Commit
•
048fffb
1
Parent(s):
4a1bc07
Upload 42 files
Browse files- config.json +82 -0
- generation_config.json +7 -0
- merges.txt +0 -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 +491 -0
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +33 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "KoboldAI/GPT-Neo-2.7B-Horni",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPTNeoForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0,
|
8 |
+
"attention_layers": [
|
9 |
+
"global",
|
10 |
+
"local",
|
11 |
+
"global",
|
12 |
+
"local",
|
13 |
+
"global",
|
14 |
+
"local",
|
15 |
+
"global",
|
16 |
+
"local",
|
17 |
+
"global",
|
18 |
+
"local",
|
19 |
+
"global",
|
20 |
+
"local",
|
21 |
+
"global",
|
22 |
+
"local",
|
23 |
+
"global",
|
24 |
+
"local",
|
25 |
+
"global",
|
26 |
+
"local",
|
27 |
+
"global",
|
28 |
+
"local",
|
29 |
+
"global",
|
30 |
+
"local",
|
31 |
+
"global",
|
32 |
+
"local",
|
33 |
+
"global",
|
34 |
+
"local",
|
35 |
+
"global",
|
36 |
+
"local",
|
37 |
+
"global",
|
38 |
+
"local",
|
39 |
+
"global",
|
40 |
+
"local"
|
41 |
+
],
|
42 |
+
"attention_types": [
|
43 |
+
[
|
44 |
+
[
|
45 |
+
"global",
|
46 |
+
"local"
|
47 |
+
],
|
48 |
+
16
|
49 |
+
]
|
50 |
+
],
|
51 |
+
"bos_token_id": 50256,
|
52 |
+
"embed_dropout": 0,
|
53 |
+
"eos_token_id": 50256,
|
54 |
+
"hidden_size": 2560,
|
55 |
+
"initializer_range": 0.02,
|
56 |
+
"intermediate_size": null,
|
57 |
+
"layer_norm_epsilon": 1e-05,
|
58 |
+
"max_position_embeddings": 2048,
|
59 |
+
"model_type": "gpt_neo",
|
60 |
+
"num_heads": 20,
|
61 |
+
"num_layers": 32,
|
62 |
+
"rep_pen": 2.0,
|
63 |
+
"resid_dropout": 0,
|
64 |
+
"summary_activation": null,
|
65 |
+
"summary_first_dropout": 0.1,
|
66 |
+
"summary_proj_to_labels": true,
|
67 |
+
"summary_type": "cls_index",
|
68 |
+
"summary_use_proj": true,
|
69 |
+
"task_specific_params": {
|
70 |
+
"text-generation": {
|
71 |
+
"do_sample": true,
|
72 |
+
"max_length": 50,
|
73 |
+
"temperature": 0.9
|
74 |
+
}
|
75 |
+
},
|
76 |
+
"tokenizer_class": "GPT2Tokenizer",
|
77 |
+
"torch_dtype": "float16",
|
78 |
+
"transformers_version": "4.27.4",
|
79 |
+
"use_cache": false,
|
80 |
+
"vocab_size": 50257,
|
81 |
+
"window_size": 256
|
82 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.27.4",
|
6 |
+
"use_cache": false
|
7 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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:ff2c4811d3084e3f8899490d040f6390de3b6b300f537807026fccb961c94b55
|
3 |
+
size 257316778
|
pytorch_model-00003-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77ad16bda77e30987425ea6bbc565859580c0074df1d435f335bec81c1d610e3
|
3 |
+
size 202443995
|
pytorch_model-00004-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7693eeacab18f7fddc9790523040d019ad51ca3e78aa1ed2592afebb601e903a
|
3 |
+
size 187768439
|
pytorch_model-00005-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d2a78bbdfa93cfe8f32c9d9b60e2d87f099ee4b14ff9c00b25b4e6023afa5e7
|
3 |
+
size 161537181
|
pytorch_model-00006-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea3fe91bd58a7857889eed63d19ae4c1c6469d52c0f2a0836865f3f094e5f78f
|
3 |
+
size 161537181
|
pytorch_model-00007-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4cdf137cf12258d8914694f42a220fdae0744d6e7e33a71e2934dcd9642cb9d
|
3 |
+
size 161537181
|
pytorch_model-00008-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c4c24616eca27229c5ff6f571248bba279db99fc5f130c7d1f3b9b1929aeeb1
|
3 |
+
size 161537181
|
pytorch_model-00009-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a6c8b03e80f7b904ec35c39092f3775d753750de3fd6144e586dae1869c2dc8
|
3 |
+
size 161537181
|
pytorch_model-00010-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58e8795ab24bbe49c64c196a9b44714fd734d925fc35f45c70a44caaf00e40f4
|
3 |
+
size 161537181
|
pytorch_model-00011-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd3911936872ab0c4fa5832ac3f4f1229d8ac5aacf960521357deccb2855c8bd
|
3 |
+
size 161537181
|
pytorch_model-00012-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:079901b8bf4738cc049abc9abb64f1617386ebd4968584b2daf53af8885b6883
|
3 |
+
size 161537181
|
pytorch_model-00013-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9765e40c4365d88b0c2b9a3ce8dd01ebe6bc6fd414623cde1175660035004883
|
3 |
+
size 161537181
|
pytorch_model-00014-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba1235ab0e45428d8da691a4e206c35940bc3ec16d2e09b6b77bf109d6336cd6
|
3 |
+
size 161537181
|
pytorch_model-00015-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55cb363102c04a5db91508782798cab1f0504bbd006293e466d60fd2b887adcc
|
3 |
+
size 161537181
|
pytorch_model-00016-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b46beae3fede30053bec5405c5b7581aebeb256b321739bb6d61a760eecbf7ea
|
3 |
+
size 161537181
|
pytorch_model-00017-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1b2d513be157415e05b9211c00348d491215ac009bfdb5df072d5c17a37dd86
|
3 |
+
size 161537181
|
pytorch_model-00018-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a0cc4e2c67b69cf0248c5840328dcf0da728df3299c48fe4774fce89d7d8402
|
3 |
+
size 161537181
|
pytorch_model-00019-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06afc4d91903fc611c468461f9c35af2da7815e967313e8e70590970ae4f204c
|
3 |
+
size 161537181
|
pytorch_model-00020-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6890fdabe9ea3d62963bcf77a50cfe75faadfb05be25098bd4ac500f9c60c87
|
3 |
+
size 161537181
|
pytorch_model-00021-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e15418ddcff312163cbf0fc02644ca716a55de24a9161f124f05215de7ee446
|
3 |
+
size 161537181
|
pytorch_model-00022-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d959119c3b14b8488c87ca7a1e0611b4ea8f9a56ba0308985582652440863ccd
|
3 |
+
size 161537181
|
pytorch_model-00023-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6f04996567765611dd844fc0e82f07b2d06cca6f566531a006326dbd255389d
|
3 |
+
size 161537181
|
pytorch_model-00024-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4ec3f4b5418876ad642f9e8f67b50256886b77a62b1a9360d2d22f45a7c6983
|
3 |
+
size 161537181
|
pytorch_model-00025-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97470d9dc4c7ef6c63b80e1a57f96fb783a6f6e9d6be26f340269ed572166efb
|
3 |
+
size 161537181
