Upload 45 files
Browse files- config.json +26 -0
- pytorch_model-00001-of-00040.bin +3 -0
- pytorch_model-00002-of-00040.bin +3 -0
- pytorch_model-00003-of-00040.bin +3 -0
- pytorch_model-00004-of-00040.bin +3 -0
- pytorch_model-00005-of-00040.bin +3 -0
- pytorch_model-00006-of-00040.bin +3 -0
- pytorch_model-00007-of-00040.bin +3 -0
- pytorch_model-00008-of-00040.bin +3 -0
- pytorch_model-00009-of-00040.bin +3 -0
- pytorch_model-00010-of-00040.bin +3 -0
- pytorch_model-00011-of-00040.bin +3 -0
- pytorch_model-00012-of-00040.bin +3 -0
- pytorch_model-00013-of-00040.bin +3 -0
- pytorch_model-00014-of-00040.bin +3 -0
- pytorch_model-00015-of-00040.bin +3 -0
- pytorch_model-00016-of-00040.bin +3 -0
- pytorch_model-00017-of-00040.bin +3 -0
- pytorch_model-00018-of-00040.bin +3 -0
- pytorch_model-00019-of-00040.bin +3 -0
- pytorch_model-00020-of-00040.bin +3 -0
- pytorch_model-00021-of-00040.bin +3 -0
- pytorch_model-00022-of-00040.bin +3 -0
- pytorch_model-00023-of-00040.bin +3 -0
- pytorch_model-00024-of-00040.bin +3 -0
- pytorch_model-00025-of-00040.bin +3 -0
- pytorch_model-00026-of-00040.bin +3 -0
- pytorch_model-00027-of-00040.bin +3 -0
- pytorch_model-00028-of-00040.bin +3 -0
- pytorch_model-00029-of-00040.bin +3 -0
- pytorch_model-00030-of-00040.bin +3 -0
- pytorch_model-00031-of-00040.bin +3 -0
- pytorch_model-00032-of-00040.bin +3 -0
- pytorch_model-00033-of-00040.bin +3 -0
- pytorch_model-00034-of-00040.bin +3 -0
- pytorch_model-00035-of-00040.bin +3 -0
- pytorch_model-00036-of-00040.bin +3 -0
- pytorch_model-00037-of-00040.bin +3 -0
- pytorch_model-00038-of-00040.bin +3 -0
- pytorch_model-00039-of-00040.bin +3 -0
- pytorch_model-00040-of-00040.bin +3 -0
- pytorch_model.bin.index.json +298 -0
- special_tokens_map.json +5 -0
- tokenizer.model +3 -0
- tokenizer_config.json +33 -0
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/content/drive/MyDrive/BaseModel/openthaigpt-merge-lora-llama-2-7B-3470k",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 4096,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 11008,
|
12 |
+
"max_position_embeddings": 4096,
|
13 |
+
"model_type": "llama",
|
14 |
+
"num_attention_heads": 32,
|
15 |
+
"num_hidden_layers": 32,
|
16 |
+
"num_key_value_heads": 32,
|
17 |
+
"pad_token_id": 0,
|
18 |
+
"pretraining_tp": 1,
|
19 |
+
"rms_norm_eps": 1e-05,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "float16",
|
23 |
+
"transformers_version": "4.32.1",
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 56554
|
26 |
+
}
|
pytorch_model-00001-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc127e06b839c2a4a44da8b0fba15afddbba4b495480dc33a819d7909c69508b
|
3 |
+
size 463291306
|
pytorch_model-00002-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50a43f138b5138ee495db6c6a8d1a6e899621ac6b8c2562b8c6ca1565900731b
|
3 |
+
size 314575359
|
pytorch_model-00003-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2e7a1e1f4e8e8ed9fd778d06dec1092c160c56b08e9ea5d3ef1c8cc31a7edcc
|
3 |
+
size 314592353
|
pytorch_model-00004-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e746f478328b512e1f9084b43479e77cf55e26a3d929cc2825ece8ca089f8b3
|
3 |
+
size 314592353
|
pytorch_model-00005-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c55377e3560a5e0f4c341de4d013d7648a42647bcffef489c9ee9dc884076640
|
3 |
+
size 371215457
|
pytorch_model-00006-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f4ce99e56b416eeb2fbc087fffdb5031369a62589ef58870c49756047267fd6
|
3 |
+
size 371215457
|
pytorch_model-00007-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4ff143d760fedfc72e9fa81bcf52e07baeddb2dcfd24b9cd399238618d843bc
|
3 |
+
size 371215457
|
pytorch_model-00008-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c54b2573a7375edda74c377312e3a0cfe20621d7eb49b4a62f4941ae1a6a798
|
3 |
+
size 371215457
|
pytorch_model-00009-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5048d0b3bc8be19d71a16887f919703915e60e304acbdccf0c45dab894cc06ce
|
3 |
+
size 314575359
|
pytorch_model-00010-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51e4d61cf949bb19621e1b25203f180e150ad6707b96a9310e0809405ae425bb
|
3 |
+
size 314592353
|
pytorch_model-00011-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb539a41853ecc8d210d8d0a9a2ca4c0abc09e2d5d3cc957eb986274f780b2e8
|
3 |
+
size 314592353
|
pytorch_model-00012-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:498b9031ef28fdd7135a3df1d63079c64632955898656f9f97b73ef73939183b
|
3 |
+
size 371215457
|
pytorch_model-00013-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70a2b94414a753c8d877a346456dbb248c6b77e6642f6ac00ff3aff6018fa5a4
|
3 |
+
size 371215457
|
pytorch_model-00014-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3ca85fbcfae9f45c72879c78c1b3c03a306b972b698d3b39f0f386fbf5f01df
|
3 |
+
size 371215521
|
pytorch_model-00015-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d6880cb364be0a43594963d4626dacd991184f7b066ce3e3d3abf5831d15076
|
3 |
+
size 371215521
|
pytorch_model-00016-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c973481c26a7087dee4730f5a5d82aad01cd8cced06a8ae9bfb6e017a9ac65c2
|
3 |
+
size 314575359
|
pytorch_model-00017-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3279d0fc00f1a8b2075ab1ee26dff27c80e092aea4bc263e39103df8ec168b92
|
3 |
+
size 314592417
|
pytorch_model-00018-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:361c98a67636ce056094dda95da974f60fb948b24396d21a63c51cf26bb962ae
|
3 |
+
size 314592417
|
pytorch_model-00019-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10fbfbdf88f67a3ac982011241e7ea87958432f39084f8e2d5b9d8542eb228d4
|
3 |
+
size 371215521
|
pytorch_model-00020-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a37511e5c1d2dbc3cf5c5731ffc25578fa7078ebf61c5c537a499485a4fec137
|
3 |
+
size 371215521
|
pytorch_model-00021-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5d712576d2f8d3fd4c38e2189600a5b3003ffaeb04141f7a8fc4e3548a92a9d
|
3 |
+
size 371215521
|
pytorch_model-00022-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1fc1cfb3b77849e71f585af9b4778d6905b269953aaf01d8c211c18ea832c56c
