559 |
+
"transformer.h.71.ln_attn.bias": "pytorch_model-00037-of-00041.bin",
|
560 |
+
"transformer.h.71.ln_attn.weight": "pytorch_model-00037-of-00041.bin",
|
561 |
+
"transformer.h.71.ln_mlp.bias": "pytorch_model-00037-of-00041.bin",
|
562 |
+
"transformer.h.71.ln_mlp.weight": "pytorch_model-00037-of-00041.bin",
|
563 |
+
"transformer.h.71.mlp.dense_4h_to_h.weight": "pytorch_model-00037-of-00041.bin",
|
564 |
+
"transformer.h.71.mlp.dense_h_to_4h.weight": "pytorch_model-00036-of-00041.bin",
|
565 |
+
"transformer.h.71.self_attention.dense.weight": "pytorch_model-00036-of-00041.bin",
|
566 |
+
"transformer.h.71.self_attention.query_key_value.weight": "pytorch_model-00036-of-00041.bin",
|
567 |
+
"transformer.h.72.ln_attn.bias": "pytorch_model-00037-of-00041.bin",
|
568 |
+
"transformer.h.72.ln_attn.weight": "pytorch_model-00037-of-00041.bin",
|
569 |
+
"transformer.h.72.ln_mlp.bias": "pytorch_model-00037-of-00041.bin",
|
570 |
+
"transformer.h.72.ln_mlp.weight": "pytorch_model-00037-of-00041.bin",
|
571 |
+
"transformer.h.72.mlp.dense_4h_to_h.weight": "pytorch_model-00037-of-00041.bin",
|
572 |
+
"transformer.h.72.mlp.dense_h_to_4h.weight": "pytorch_model-00037-of-00041.bin",
|
573 |
+
"transformer.h.72.self_attention.dense.weight": "pytorch_model-00037-of-00041.bin",
|
574 |
+
"transformer.h.72.self_attention.query_key_value.weight": "pytorch_model-00037-of-00041.bin",
|
575 |
+
"transformer.h.73.ln_attn.bias": "pytorch_model-00038-of-00041.bin",
|
576 |
+
"transformer.h.73.ln_attn.weight": "pytorch_model-00038-of-00041.bin",
|
577 |
+
"transformer.h.73.ln_mlp.bias": "pytorch_model-00038-of-00041.bin",
|
578 |
+
"transformer.h.73.ln_mlp.weight": "pytorch_model-00038-of-00041.bin",
|
579 |
+
"transformer.h.73.mlp.dense_4h_to_h.weight": "pytorch_model-00038-of-00041.bin",
|
580 |
+
"transformer.h.73.mlp.dense_h_to_4h.weight": "pytorch_model-00037-of-00041.bin",
|
581 |
+
"transformer.h.73.self_attention.dense.weight": "pytorch_model-00037-of-00041.bin",
|
582 |
+
"transformer.h.73.self_attention.query_key_value.weight": "pytorch_model-00037-of-00041.bin",
|
583 |
+
"transformer.h.74.ln_attn.bias": "pytorch_model-00038-of-00041.bin",
|
584 |
+
"transformer.h.74.ln_attn.weight": "pytorch_model-00038-of-00041.bin",
|
585 |
+
"transformer.h.74.ln_mlp.bias": "pytorch_model-00038-of-00041.bin",
|
586 |
+
"transformer.h.74.ln_mlp.weight": "pytorch_model-00038-of-00041.bin",
|
587 |
+
"transformer.h.74.mlp.dense_4h_to_h.weight": "pytorch_model-00038-of-00041.bin",
|
588 |
+
"transformer.h.74.mlp.dense_h_to_4h.weight": "pytorch_model-00038-of-00041.bin",
|
589 |
+
"transformer.h.74.self_attention.dense.weight": "pytorch_model-00038-of-00041.bin",
|
590 |
+
"transformer.h.74.self_attention.query_key_value.weight": "pytorch_model-00038-of-00041.bin",
|
591 |
+
"transformer.h.75.ln_attn.bias": "pytorch_model-00039-of-00041.bin",
|
592 |
+
"transformer.h.75.ln_attn.weight": "pytorch_model-00039-of-00041.bin",
|
593 |
+
"transformer.h.75.ln_mlp.bias": "pytorch_model-00039-of-00041.bin",
|
594 |
+
"transformer.h.75.ln_mlp.weight": "pytorch_model-00039-of-00041.bin",
|
595 |
+
"transformer.h.75.mlp.dense_4h_to_h.weight": "pytorch_model-00039-of-00041.bin",
|
596 |
+
"transformer.h.75.mlp.dense_h_to_4h.weight": "pytorch_model-00038-of-00041.bin",
|
597 |
+
"transformer.h.75.self_attention.dense.weight": "pytorch_model-00038-of-00041.bin",
|
598 |
+
"transformer.h.75.self_attention.query_key_value.weight": "pytorch_model-00038-of-00041.bin",
|
599 |
+
"transformer.h.76.ln_attn.bias": "pytorch_model-00039-of-00041.bin",
|
600 |
+
"transformer.h.76.ln_attn.weight": "pytorch_model-00039-of-00041.bin",
|
601 |
+
"transformer.h.76.ln_mlp.bias": "pytorch_model-00039-of-00041.bin",
|
602 |
+
"transformer.h.76.ln_mlp.weight": "pytorch_model-00039-of-00041.bin",
|
603 |
+
"transformer.h.76.mlp.dense_4h_to_h.weight": "pytorch_model-00039-of-00041.bin",
|
604 |
+
"transformer.h.76.mlp.dense_h_to_4h.weight": "pytorch_model-00039-of-00041.bin",
|
605 |
+
"transformer.h.76.self_attention.dense.weight": "pytorch_model-00039-of-00041.bin",
|
606 |
+
"transformer.h.76.self_attention.query_key_value.weight": "pytorch_model-00039-of-00041.bin",
|
607 |