|
pytorch_model-00026-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ac2c53428c5bd26af9f9dc333e2ac9c53d114c1349d6cfa15525698b9c21672
|
3 |
+
size 161537181
|
pytorch_model-00027-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67785749f1dda5c213de5a78ccd6e8e6cc5cffa28c3e64a1f28baba6f866bc3a
|
3 |
+
size 161537181
|
pytorch_model-00028-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8967a6cc210a9fcac268021996454a53c09de4b8186db85089ca312740d6038b
|
3 |
+
size 161537181
|
pytorch_model-00029-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:903907068603b879c1a13be04b29be4285bafd3f5e749a112689cf5d2cf7a5c6
|
3 |
+
size 161537181
|
pytorch_model-00030-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01852da94533457319203c205a75e4835f1cdb9627bd31175f3497e19bba5711
|
3 |
+
size 161537181
|
pytorch_model-00031-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f0166ff19d9ae7e469021d1aa5b9d4cdd1ba4266c2f18cf2f90b6ba8bcba0d1
|
3 |
+
size 161537181
|
pytorch_model-00032-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b78f6fa5b004abbd90eae1888baed8042ff4212c5ba57f1ba1c72f61620b81d
|
3 |
+
size 161537181
|
pytorch_model-00033-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:662818f32484cd5b7330330b301af7891f811d46a4a7df893a5084b36be83b0c
|
3 |
+
size 161537181
|
pytorch_model-00034-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e52d5ec04e9d8d07185a75409cf8d909ff20df1099ba28f5223cfb035532f40e
|
3 |
+
size 104895871
|
pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,491 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 5319392320.0
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"transformer.h.0.attn.attention.bias": "pytorch_model-00003-of-00034.bin",
|
7 |
+
"transformer.h.0.attn.attention.k_proj.weight": "pytorch_model-00003-of-00034.bin",
|
8 |
+
"transformer.h.0.attn.attention.masked_bias": "pytorch_model-00003-of-00034.bin",
|
9 |
+
"transformer.h.0.attn.attention.out_proj.bias": "pytorch_model-00003-of-00034.bin",
|
10 |
+
"transformer.h.0.attn.attention.out_proj.weight": "pytorch_model-00003-of-00034.bin",
|
11 |
+
"transformer.h.0.attn.attention.q_proj.weight": "pytorch_model-00003-of-00034.bin",
|
12 |
+
"transformer.h.0.attn.attention.v_proj.weight": "pytorch_model-00003-of-00034.bin",
|
13 |
+
"transformer.h.0.ln_1.bias": "pytorch_model-00003-of-00034.bin",
|
14 |
+
"transformer.h.0.ln_1.weight": "pytorch_model-00003-of-00034.bin",
|
15 |
+
"transformer.h.0.ln_2.bias": "pytorch_model-00003-of-00034.bin",
|
16 |
+
"transformer.h.0.ln_2.weight": "pytorch_model-00003-of-00034.bin",
|
17 |
+
"transformer.h.0.mlp.c_fc.bias": "pytorch_model-00003-of-00034.bin",
|
18 |
+
"transformer.h.0.mlp.c_fc.weight": "pytorch_model-00003-of-00034.bin",
|
19 |
+
"transformer.h.0.mlp.c_proj.bias": "pytorch_model-00003-of-00034.bin",
|
20 |
+
"transformer.h.0.mlp.c_proj.weight": "pytorch_model-00003-of-00034.bin",
|
21 |
+
"transformer.h.1.attn.attention.bias": "pytorch_model-00003-of-00034.bin",
|
22 |
+
"transformer.h.1.attn.attention.k_proj.weight": "pytorch_model-00003-of-00034.bin",
|
23 |
+
"transformer.h.1.attn.attention.masked_bias": "pytorch_model-00003-of-00034.bin",
|
24 |
+
"transformer.h.1.attn.attention.out_proj.bias": "pytorch_model-00004-of-00034.bin",
|
25 |
+
"transformer.h.1.attn.attention.out_proj.weight": "pytorch_model-00004-of-00034.bin",
|
26 |
+
"transformer.h.1.attn.attention.q_proj.weight": "pytorch_model-00004-of-00034.bin",
|
27 |
+
"transformer.h.1.attn.attention.v_proj.weight": "pytorch_model-00003-of-00034.bin",
|
28 |
+
"transformer.h.1.ln_1.bias": "pytorch_model-00003-of-00034.bin",
|
29 |
+
"transformer.h.1.ln_1.weight": "pytorch_model-00003-of-00034.bin",
|
30 |
+
"transformer.h.1.ln_2.bias": "pytorch_model-00004-of-00034.bin",
|
31 |
+
"transformer.h.1.ln_2.weight": "pytorch_model-00004-of-00034.bin",
|
32 |
+
"transformer.h.1.mlp.c_fc.bias": "pytorch_model-00004-of-00034.bin",
|
33 |
+
"transformer.h.1.mlp.c_fc.weight": "pytorch_model-00004-of-00034.bin",
|
34 |
+
"transformer.h.1.mlp.c_proj.bias": "pytorch_model-00004-of-00034.bin",
|
35 |
+
"transformer.h.1.mlp.c_proj.weight": "pytorch_model-00004-of-00034.bin",
|
36 |
+
"transformer.h.10.attn.attention.bias": "pytorch_model-00012-of-00034.bin",
|
37 |
+
"transformer.h.10.attn.attention.k_proj.weight": "pytorch_model-00012-of-00034.bin",
|
38 |
+
"transformer.h.10.attn.attention.masked_bias": "pytorch_model-00012-of-00034.bin",
|
39 |
+
"transformer.h.10.attn.attention.out_proj.bias": "pytorch_model-00012-of-00034.bin",
|
40 |
+
"transformer.h.10.attn.attention.out_proj.weight": "pytorch_model-00012-of-00034.bin",
|
41 |
+
"transformer.h.10.attn.attention.q_proj.weight": "pytorch_model-00012-of-00034.bin",
|
42 |
+
"transformer.h.10.attn.attention.v_proj.weight": "pytorch_model-00012-of-00034.bin",
|
43 |
+
"transformer.h.10.ln_1.bias": "pytorch_model-00012-of-00034.bin",
|
44 |
+
"transformer.h.10.ln_1.weight": "pytorch_model-00012-of-00034.bin",
|
45 |
+
"transformer.h.10.ln_2.bias": "pytorch_model-00012-of-00034.bin",
|
46 |
+
"transformer.h.10.ln_2.weight": "pytorch_model-00012-of-00034.bin",
|
47 |
+
"transformer.h.10.mlp.c_fc.bias": "pytorch_model-00013-of-00034.bin",
|
48 |
+
"transformer.h.10.mlp.c_fc.weight": "pytorch_model-00013-of-00034.bin",
|
49 |
+
"transformer.h.10.mlp.c_proj.bias": "pytorch_model-00013-of-00034.bin",
|
50 |
+
"transformer.h.10.mlp.c_proj.weight": "pytorch_model-00013-of-00034.bin",
|
51 |
+
"transformer.h.11.attn.attention.bias": "pytorch_model-00013-of-00034.bin",
|
52 |
+
"transformer.h.11.attn.attention.k_proj.weight": "pytorch_model-00013-of-00034.bin",
|
53 |
+
"transformer.h.11.attn.attention.masked_bias": "pytorch_model-00013-of-00034.bin",
|
54 |
+
"transformer.h.11.attn.attention.out_proj.bias": "pytorch_model-00013-of-00034.bin",
|
55 |
+
"transformer.h.11.attn.attention.out_proj.weight": "pytorch_model-00013-of-00034.bin",
|
56 |
+
"transformer.h.11.attn.attention.q_proj.weight": "pytorch_model-00013-of-00034.bin",
|
57 |
+
"transformer.h.11.attn.attention.v_proj.weight": "pytorch_model-00013-of-00034.bin",
|
58 |
+
"transformer.h.11.ln_1.bias": "pytorch_model-00013-of-00034.bin",
|
59 |
+
"transformer.h.11.ln_1.weight": "pytorch_model-00013-of-00034.bin",
|