|
3 |
+
size 371215521
|
pytorch_model-00023-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c918804b27011555a045a772f2e6e9f90a576c4790c806f70395a9699bc2d7c0
|
3 |
+
size 314575359
|
pytorch_model-00024-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0edefbffda1d2445063662876f03c067fa2eb2dc274918a4275eeed930f68778
|
3 |
+
size 314592417
|
pytorch_model-00025-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba661b95f2ce0de34209dacac06f287672b8b39b1846b81e1a37ac20fbd1a07f
|
3 |
+
size 314592417
|
pytorch_model-00026-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9aabdc2c2df2e84d48c32713816fce9cbfe9965a171dfd8df9519de4306f8006
|
3 |
+
size 371215521
|
pytorch_model-00027-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7acdfae864f985432575db0302f74fbb088815e6a60ddfaa375c4e33bdc95c2
|
3 |
+
size 371215521
|
pytorch_model-00028-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:725110efb05c033b6de9809e33d02ec2cd66a0283af61074cd70673f8860e03a
|
3 |
+
size 371215521
|
pytorch_model-00029-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cb92d4380df5b54b717ee5add98d3ece1646f9d3c52a4863f294b54b5e3ad85
|
3 |
+
size 371215521
|
pytorch_model-00030-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ddb95c95b75ab781230dd04e538dfe24b7f014b0820d7574453ab91aad27fd8e
|
3 |
+
size 314575359
|
pytorch_model-00031-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:584d1a276b0172ce4c292872288b9eb1ee65d2a315a1210fb0f866879b279998
|
3 |
+
size 314592417
|
pytorch_model-00032-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e8ea28a26afd41bd5a2489217d220e2a2cacda43d17852bde12c4366b22db95
|
3 |
+
size 314592417
|
pytorch_model-00033-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0b70f3816c0f3a8d0117fcd84753f83ad85a79d4d89016ab111b05ac91f6dc4
|
3 |
+
size 371215521
|
pytorch_model-00034-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39e84f00c0a992710de1eea04d0748ac8bb12c90833d574856e9079708be4542
|
3 |
+
size 371215521
|
pytorch_model-00035-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca162ab90e457dde3c33d8a5febbe2c5a437d17ca6ffd1413d1b37a36e4fefa0
|
3 |
+
size 371215521
|
pytorch_model-00036-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62266deceba96804ea3100122224038e83d6c1e63118050b132204bf6162667e
|
3 |
+
size 371215521
|
pytorch_model-00037-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f738780924e88618979742608b16b4fee17479c76c803aa58f905e266d35760
|
3 |
+
size 314575359
|
pytorch_model-00038-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f55a5fe8e52deaa4604201e10ea04629fce1837c1b62adf2e7f512d0bd6c4034
|
3 |
+
size 314592417
|
pytorch_model-00039-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22fb2a440632e347b00f318bf1a6d8d6a01463df818a782982bbb68e86190eba
|
3 |
+
size 180381870
|
pytorch_model-00040-of-00040.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:caade18dfbb0e15fe9b2f29d6b25b869c1dc403ce270a04966cc3401f07b0cf8
|
3 |
+
size 463291306
|
pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 13879123968
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "pytorch_model-00040-of-00040.bin",
|
7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00040.bin",
|
8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00003-of-00040.bin",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00003-of-00040.bin",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00040.bin",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00040.bin",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00003-of-00040.bin",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00002-of-00040.bin",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00002-of-00040.bin",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00002-of-00040.bin",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00002-of-00040.bin",
|
17 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00004-of-00040.bin",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00004-of-00040.bin",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00003-of-00040.bin",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00004-of-00040.bin",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00004-of-00040.bin",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00003-of-00040.bin",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00003-of-00040.bin",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00003-of-00040.bin",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00003-of-00040.bin",
|
26 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00014-of-00040.bin",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00014-of-00040.bin",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00014-of-00040.bin",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00014-of-00040.bin",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00014-of-00040.bin",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00013-of-00040.bin",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00014-of-00040.bin",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00013-of-00040.bin",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00014-of-00040.bin",
|
35 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00015-of-00040.bin",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00015-of-00040.bin",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00015-of-00040.bin",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00015-of-00040.bin",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00015-of-00040.bin",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00015-of-00040.bin",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00015-of-00040.bin",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00014-of-00040.bin",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00015-of-00040.bin",
|