+
"transformer.h.77.ln_attn.bias": "pytorch_model-00040-of-00041.bin",
|
608 |
+
"transformer.h.77.ln_attn.weight": "pytorch_model-00040-of-00041.bin",
|
609 |
+
"transformer.h.77.ln_mlp.bias": "pytorch_model-00040-of-00041.bin",
|
610 |
+
"transformer.h.77.ln_mlp.weight": "pytorch_model-00040-of-00041.bin",
|
611 |
+
"transformer.h.77.mlp.dense_4h_to_h.weight": "pytorch_model-00040-of-00041.bin",
|
612 |
+
"transformer.h.77.mlp.dense_h_to_4h.weight": "pytorch_model-00039-of-00041.bin",
|
613 |
+
"transformer.h.77.self_attention.dense.weight": "pytorch_model-00039-of-00041.bin",
|
614 |
+
"transformer.h.77.self_attention.query_key_value.weight": "pytorch_model-00039-of-00041.bin",
|
615 |
+
"transformer.h.78.ln_attn.bias": "pytorch_model-00040-of-00041.bin",
|
616 |
+
"transformer.h.78.ln_attn.weight": "pytorch_model-00040-of-00041.bin",
|
617 |
+
"transformer.h.78.ln_mlp.bias": "pytorch_model-00040-of-00041.bin",
|
618 |
+
"transformer.h.78.ln_mlp.weight": "pytorch_model-00040-of-00041.bin",
|
619 |
+
"transformer.h.78.mlp.dense_4h_to_h.weight": "pytorch_model-00040-of-00041.bin",
|
620 |
+
"transformer.h.78.mlp.dense_h_to_4h.weight": "pytorch_model-00040-of-00041.bin",
|
621 |
+
"transformer.h.78.self_attention.dense.weight": "pytorch_model-00040-of-00041.bin",
|
622 |
+
"transformer.h.78.self_attention.query_key_value.weight": "pytorch_model-00040-of-00041.bin",
|
623 |
+
"transformer.h.79.ln_attn.bias": "pytorch_model-00041-of-00041.bin",
|
624 |
+
"transformer.h.79.ln_attn.weight": "pytorch_model-00041-of-00041.bin",
|
625 |
+
"transformer.h.79.ln_mlp.bias": "pytorch_model-00041-of-00041.bin",
|
626 |
+
"transformer.h.79.ln_mlp.weight": "pytorch_model-00041-of-00041.bin",
|
627 |
+
"transformer.h.79.mlp.dense_4h_to_h.weight": "pytorch_model-00041-of-00041.bin",
|
628 |
+
"transformer.h.79.mlp.dense_h_to_4h.weight": "pytorch_model-00040-of-00041.bin",
|
629 |
+
"transformer.h.79.self_attention.dense.weight": "pytorch_model-00040-of-00041.bin",
|
630 |
+
"transformer.h.79.self_attention.query_key_value.weight": "pytorch_model-00040-of-00041.bin",
|
631 |
+
"transformer.h.8.ln_attn.bias": "pytorch_model-00005-of-00041.bin",
|
632 |
+
"transformer.h.8.ln_attn.weight": "pytorch_model-00005-of-00041.bin",
|
633 |
+
"transformer.h.8.ln_mlp.bias": "pytorch_model-00005-of-00041.bin",
|
634 |
+
"transformer.h.8.ln_mlp.weight": "pytorch_model-00005-of-00041.bin",
|
635 |
+
"transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00041.bin",
|
636 |
+
"transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00041.bin",
|
637 |
+
"transformer.h.8.self_attention.dense.weight": "pytorch_model-00005-of-00041.bin",
|
638 |
+
"transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00005-of-00041.bin",
|
639 |
+
"transformer.h.9.ln_attn.bias": "pytorch_model-00006-of-00041.bin",
|
640 |
+
"transformer.h.9.ln_attn.weight": "pytorch_model-00006-of-00041.bin",
|
641 |
+
"transformer.h.9.ln_mlp.bias": "pytorch_model-00006-of-00041.bin",
|
642 |
+
"transformer.h.9.ln_mlp.weight": "pytorch_model-00006-of-00041.bin",
|
643 |
+
"transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00041.bin",
|
644 |
+
"transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00041.bin",
|
645 |
+
"transformer.h.9.self_attention.dense.weight": "pytorch_model-00005-of-00041.bin",
|
646 |
+
"transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00005-of-00041.bin",
|
647 |
+
"transformer.ln_f.bias": "pytorch_model-00041-of-00041.bin",
|
648 |
+
"transformer.ln_f.weight": "pytorch_model-00041-of-00041.bin",
|
649 |
+
"transformer.word_embeddings.weight": "pytorch_model-00001-of-00041.bin"
|
650 |
+
}
|
651 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
">>TITLE<<",
|
4 |
+
">>ABSTRACT<<",
|
5 |
+
">>INTRODUCTION<<",
|
6 |
+
">>SUMMARY<<",
|
7 |
+
">>COMMENT<<",
|
8 |
+
">>ANSWER<<",
|
9 |
+
">>QUESTION<<",
|
10 |
+
">>DOMAIN<<",
|
11 |
+
">>PREFIX<<",
|
12 |
+
">>SUFFIX<<",
|
13 |
+
">>MIDDLE<<"
|
14 |
+
],
|
15 |
+
"eos_token": "<|endoftext|>"
|
16 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"eos_token": "<|endoftext|>",
|
5 |
+
"model_max_length": 2048,
|
6 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
7 |
+
}
|