60 |
+
"transformer.h.11.ln_2.bias": "pytorch_model-00013-of-00034.bin",
|
61 |
+
"transformer.h.11.ln_2.weight": "pytorch_model-00013-of-00034.bin",
|
62 |
+
"transformer.h.11.mlp.c_fc.bias": "pytorch_model-00014-of-00034.bin",
|
63 |
+
"transformer.h.11.mlp.c_fc.weight": "pytorch_model-00014-of-00034.bin",
|
64 |
+
"transformer.h.11.mlp.c_proj.bias": "pytorch_model-00014-of-00034.bin",
|
65 |
+
"transformer.h.11.mlp.c_proj.weight": "pytorch_model-00014-of-00034.bin",
|
66 |
+
"transformer.h.12.attn.attention.bias": "pytorch_model-00014-of-00034.bin",
|
67 |
+
"transformer.h.12.attn.attention.k_proj.weight": "pytorch_model-00014-of-00034.bin",
|
68 |
+
"transformer.h.12.attn.attention.masked_bias": "pytorch_model-00014-of-00034.bin",
|
69 |
+
"transformer.h.12.attn.attention.out_proj.bias": "pytorch_model-00014-of-00034.bin",
|
70 |
+
"transformer.h.12.attn.attention.out_proj.weight": "pytorch_model-00014-of-00034.bin",
|
71 |
+
"transformer.h.12.attn.attention.q_proj.weight": "pytorch_model-00014-of-00034.bin",
|
72 |
+
"transformer.h.12.attn.attention.v_proj.weight": "pytorch_model-00014-of-00034.bin",
|
73 |
+
"transformer.h.12.ln_1.bias": "pytorch_model-00014-of-00034.bin",
|
74 |
+
"transformer.h.12.ln_1.weight": "pytorch_model-00014-of-00034.bin",
|
75 |
+
"transformer.h.12.ln_2.bias": "pytorch_model-00014-of-00034.bin",
|
76 |
+
"transformer.h.12.ln_2.weight": "pytorch_model-00014-of-00034.bin",
|
77 |
+
"transformer.h.12.mlp.c_fc.bias": "pytorch_model-00015-of-00034.bin",
|
78 |
+
"transformer.h.12.mlp.c_fc.weight": "pytorch_model-00015-of-00034.bin",
|
79 |
+
"transformer.h.12.mlp.c_proj.bias": "pytorch_model-00015-of-00034.bin",
|
80 |
+
"transformer.h.12.mlp.c_proj.weight": "pytorch_model-00015-of-00034.bin",
|
81 |
+
"transformer.h.13.attn.attention.bias": "pytorch_model-00015-of-00034.bin",
|
82 |
+
"transformer.h.13.attn.attention.k_proj.weight": "pytorch_model-00015-of-00034.bin",
|
83 |
+
"transformer.h.13.attn.attention.masked_bias": "pytorch_model-00015-of-00034.bin",
|
84 |
+
"transformer.h.13.attn.attention.out_proj.bias": "pytorch_model-00015-of-00034.bin",
|
85 |
+
"transformer.h.13.attn.attention.out_proj.weight": "pytorch_model-00015-of-00034.bin",
|
86 |
+
"transformer.h.13.attn.attention.q_proj.weight": "pytorch_model-00015-of-00034.bin",
|
87 |
+
"transformer.h.13.attn.attention.v_proj.weight": "pytorch_model-00015-of-00034.bin",
|
88 |
+
"transformer.h.13.ln_1.bias": "pytorch_model-00015-of-00034.bin",
|
89 |
+
"transformer.h.13.ln_1.weight": "pytorch_model-00015-of-00034.bin",
|
90 |
+
"transformer.h.13.ln_2.bias": "pytorch_model-00015-of-00034.bin",
|
91 |
+
"transformer.h.13.ln_2.weight": "pytorch_model-00015-of-00034.bin",
|
92 |
+
"transformer.h.13.mlp.c_fc.bias": "pytorch_model-00016-of-00034.bin",
|
93 |
+
"transformer.h.13.mlp.c_fc.weight": "pytorch_model-00016-of-00034.bin",
|
94 |
+
"transformer.h.13.mlp.c_proj.bias": "pytorch_model-00016-of-00034.bin",
|
95 |
+
"transformer.h.13.mlp.c_proj.weight": "pytorch_model-00016-of-00034.bin",
|
96 |
+
"transformer.h.14.attn.attention.bias": "pytorch_model-00016-of-00034.bin",
|
97 |
+
"transformer.h.14.attn.attention.k_proj.weight": "pytorch_model-00016-of-00034.bin",
|
98 |
+
"transformer.h.14.attn.attention.masked_bias": "pytorch_model-00016-of-00034.bin",
|
99 |
+
"transformer.h.14.attn.attention.out_proj.bias": "pytorch_model-00016-of-00034.bin",
|
100 |
+
"transformer.h.14.attn.attention.out_proj.weight": "pytorch_model-00016-of-00034.bin",
|
101 |
+
"transformer.h.14.attn.attention.q_proj.weight": "pytorch_model-00016-of-00034.bin",
|
102 |
+
"transformer.h.14.attn.attention.v_proj.weight": "pytorch_model-00016-of-00034.bin",
|
103 |
+
"transformer.h.14.ln_1.bias": "pytorch_model-00016-of-00034.bin",
|
104 |
+
"transformer.h.14.ln_1.weight": "pytorch_model-00016-of-00034.bin",
|
105 |
+
"transformer.h.14.ln_2.bias": "pytorch_model-00016-of-00034.bin",
|
106 |
+
"transformer.h.14.ln_2.weight": "pytorch_model-00016-of-00034.bin",
|
107 |
+
"transformer.h.14.mlp.c_fc.bias": "pytorch_model-00017-of-00034.bin",
|
108 |
+
"transformer.h.14.mlp.c_fc.weight": "pytorch_model-00017-of-00034.bin",
|
109 |
+
"transformer.h.14.mlp.c_proj.bias": "pytorch_model-00017-of-00034.bin",
|
110 |
+
"transformer.h.14.mlp.c_proj.weight": "pytorch_model-00017-of-00034.bin",
|
111 |
+
"transformer.h.15.attn.attention.bias": "pytorch_model-00017-of-00034.bin",
|
112 |
+
"transformer.h.15.attn.attention.k_proj.weight": "pytorch_model-00017-of-00034.bin",
|
113 |
+
"transformer.h.15.attn.attention.masked_bias": "pytorch_model-00017-of-00034.bin",
|
114 |
+
"transformer.h.15.attn.attention.out_proj.bias": "pytorch_model-00017-of-00034.bin",
|
115 |
+
"transformer.h.15.attn.attention.out_proj.weight": "pytorch_model-00017-of-00034.bin",
|
116 |
+
"transformer.h.15.attn.attention.q_proj.weight": "pytorch_model-00017-of-00034.bin",
|
117 |
+
"transformer.h.15.attn.attention.v_proj.weight": "pytorch_model-00017-of-00034.bin",
|
118 |
+
"transformer.h.15.ln_1.bias": "pytorch_model-00017-of-00034.bin",
|
119 |
+
"transformer.h.15.ln_1.weight": "pytorch_model-00017-of-00034.bin",
|
120 |
+
"transformer.h.15.ln_2.bias": "pytorch_model-00017-of-00034.bin",
|
121 |
+
"transformer.h.15.ln_2.weight": "pytorch_model-00017-of-00034.bin",
|
122 |
+
"transformer.h.15.mlp.c_fc.bias": "pytorch_model-00018-of-00034.bin",
|
123 |
+
"transformer.h.15.mlp.c_fc.weight": "pytorch_model-00018-of-00034.bin",
|
124 |
+
"transformer.h.15.mlp.c_proj.bias": "pytorch_model-00018-of-00034.bin",
|
125 |
+
"transformer.h.15.mlp.c_proj.weight": "pytorch_model-00018-of-00034.bin",
|
126 |
+
"transformer.h.16.attn.attention.bias": "pytorch_model-00018-of-00034.bin",
|
127 |
+
"transformer.h.16.attn.attention.k_proj.weight": "pytorch_model-00018-of-00034.bin",
|
128 |
+
"transformer.h.16.attn.attention.masked_bias": "pytorch_model-00018-of-00034.bin",
|
129 |
+
"transformer.h.16.attn.attention.out_proj.bias": "pytorch_model-00018-of-00034.bin",
|
130 |
+
"transformer.h.16.attn.attention.out_proj.weight": "pytorch_model-00018-of-00034.bin",
|
131 |
+
"transformer.h.16.attn.attention.q_proj.weight": "pytorch_model-00018-of-00034.bin",
|
132 |
+
"transformer.h.16.attn.attention.v_proj.weight": "pytorch_model-00018-of-00034.bin",