44 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00017-of-00040.bin",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00017-of-00040.bin",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00016-of-00040.bin",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00016-of-00040.bin",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00017-of-00040.bin",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00016-of-00040.bin",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00016-of-00040.bin",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00016-of-00040.bin",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00016-of-00040.bin",
|
53 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00018-of-00040.bin",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00018-of-00040.bin",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00017-of-00040.bin",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00018-of-00040.bin",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00018-of-00040.bin",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00017-of-00040.bin",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00017-of-00040.bin",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00017-of-00040.bin",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00017-of-00040.bin",
|
62 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00019-of-00040.bin",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00019-of-00040.bin",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00019-of-00040.bin",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00019-of-00040.bin",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00019-of-00040.bin",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00018-of-00040.bin",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00018-of-00040.bin",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00018-of-00040.bin",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00018-of-00040.bin",
|
71 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00020-of-00040.bin",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00020-of-00040.bin",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00020-of-00040.bin",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00020-of-00040.bin",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00020-of-00040.bin",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00019-of-00040.bin",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00020-of-00040.bin",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00019-of-00040.bin",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00019-of-00040.bin",
|
80 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00021-of-00040.bin",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00021-of-00040.bin",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00021-of-00040.bin",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00021-of-00040.bin",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00021-of-00040.bin",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00020-of-00040.bin",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00021-of-00040.bin",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00020-of-00040.bin",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00021-of-00040.bin",
|
89 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00022-of-00040.bin",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00022-of-00040.bin",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00022-of-00040.bin",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00022-of-00040.bin",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00022-of-00040.bin",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00022-of-00040.bin",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00022-of-00040.bin",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00021-of-00040.bin",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00022-of-00040.bin",
|
98 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00024-of-00040.bin",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00024-of-00040.bin",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00023-of-00040.bin",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00023-of-00040.bin",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00024-of-00040.bin",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00023-of-00040.bin",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00023-of-00040.bin",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00023-of-00040.bin",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00023-of-00040.bin",
|
107 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00025-of-00040.bin",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00025-of-00040.bin",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00024-of-00040.bin",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00025-of-00040.bin",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00025-of-00040.bin",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00024-of-00040.bin",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00024-of-00040.bin",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00024-of-00040.bin",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00024-of-00040.bin",
|
116 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00005-of-00040.bin",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00005-of-00040.bin",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00005-of-00040.bin",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00005-of-00040.bin",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00005-of-00040.bin",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00004-of-00040.bin",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00004-of-00040.bin",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00004-of-00040.bin",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00004-of-00040.bin",
|