|
133 |
+
"transformer.h.16.ln_1.bias": "pytorch_model-00018-of-00034.bin",
|
134 |
+
"transformer.h.16.ln_1.weight": "pytorch_model-00018-of-00034.bin",
|
135 |
+
"transformer.h.16.ln_2.bias": "pytorch_model-00018-of-00034.bin",
|
136 |
+
"transformer.h.16.ln_2.weight": "pytorch_model-00018-of-00034.bin",
|
137 |
+
"transformer.h.16.mlp.c_fc.bias": "pytorch_model-00019-of-00034.bin",
|
138 |
+
"transformer.h.16.mlp.c_fc.weight": "pytorch_model-00019-of-00034.bin",
|
139 |
+
"transformer.h.16.mlp.c_proj.bias": "pytorch_model-00019-of-00034.bin",
|
140 |
+
"transformer.h.16.mlp.c_proj.weight": "pytorch_model-00019-of-00034.bin",
|
141 |
+
"transformer.h.17.attn.attention.bias": "pytorch_model-00019-of-00034.bin",
|
142 |
+
"transformer.h.17.attn.attention.k_proj.weight": "pytorch_model-00019-of-00034.bin",
|
143 |
+
"transformer.h.17.attn.attention.masked_bias": "pytorch_model-00019-of-00034.bin",
|
144 |
+
"transformer.h.17.attn.attention.out_proj.bias": "pytorch_model-00019-of-00034.bin",
|
145 |
+
"transformer.h.17.attn.attention.out_proj.weight": "pytorch_model-00019-of-00034.bin",
|
146 |
+
"transformer.h.17.attn.attention.q_proj.weight": "pytorch_model-00019-of-00034.bin",
|
147 |
+
"transformer.h.17.attn.attention.v_proj.weight": "pytorch_model-00019-of-00034.bin",
|
148 |
+
"transformer.h.17.ln_1.bias": "pytorch_model-00019-of-00034.bin",
|
149 |
+
"transformer.h.17.ln_1.weight": "pytorch_model-00019-of-00034.bin",
|
150 |
+
"transformer.h.17.ln_2.bias": "pytorch_model-00019-of-00034.bin",
|
151 |
+
"transformer.h.17.ln_2.weight": "pytorch_model-00019-of-00034.bin",
|
152 |
+
"transformer.h.17.mlp.c_fc.bias": "pytorch_model-00020-of-00034.bin",
|
153 |
+
"transformer.h.17.mlp.c_fc.weight": "pytorch_model-00020-of-00034.bin",
|
154 |
+
"transformer.h.17.mlp.c_proj.bias": "pytorch_model-00020-of-00034.bin",
|
155 |
+
"transformer.h.17.mlp.c_proj.weight": "pytorch_model-00020-of-00034.bin",
|
156 |
+
"transformer.h.18.attn.attention.bias": "pytorch_model-00020-of-00034.bin",
|
157 |
+
"transformer.h.18.attn.attention.k_proj.weight": "pytorch_model-00020-of-00034.bin",
|
158 |
+
"transformer.h.18.attn.attention.masked_bias": "pytorch_model-00020-of-00034.bin",
|
159 |
+
"transformer.h.18.attn.attention.out_proj.bias": "pytorch_model-00020-of-00034.bin",
|
160 |
+
"transformer.h.18.attn.attention.out_proj.weight": "pytorch_model-00020-of-00034.bin",
|
161 |
+
"transformer.h.18.attn.attention.q_proj.weight": "pytorch_model-00020-of-00034.bin",
|
162 |
+
"transformer.h.18.attn.attention.v_proj.weight": "pytorch_model-00020-of-00034.bin",
|
163 |
+
"transformer.h.18.ln_1.bias": "pytorch_model-00020-of-00034.bin",
|
164 |
+
"transformer.h.18.ln_1.weight": "pytorch_model-00020-of-00034.bin",
|
165 |
+
"transformer.h.18.ln_2.bias": "pytorch_model-00020-of-00034.bin",
|
166 |
+
"transformer.h.18.ln_2.weight": "pytorch_model-00020-of-00034.bin",
|
167 |
+
"transformer.h.18.mlp.c_fc.bias": "pytorch_model-00021-of-00034.bin",
|
168 |
+
"transformer.h.18.mlp.c_fc.weight": "pytorch_model-00021-of-00034.bin",
|
169 |
+
"transformer.h.18.mlp.c_proj.bias": "pytorch_model-00021-of-00034.bin",
|
170 |
+
"transformer.h.18.mlp.c_proj.weight": "pytorch_model-00021-of-00034.bin",
|
171 |
+
"transformer.h.19.attn.attention.bias": "pytorch_model-00021-of-00034.bin",
|
172 |
+
"transformer.h.19.attn.attention.k_proj.weight": "pytorch_model-00021-of-00034.bin",
|
173 |
+
"transformer.h.19.attn.attention.masked_bias": "pytorch_model-00021-of-00034.bin",
|
174 |
+
"transformer.h.19.attn.attention.out_proj.bias": "pytorch_model-00021-of-00034.bin",
|
175 |
+
"transformer.h.19.attn.attention.out_proj.weight": "pytorch_model-00021-of-00034.bin",
|
176 |
+
"transformer.h.19.attn.attention.q_proj.weight": "pytorch_model-00021-of-00034.bin",
|
177 |
+
"transformer.h.19.attn.attention.v_proj.weight": "pytorch_model-00021-of-00034.bin",
|
178 |
+
"transformer.h.19.ln_1.bias": "pytorch_model-00021-of-00034.bin",
|
179 |
+
"transformer.h.19.ln_1.weight": "pytorch_model-00021-of-00034.bin",
|
180 |
+
"transformer.h.19.ln_2.bias": "pytorch_model-00021-of-00034.bin",
|
181 |
+
"transformer.h.19.ln_2.weight": "pytorch_model-00021-of-00034.bin",
|
182 |
+
"transformer.h.19.mlp.c_fc.bias": "pytorch_model-00022-of-00034.bin",
|
183 |
+
"transformer.h.19.mlp.c_fc.weight": "pytorch_model-00022-of-00034.bin",
|
184 |
+
"transformer.h.19.mlp.c_proj.bias": "pytorch_model-00022-of-00034.bin",
|
185 |
+
"transformer.h.19.mlp.c_proj.weight": "pytorch_model-00022-of-00034.bin",
|
186 |
+
"transformer.h.2.attn.attention.bias": "pytorch_model-00004-of-00034.bin",
|
187 |
+
"transformer.h.2.attn.attention.k_proj.weight": "pytorch_model-00004-of-00034.bin",
|
188 |
+
"transformer.h.2.attn.attention.masked_bias": "pytorch_model-00004-of-00034.bin",
|
189 |
+
"transformer.h.2.attn.attention.out_proj.bias": "pytorch_model-00004-of-00034.bin",
|
190 |
+
"transformer.h.2.attn.attention.out_proj.weight": "pytorch_model-00004-of-00034.bin",
|
191 |
+
"transformer.h.2.attn.attention.q_proj.weight": "pytorch_model-00004-of-00034.bin",
|
192 |
+
"transformer.h.2.attn.attention.v_proj.weight": "pytorch_model-00004-of-00034.bin",
|
193 |
+
"transformer.h.2.ln_1.bias": "pytorch_model-00004-of-00034.bin",
|
194 |
+
"transformer.h.2.ln_1.weight": "pytorch_model-00004-of-00034.bin",
|
195 |
+
"transformer.h.2.ln_2.bias": "pytorch_model-00004-of-00034.bin",
|
196 |
+
"transformer.h.2.ln_2.weight": "pytorch_model-00004-of-00034.bin",
|
197 |
+
"transformer.h.2.mlp.c_fc.bias": "pytorch_model-00005-of-00034.bin",
|
198 |
+
"transformer.h.2.mlp.c_fc.weight": "pytorch_model-00005-of-00034.bin",
|
199 |
+
"transformer.h.2.mlp.c_proj.bias": "pytorch_model-00005-of-00034.bin",
|
200 |
+
"transformer.h.2.mlp.c_proj.weight": "pytorch_model-00005-of-00034.bin",
|
201 |
+
"transformer.h.20.attn.attention.bias": "pytorch_model-00022-of-00034.bin",
|
202 |
+
"transformer.h.20.attn.attention.k_proj.weight": "pytorch_model-00022-of-00034.bin",
|
203 |
+
"transformer.h.20.attn.attention.masked_bias": "pytorch_model-00022-of-00034.bin",
|
204 |
+
"transformer.h.20.attn.attention.out_proj.bias": "pytorch_model-00022-of-00034.bin",
|
205 |
+
"transformer.h.20.attn.attention.out_proj.weight": "pytorch_model-00022-of-00034.bin",
|
206 |
+
"transformer.h.20.attn.attention.q_proj.weight": "pytorch_model-00022-of-00034.bin",
|
207 |
+
"transformer.h.20.attn.attention.v_proj.weight": "pytorch_model-00022-of-00034.bin",
|
208 |
+
"transformer.h.20.ln_1.bias": "pytorch_model-00022-of-00034.bin",
|
209 |
+
"transformer.h.20.ln_1.weight": "pytorch_model-00022-of-00034.bin",
|
210 |
+
"transformer.h.20.ln_2.bias": "pytorch_model-00022-of-00034.bin",
|
211 |
+
"transformer.h.20.ln_2.weight": "pytorch_model-00022-of-00034.bin",
|
212 |
+
"transformer.h.20.mlp.c_fc.bias": "pytorch_model-00023-of-00034.bin",
|
213 |
+
"transformer.h.20.mlp.c_fc.weight": "pytorch_model-00023-of-00034.bin",
|
214 |
+
"transformer.h.20.mlp.c_proj.bias": "pytorch_model-00023-of-00034.bin",
|
215 |
+
"transformer.h.20.mlp.c_proj.weight": "pytorch_model-00023-of-00034.bin",
|
216 |
+
"transformer.h.21.attn.attention.bias": "pytorch_model-00023-of-00034.bin",
|
217 |
+
"transformer.h.21.attn.attention.k_proj.weight": "pytorch_model-00023-of-00034.bin",
|
218 |
+
"transformer.h.21.attn.attention.masked_bias": "pytorch_model-00023-of-00034.bin",
|
219 |
+
"transformer.h.21.attn.attention.out_proj.bias": "pytorch_model-00023-of-00034.bin",
|
220 |
+
"transformer.h.21.attn.attention.out_proj.weight": "pytorch_model-00023-of-00034.bin",
|
221 |
+
"transformer.h.21.attn.attention.q_proj.weight": "pytorch_model-00023-of-00034.bin",
|
222 |
+
"transformer.h.21.attn.attention.v_proj.weight": "pytorch_model-00023-of-00034.bin",
|
223 |
+
"transformer.h.21.ln_1.bias": "pytorch_model-00023-of-00034.bin",
|
224 |
+
"transformer.h.21.ln_1.weight": "pytorch_model-00023-of-00034.bin",
|
225 |
+
"transformer.h.21.ln_2.bias": "pytorch_model-00023-of-00034.bin",
|
226 |
+
"transformer.h.21.ln_2.weight": "pytorch_model-00023-of-00034.bin",
|
227 |
+
"transformer.h.21.mlp.c_fc.bias": "pytorch_model-00024-of-00034.bin",
|
228 |
+
"transformer.h.21.mlp.c_fc.weight": "pytorch_model-00024-of-00034.bin",
|
229 |
+
"transformer.h.21.mlp.c_proj.bias": "pytorch_model-00024-of-00034.bin",
|
230 |
+
"transformer.h.21.mlp.c_proj.weight": "pytorch_model-00024-of-00034.bin",
|
231 |
+
"transformer.h.22.attn.attention.bias": "pytorch_model-00024-of-00034.bin",
|
232 |
+
"transformer.h.22.attn.attention.k_proj.weight": "pytorch_model-00024-of-00034.bin",
|
233 |
+
"transformer.h.22.attn.attention.masked_bias": "pytorch_model-00024-of-00034.bin",
|
234 |
+
"transformer.h.22.attn.attention.out_proj.bias": "pytorch_model-00024-of-00034.bin",
|
235 |
+
"transformer.h.22.attn.attention.out_proj.weight": "pytorch_model-00024-of-00034.bin",
|
236 |
+
"transformer.h.22.attn.attention.q_proj.weight": "pytorch_model-00024-of-00034.bin",
|
237 |
+
"transformer.h.22.attn.attention.v_proj.weight": "pytorch_model-00024-of-00034.bin",
|
238 |
+
"transformer.h.22.ln_1.bias": "pytorch_model-00024-of-00034.bin",
|
239 |
+
"transformer.h.22.ln_1.weight": "pytorch_model-00024-of-00034.bin",
|
240 |
+
"transformer.h.22.ln_2.bias": "pytorch_model-00024-of-00034.bin",
|
241 |
+
"transformer.h.22.ln_2.weight": "pytorch_model-00024-of-00034.bin",
|
242 |
+
"transformer.h.22.mlp.c_fc.bias": "pytorch_model-00025-of-00034.bin",
|
243 |
+
"transformer.h.22.mlp.c_fc.weight": "pytorch_model-00025-of-00034.bin",
|
244 |
+
"transformer.h.22.mlp.c_proj.bias": "pytorch_model-00025-of-00034.bin",
|
245 |
+
"transformer.h.22.mlp.c_proj.weight": "pytorch_model-00025-of-00034.bin",
|
246 |
+
"transformer.h.23.attn.attention.bias": "pytorch_model-00025-of-00034.bin",
|
247 |
+
"transformer.h.23.attn.attention.k_proj.weight": "pytorch_model-00025-of-00034.bin",
|
248 |
+
"transformer.h.23.attn.attention.masked_bias": "pytorch_model-00025-of-00034.bin",
|
249 |
+
"transformer.h.23.attn.attention.out_proj.bias": "pytorch_model-00025-of-00034.bin",
|
250 |
+
"transformer.h.23.attn.attention.out_proj.weight": "pytorch_model-00025-of-00034.bin",
|
251 |
+
"transformer.h.23.attn.attention.q_proj.weight": "pytorch_model-00025-of-00034.bin",
|
252 |
+
"transformer.h.23.attn.attention.v_proj.weight": "pytorch_model-00025-of-00034.bin",
|
253 |
+
"transformer.h.23.ln_1.bias": "pytorch_model-00025-of-00034.bin",
|
254 |
+
"transformer.h.23.ln_1.weight": "pytorch_model-00025-of-00034.bin",
|
255 |
+
"transformer.h.23.ln_2.bias": "pytorch_model-00025-of-00034.bin",
|
256 |
+
"transformer.h.23.ln_2.weight": "pytorch_model-00025-of-00034.bin",
|
257 |
+
"transformer.h.23.mlp.c_fc.bias": "pytorch_model-00026-of-00034.bin",
|
258 |
+
"transformer.h.23.mlp.c_fc.weight": "pytorch_model-00026-of-00034.bin",
|
259 |
+
"transformer.h.23.mlp.c_proj.bias": "pytorch_model-00026-of-00034.bin",
|
260 |
+
"transformer.h.23.mlp.c_proj.weight": "pytorch_model-00026-of-00034.bin",
|
261 |
+
"transformer.h.24.attn.attention.bias": "pytorch_model-00026-of-00034.bin",
|
262 |
+
"transformer.h.24.attn.attention.k_proj.weight": "pytorch_model-00026-of-00034.bin",
|
263 |
+
"transformer.h.24.attn.attention.masked_bias": "pytorch_model-00026-of-00034.bin",
|
264 |
+
"transformer.h.24.attn.attention.out_proj.bias": "pytorch_model-00026-of-00034.bin",
|
265 |
+
"transformer.h.24.attn.attention.out_proj.weight": "pytorch_model-00026-of-00034.bin",
|
266 |
+
"transformer.h.24.attn.attention.q_proj.weight": "pytorch_model-00026-of-00034.bin",
|
267 |
+
"transformer.h.24.attn.attention.v_proj.weight": "pytorch_model-00026-of-00034.bin",
|
268 |
+
"transformer.h.24.ln_1.bias": "pytorch_model-00026-of-00034.bin",
|
269 |
+
"transformer.h.24.ln_1.weight": "pytorch_model-00026-of-00034.bin",
|
270 |
+
"transformer.h.24.ln_2.bias": "pytorch_model-00026-of-00034.bin",
|
271 |
+
"transformer.h.24.ln_2.weight": "pytorch_model-00026-of-00034.bin",
|
272 |
+
"transformer.h.24.mlp.c_fc.bias": "pytorch_model-00027-of-00034.bin",
|
273 |
+
"transformer.h.24.mlp.c_fc.weight": "pytorch_model-00027-of-00034.bin",
|
274 |
+
"transformer.h.24.mlp.c_proj.bias": "pytorch_model-00027-of-00034.bin",
|
275 |
+
"transformer.h.24.mlp.c_proj.weight": "pytorch_model-00027-of-00034.bin",
|
276 |
+
"transformer.h.25.attn.attention.bias": "pytorch_model-00027-of-00034.bin",
|
277 |
+
"transformer.h.25.attn.attention.k_proj.weight": "pytorch_model-00027-of-00034.bin",
|
278 |
+
"transformer.h.25.attn.attention.masked_bias": "pytorch_model-00027-of-00034.bin",
|
279 |
+
"transformer.h.25.attn.attention.out_proj.bias": "pytorch_model-00027-of-00034.bin",
|
280 |
+
"transformer.h.25.attn.attention.out_proj.weight": "pytorch_model-00027-of-00034.bin",
|
281 |
+
"transformer.h.25.attn.attention.q_proj.weight": "pytorch_model-00027-of-00034.bin",
|
282 |
+
"transformer.h.25.attn.attention.v_proj.weight": "pytorch_model-00027-of-00034.bin",
|
283 |
+
"transformer.h.25.ln_1.bias": "pytorch_model-00027-of-00034.bin",
|
284 |
+
"transformer.h.25.ln_1.weight": "pytorch_model-00027-of-00034.bin",
|
285 |
+
"transformer.h.25.ln_2.bias": "pytorch_model-00027-of-00034.bin",
|
286 |
+
"transformer.h.25.ln_2.weight": "pytorch_model-00027-of-00034.bin",
|
287 |
+
"transformer.h.25.mlp.c_fc.bias": "pytorch_model-00028-of-00034.bin",
|
288 |
+
"transformer.h.25.mlp.c_fc.weight": "pytorch_model-00028-of-00034.bin",
|
289 |
+
"transformer.h.25.mlp.c_proj.bias": "pytorch_model-00028-of-00034.bin",
|
290 |
+
"transformer.h.25.mlp.c_proj.weight": "pytorch_model-00028-of-00034.bin",
|
291 |
+
"transformer.h.26.attn.attention.bias": "pytorch_model-00028-of-00034.bin",
|
292 |
+
"transformer.h.26.attn.attention.k_proj.weight": "pytorch_model-00028-of-00034.bin",
|
293 |
+
"transformer.h.26.attn.attention.masked_bias": "pytorch_model-00028-of-00034.bin",
|
294 |
+
"transformer.h.26.attn.attention.out_proj.bias": "pytorch_model-00028-of-00034.bin",
|
295 |
+
"transformer.h.26.attn.attention.out_proj.weight": "pytorch_model-00028-of-00034.bin",
|
296 |
+
"transformer.h.26.attn.attention.q_proj.weight": "pytorch_model-00028-of-00034.bin",
|
297 |
+
"transformer.h.26.attn.attention.v_proj.weight": "pytorch_model-00028-of-00034.bin",
|
298 |
+
"transformer.h.26.ln_1.bias": "pytorch_model-00028-of-00034.bin",
|
299 |
+
"transformer.h.26.ln_1.weight": "pytorch_model-00028-of-00034.bin",
|
300 |
+
"transformer.h.26.ln_2.bias": "pytorch_model-00028-of-00034.bin",
|
301 |
+
"transformer.h.26.ln_2.weight": "pytorch_model-00028-of-00034.bin",
|
302 |
+
"transformer.h.26.mlp.c_fc.bias": "pytorch_model-00029-of-00034.bin",
|
303 |
+
"transformer.h.26.mlp.c_fc.weight": "pytorch_model-00029-of-00034.bin",
|
304 |
+
"transformer.h.26.mlp.c_proj.bias": "pytorch_model-00029-of-00034.bin",
|
305 |
+
"transformer.h.26.mlp.c_proj.weight": "pytorch_model-00029-of-00034.bin",
|
306 |
+
"transformer.h.27.attn.attention.bias": "pytorch_model-00029-of-00034.bin",
|
307 |
+
"transformer.h.27.attn.attention.k_proj.weight": "pytorch_model-00029-of-00034.bin",
|
308 |
+
"transformer.h.27.attn.attention.masked_bias": "pytorch_model-00029-of-00034.bin",
|
309 |
+
"transformer.h.27.attn.attention.out_proj.bias": "pytorch_model-00029-of-00034.bin",
|
310 |
+
"transformer.h.27.attn.attention.out_proj.weight": "pytorch_model-00029-of-00034.bin",
|
311 |
+
"transformer.h.27.attn.attention.q_proj.weight": "pytorch_model-00029-of-00034.bin",
|
312 |
+
"transformer.h.27.attn.attention.v_proj.weight": "pytorch_model-00029-of-00034.bin",
|
313 |
+
"transformer.h.27.ln_1.bias": "pytorch_model-00029-of-00034.bin",
|
314 |
+
"transformer.h.27.ln_1.weight": "pytorch_model-00029-of-00034.bin",
|
315 |
+
"transformer.h.27.ln_2.bias": "pytorch_model-00029-of-00034.bin",
|
316 |
+
"transformer.h.27.ln_2.weight": "pytorch_model-00029-of-00034.bin",
|
317 |
+
"transformer.h.27.mlp.c_fc.bias": "pytorch_model-00030-of-00034.bin",
|
318 |
+
"transformer.h.27.mlp.c_fc.weight": "pytorch_model-00030-of-00034.bin",
|
319 |
+
"transformer.h.27.mlp.c_proj.bias": "pytorch_model-00030-of-00034.bin",
|
320 |
+
"transformer.h.27.mlp.c_proj.weight": "pytorch_model-00030-of-00034.bin",
|
321 |
+
"transformer.h.28.attn.attention.bias": "pytorch_model-00030-of-00034.bin",
|
322 |
+
"transformer.h.28.attn.attention.k_proj.weight": "pytorch_model-00030-of-00034.bin",
|
323 |
+
"transformer.h.28.attn.attention.masked_bias": "pytorch_model-00030-of-00034.bin",
|
324 |
+
"transformer.h.28.attn.attention.out_proj.bias": "pytorch_model-00030-of-00034.bin",
|
325 |
+
"transformer.h.28.attn.attention.out_proj.weight": "pytorch_model-00030-of-00034.bin",
|
326 |
+
"transformer.h.28.attn.attention.q_proj.weight": "pytorch_model-00030-of-00034.bin",
|
327 |
+
"transformer.h.28.attn.attention.v_proj.weight": "pytorch_model-00030-of-00034.bin",
|
328 |
+
"transformer.h.28.ln_1.bias": "pytorch_model-00030-of-00034.bin",
|
329 |
+
"transformer.h.28.ln_1.weight": "pytorch_model-00030-of-00034.bin",
|
330 |
+
"transformer.h.28.ln_2.bias": "pytorch_model-00030-of-00034.bin",
|
331 |
+
"transformer.h.28.ln_2.weight": "pytorch_model-00030-of-00034.bin",
|
332 |
+
"transformer.h.28.mlp.c_fc.bias": "pytorch_model-00031-of-00034.bin",
|
333 |
+
"transformer.h.28.mlp.c_fc.weight": "pytorch_model-00031-of-00034.bin",
|
334 |
+
"transformer.h.28.mlp.c_proj.bias": "pytorch_model-00031-of-00034.bin",
|
335 |
+
"transformer.h.28.mlp.c_proj.weight": "pytorch_model-00031-of-00034.bin",
|
336 |
+
"transformer.h.29.attn.attention.bias": "pytorch_model-00031-of-00034.bin",
|
337 |
+
"transformer.h.29.attn.attention.k_proj.weight": "pytorch_model-00031-of-00034.bin",
|
338 |
+
"transformer.h.29.attn.attention.masked_bias": "pytorch_model-00031-of-00034.bin",
|
339 |
+
"transformer.h.29.attn.attention.out_proj.bias": "pytorch_model-00031-of-00034.bin",
|
340 |
+
"transformer.h.29.attn.attention.out_proj.weight": "pytorch_model-00031-of-00034.bin",
|
341 |
+
"transformer.h.29.attn.attention.q_proj.weight": "pytorch_model-00031-of-00034.bin",
|
342 |
+
"transformer.h.29.attn.attention.v_proj.weight": "pytorch_model-00031-of-00034.bin",
|
343 |
+
"transformer.h.29.ln_1.bias": "pytorch_model-00031-of-00034.bin",
|
344 |
+
"transformer.h.29.ln_1.weight": "pytorch_model-00031-of-00034.bin",
|
345 |
+
"transformer.h.29.ln_2.bias": "pytorch_model-00031-of-00034.bin",
|
346 |
+
"transformer.h.29.ln_2.weight": "pytorch_model-00031-of-00034.bin",
|
347 |
+
"transformer.h.29.mlp.c_fc.bias": "pytorch_model-00032-of-00034.bin",
|
348 |
+
"transformer.h.29.mlp.c_fc.weight": "pytorch_model-00032-of-00034.bin",
|
349 |
+
"transformer.h.29.mlp.c_proj.bias": "pytorch_model-00032-of-00034.bin",
|
350 |
+
"transformer.h.29.mlp.c_proj.weight": "pytorch_model-00032-of-00034.bin",
|
351 |
+
"transformer.h.3.attn.attention.bias": "pytorch_model-00005-of-00034.bin",
|
352 |
+
"transformer.h.3.attn.attention.k_proj.weight": "pytorch_model-00005-of-00034.bin",
|
353 |
+
"transformer.h.3.attn.attention.masked_bias": "pytorch_model-00005-of-00034.bin",
|
354 |
+
"transformer.h.3.attn.attention.out_proj.bias": "pytorch_model-00005-of-00034.bin",
|
355 |
+
"transformer.h.3.attn.attention.out_proj.weight": "pytorch_model-00005-of-00034.bin",
|
356 |
+
"transformer.h.3.attn.attention.q_proj.weight": "pytorch_model-00005-of-00034.bin",
|
357 |
+
"transformer.h.3.attn.attention.v_proj.weight": "pytorch_model-00005-of-00034.bin",
|
358 |
+
"transformer.h.3.ln_1.bias": "pytorch_model-00005-of-00034.bin",
|
359 |
+
"transformer.h.3.ln_1.weight": "pytorch_model-00005-of-00034.bin",
|
360 |
+
"transformer.h.3.ln_2.bias": "pytorch_model-00005-of-00034.bin",
|
361 |
+
"transformer.h.3.ln_2.weight": "pytorch_model-00005-of-00034.bin",
|
362 |
+
"transformer.h.3.mlp.c_fc.bias": "pytorch_model-00006-of-00034.bin",
|
363 |
+
"transformer.h.3.mlp.c_fc.weight": "pytorch_model-00006-of-00034.bin",
|
364 |
+
"transformer.h.3.mlp.c_proj.bias": "pytorch_model-00006-of-00034.bin",
|
365 |
+
"transformer.h.3.mlp.c_proj.weight": "pytorch_model-00006-of-00034.bin",
|
366 |
+
"transformer.h.30.attn.attention.bias": "pytorch_model-00032-of-00034.bin",
|
367 |
+
"transformer.h.30.attn.attention.k_proj.weight": "pytorch_model-00032-of-00034.bin",
|
368 |
+
"transformer.h.30.attn.attention.masked_bias": "pytorch_model-00032-of-00034.bin",
|
369 |
+
"transformer.h.30.attn.attention.out_proj.bias": "pytorch_model-00032-of-00034.bin",
|
370 |
+
"transformer.h.30.attn.attention.out_proj.weight": "pytorch_model-00032-of-00034.bin",
|
371 |
+
"transformer.h.30.attn.attention.q_proj.weight": "pytorch_model-00032-of-00034.bin",
|
372 |
+
"transformer.h.30.attn.attention.v_proj.weight": "pytorch_model-00032-of-00034.bin",
|
373 |
+
"transformer.h.30.ln_1.bias": "pytorch_model-00032-of-00034.bin",
|
374 |
+
"transformer.h.30.ln_1.weight": "pytorch_model-00032-of-00034.bin",
|
375 |
+
"transformer.h.30.ln_2.bias": "pytorch_model-00032-of-00034.bin",
|
376 |
+
"transformer.h.30.ln_2.weight": "pytorch_model-00032-of-00034.bin",
|
377 |
+
"transformer.h.30.mlp.c_fc.bias": "pytorch_model-00033-of-00034.bin",
|
378 |
+
"transformer.h.30.mlp.c_fc.weight": "pytorch_model-00033-of-00034.bin",
|
379 |
+
"transformer.h.30.mlp.c_proj.bias": "pytorch_model-00033-of-00034.bin",
|
380 |
+
"transformer.h.30.mlp.c_proj.weight": "pytorch_model-00033-of-00034.bin",
|
381 |
+
"transformer.h.31.attn.attention.bias": "pytorch_model-00033-of-00034.bin",
|
382 |
+
"transformer.h.31.attn.attention.k_proj.weight": "pytorch_model-00033-of-00034.bin",
|
383 |
+
"transformer.h.31.attn.attention.masked_bias": "pytorch_model-00033-of-00034.bin",
|
384 |
+
"transformer.h.31.attn.attention.out_proj.bias": "pytorch_model-00033-of-00034.bin",
|
385 |
+
"transformer.h.31.attn.attention.out_proj.weight": "pytorch_model-00033-of-00034.bin",
|
386 |
+
"transformer.h.31.attn.attention.q_proj.weight": "pytorch_model-00033-of-00034.bin",
|
387 |
+
"transformer.h.31.attn.attention.v_proj.weight": "pytorch_model-00033-of-00034.bin",
|
388 |
+
"transformer.h.31.ln_1.bias": "pytorch_model-00033-of-00034.bin",
|
389 |
+
"transformer.h.31.ln_1.weight": "pytorch_model-00033-of-00034.bin",
|
390 |
+
"transformer.h.31.ln_2.bias": "pytorch_model-00033-of-00034.bin",
|
391 |
+
"transformer.h.31.ln_2.weight": "pytorch_model-00033-of-00034.bin",
|
392 |
+
"transformer.h.31.mlp.c_fc.bias": "pytorch_model-00034-of-00034.bin",
|
393 |
+
"transformer.h.31.mlp.c_fc.weight": "pytorch_model-00034-of-00034.bin",
|
394 |
+
"transformer.h.31.mlp.c_proj.bias": "pytorch_model-00034-of-00034.bin",
|
395 |
+
"transformer.h.31.mlp.c_proj.weight": "pytorch_model-00034-of-00034.bin",
|
396 |
+
"transformer.h.4.attn.attention.bias": "pytorch_model-00006-of-00034.bin",
|
397 |
+
"transformer.h.4.attn.attention.k_proj.weight": "pytorch_model-00006-of-00034.bin",
|
398 |
+
"transformer.h.4.attn.attention.masked_bias": "pytorch_model-00006-of-00034.bin",
|
399 |
+
"transformer.h.4.attn.attention.out_proj.bias": "pytorch_model-00006-of-00034.bin",
|
400 |
+
"transformer.h.4.attn.attention.out_proj.weight": "pytorch_model-00006-of-00034.bin",
|
401 |
+
"transformer.h.4.attn.attention.q_proj.weight": "pytorch_model-00006-of-00034.bin",
|
402 |
+
"transformer.h.4.attn.attention.v_proj.weight": "pytorch_model-00006-of-00034.bin",
|
403 |
+
"transformer.h.4.ln_1.bias": "pytorch_model-00006-of-00034.bin",
|
404 |
+
"transformer.h.4.ln_1.weight": "pytorch_model-00006-of-00034.bin",
|
405 |
+
"transformer.h.4.ln_2.bias": "pytorch_model-00006-of-00034.bin",
|
406 |
+
"transformer.h.4.ln_2.weight": "pytorch_model-00006-of-00034.bin",
|
407 |
+
"transformer.h.4.mlp.c_fc.bias": "pytorch_model-00007-of-00034.bin",
|
408 |
+
"transformer.h.4.mlp.c_fc.weight": "pytorch_model-00007-of-00034.bin",
|
409 |
+
"transformer.h.4.mlp.c_proj.bias": "pytorch_model-00007-of-00034.bin",
|
410 |
+
"transformer.h.4.mlp.c_proj.weight": "pytorch_model-00007-of-00034.bin",
|
411 |
+
"transformer.h.5.attn.attention.bias": "pytorch_model-00007-of-00034.bin",
|
412 |
+
"transformer.h.5.attn.attention.k_proj.weight": "pytorch_model-00007-of-00034.bin",
|
413 |
+
"transformer.h.5.attn.attention.masked_bias": "pytorch_model-00007-of-00034.bin",
|
414 |
+
"transformer.h.5.attn.attention.out_proj.bias": "pytorch_model-00007-of-00034.bin",
|
415 |
+
"transformer.h.5.attn.attention.out_proj.weight": "pytorch_model-00007-of-00034.bin",
|
416 |
+
"transformer.h.5.attn.attention.q_proj.weight": "pytorch_model-00007-of-00034.bin",
|
417 |
+
"transformer.h.5.attn.attention.v_proj.weight": "pytorch_model-00007-of-00034.bin",
|
418 |
+
"transformer.h.5.ln_1.bias": "pytorch_model-00007-of-00034.bin",
|
419 |
+
"transformer.h.5.ln_1.weight": "pytorch_model-00007-of-00034.bin",
|
420 |
+
"transformer.h.5.ln_2.bias": "pytorch_model-00007-of-00034.bin",
|
421 |
+
"transformer.h.5.ln_2.weight": "pytorch_model-00007-of-00034.bin",
|
422 |
+
"transformer.h.5.mlp.c_fc.bias": "pytorch_model-00008-of-00034.bin",
|
423 |
+
"transformer.h.5.mlp.c_fc.weight": "pytorch_model-00008-of-00034.bin",
|
424 |
+
"transformer.h.5.mlp.c_proj.bias": "pytorch_model-00008-of-00034.bin",
|
425 |
+
"transformer.h.5.mlp.c_proj.weight": "pytorch_model-00008-of-00034.bin",
|
426 |
+
"transformer.h.6.attn.attention.bias": "pytorch_model-00008-of-00034.bin",
|
427 |
+
"transformer.h.6.attn.attention.k_proj.weight": "pytorch_model-00008-of-00034.bin",
|
428 |
+
"transformer.h.6.attn.attention.masked_bias": "pytorch_model-00008-of-00034.bin",
|
429 |
+
"transformer.h.6.attn.attention.out_proj.bias": "pytorch_model-00008-of-00034.bin",
|
430 |
+
"transformer.h.6.attn.attention.out_proj.weight": "pytorch_model-00008-of-00034.bin",
|
431 |
+
"transformer.h.6.attn.attention.q_proj.weight": "pytorch_model-00008-of-00034.bin",
|
432 |
+
"transformer.h.6.attn.attention.v_proj.weight": "pytorch_model-00008-of-00034.bin",
|
433 |
+
"transformer.h.6.ln_1.bias": "pytorch_model-00008-of-00034.bin",
|
434 |
+
"transformer.h.6.ln_1.weight": "pytorch_model-00008-of-00034.bin",
|
435 |
+
"transformer.h.6.ln_2.bias": "pytorch_model-00008-of-00034.bin",
|
436 |
+
"transformer.h.6.ln_2.weight": "pytorch_model-00008-of-00034.bin",
|
437 |
+
"transformer.h.6.mlp.c_fc.bias": "pytorch_model-00009-of-00034.bin",
|
438 |
+
"transformer.h.6.mlp.c_fc.weight": "pytorch_model-00009-of-00034.bin",
|
439 |
+
"transformer.h.6.mlp.c_proj.bias": "pytorch_model-00009-of-00034.bin",
|
440 |
+
"transformer.h.6.mlp.c_proj.weight": "pytorch_model-00009-of-00034.bin",
|
441 |
+
"transformer.h.7.attn.attention.bias": "pytorch_model-00009-of-00034.bin",
|
442 |
+
"transformer.h.7.attn.attention.k_proj.weight": "pytorch_model-00009-of-00034.bin",
|
443 |
+
"transformer.h.7.attn.attention.masked_bias": "pytorch_model-00009-of-00034.bin",
|
444 |
+
"transformer.h.7.attn.attention.out_proj.bias": "pytorch_model-00009-of-00034.bin",
|
445 |
+
"transformer.h.7.attn.attention.out_proj.weight": "pytorch_model-00009-of-00034.bin",
|
446 |
+
"transformer.h.7.attn.attention.q_proj.weight": "pytorch_model-00009-of-00034.bin",
|
447 |
+
"transformer.h.7.attn.attention.v_proj.weight": "pytorch_model-00009-of-00034.bin",
|
448 |
+
"transformer.h.7.ln_1.bias": "pytorch_model-00009-of-00034.bin",
|
449 |
+
"transformer.h.7.ln_1.weight": "pytorch_model-00009-of-00034.bin",
|
450 |
+
"transformer.h.7.ln_2.bias": "pytorch_model-00009-of-00034.bin",
|
451 |
+
"transformer.h.7.ln_2.weight": "pytorch_model-00009-of-00034.bin",
|
452 |
+
"transformer.h.7.mlp.c_fc.bias": "pytorch_model-00010-of-00034.bin",
|
453 |
+
"transformer.h.7.mlp.c_fc.weight": "pytorch_model-00010-of-00034.bin",
|
454 |
+
"transformer.h.7.mlp.c_proj.bias": "pytorch_model-00010-of-00034.bin",
|
455 |
+
"transformer.h.7.mlp.c_proj.weight": "pytorch_model-00010-of-00034.bin",
|
456 |
+
"transformer.h.8.attn.attention.bias": "pytorch_model-00010-of-00034.bin",
|
457 |
+
"transformer.h.8.attn.attention.k_proj.weight": "pytorch_model-00010-of-00034.bin",
|
458 |
+
"transformer.h.8.attn.attention.masked_bias": "pytorch_model-00010-of-00034.bin",
|
459 |
+
"transformer.h.8.attn.attention.out_proj.bias": "pytorch_model-00010-of-00034.bin",
|
460 |
+
"transformer.h.8.attn.attention.out_proj.weight": "pytorch_model-00010-of-00034.bin",
|
461 |
+
"transformer.h.8.attn.attention.q_proj.weight": "pytorch_model-00010-of-00034.bin",
|
462 |
+
"transformer.h.8.attn.attention.v_proj.weight": "pytorch_model-00010-of-00034.bin",
|
463 |
+
"transformer.h.8.ln_1.bias": "pytorch_model-00010-of-00034.bin",
|
464 |
+
"transformer.h.8.ln_1.weight": "pytorch_model-00010-of-00034.bin",
|
465 |
+
"transformer.h.8.ln_2.bias": "pytorch_model-00010-of-00034.bin",
|
466 |
+
"transformer.h.8.ln_2.weight": "pytorch_model-00010-of-00034.bin",
|
467 |
+
"transformer.h.8.mlp.c_fc.bias": "pytorch_model-00011-of-00034.bin",
|
468 |
+
"transformer.h.8.mlp.c_fc.weight": "pytorch_model-00011-of-00034.bin",
|
469 |
+
"transformer.h.8.mlp.c_proj.bias": "pytorch_model-00011-of-00034.bin",
|
470 |
+
"transformer.h.8.mlp.c_proj.weight": "pytorch_model-00011-of-00034.bin",
|
471 |
+
"transformer.h.9.attn.attention.bias": "pytorch_model-00011-of-00034.bin",
|
472 |
+
"transformer.h.9.attn.attention.k_proj.weight": "pytorch_model-00011-of-00034.bin",
|
473 |
+
"transformer.h.9.attn.attention.masked_bias": "pytorch_model-00011-of-00034.bin",
|
474 |
+
"transformer.h.9.attn.attention.out_proj.bias": "pytorch_model-00011-of-00034.bin",
|
475 |
+
"transformer.h.9.attn.attention.out_proj.weight": "pytorch_model-00011-of-00034.bin",
|
476 |
+
"transformer.h.9.attn.attention.q_proj.weight": "pytorch_model-00011-of-00034.bin",
|
477 |
+
"transformer.h.9.attn.attention.v_proj.weight": "pytorch_model-00011-of-00034.bin",
|
478 |
+
"transformer.h.9.ln_1.bias": "pytorch_model-00011-of-00034.bin",
|
479 |
+
"transformer.h.9.ln_1.weight": "pytorch_model-00011-of-00034.bin",
|
480 |
+
"transformer.h.9.ln_2.bias": "pytorch_model-00011-of-00034.bin",
|
481 |
+
"transformer.h.9.ln_2.weight": "pytorch_model-00011-of-00034.bin",
|
482 |
+
"transformer.h.9.mlp.c_fc.bias": "pytorch_model-00012-of-00034.bin",
|
483 |
+
"transformer.h.9.mlp.c_fc.weight": "pytorch_model-00012-of-00034.bin",
|
484 |
+
"transformer.h.9.mlp.c_proj.bias": "pytorch_model-00012-of-00034.bin",
|
485 |
+
"transformer.h.9.mlp.c_proj.weight": "pytorch_model-00012-of-00034.bin",
|
486 |
+
"transformer.ln_f.bias": "pytorch_model-00034-of-00034.bin",
|
487 |
+
"transformer.ln_f.weight": "pytorch_model-00034-of-00034.bin",
|
488 |
+
"transformer.wpe.weight": "pytorch_model-00003-of-00034.bin",
|
489 |
+
"transformer.wte.weight": "pytorch_model-00002-of-00034.bin"
|
490 |
+
}
|
491 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"unk_token": "<|endoftext|>"
|
5 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"eos_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"errors": "replace",
|
21 |
+
"model_max_length": 2048,
|
22 |
+
"pad_token": null,
|
23 |
+
"special_tokens_map_file": null,
|
24 |
+
"tokenizer_class": "GPT2Tokenizer",
|
25 |
+
"unk_token": {
|
26 |
+
"__type": "AddedToken",
|
27 |
+
"content": "<|endoftext|>",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": true,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
}
|
33 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|