125 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00026-of-00040.bin",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00026-of-00040.bin",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00026-of-00040.bin",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00026-of-00040.bin",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00026-of-00040.bin",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00025-of-00040.bin",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00025-of-00040.bin",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00025-of-00040.bin",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00025-of-00040.bin",
|
134 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00027-of-00040.bin",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00027-of-00040.bin",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00027-of-00040.bin",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00027-of-00040.bin",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00027-of-00040.bin",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00026-of-00040.bin",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00027-of-00040.bin",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00026-of-00040.bin",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00026-of-00040.bin",
|
143 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00028-of-00040.bin",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00028-of-00040.bin",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00028-of-00040.bin",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00028-of-00040.bin",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00028-of-00040.bin",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00027-of-00040.bin",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00028-of-00040.bin",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00027-of-00040.bin",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00028-of-00040.bin",
|
152 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00029-of-00040.bin",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00029-of-00040.bin",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00029-of-00040.bin",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00029-of-00040.bin",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00029-of-00040.bin",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00029-of-00040.bin",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00029-of-00040.bin",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00028-of-00040.bin",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00029-of-00040.bin",
|
161 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00031-of-00040.bin",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00031-of-00040.bin",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00030-of-00040.bin",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00030-of-00040.bin",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00031-of-00040.bin",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00030-of-00040.bin",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00030-of-00040.bin",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00030-of-00040.bin",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00030-of-00040.bin",
|
170 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00032-of-00040.bin",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00032-of-00040.bin",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00031-of-00040.bin",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00032-of-00040.bin",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00032-of-00040.bin",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00031-of-00040.bin",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00031-of-00040.bin",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00031-of-00040.bin",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00031-of-00040.bin",
|
179 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00033-of-00040.bin",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00033-of-00040.bin",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00033-of-00040.bin",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00033-of-00040.bin",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00033-of-00040.bin",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00032-of-00040.bin",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00032-of-00040.bin",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00032-of-00040.bin",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00032-of-00040.bin",
|
188 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00034-of-00040.bin",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00034-of-00040.bin",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00034-of-00040.bin",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00034-of-00040.bin",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00034-of-00040.bin",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00033-of-00040.bin",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00034-of-00040.bin",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00033-of-00040.bin",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00033-of-00040.bin",
|
197 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00035-of-00040.bin",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00035-of-00040.bin",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00035-of-00040.bin",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00035-of-00040.bin",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00035-of-00040.bin",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00034-of-00040.bin",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00035-of-00040.bin",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00034-of-00040.bin",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00035-of-00040.bin",
|
206 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00036-of-00040.bin",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00036-of-00040.bin",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00036-of-00040.bin",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00036-of-00040.bin",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00036-of-00040.bin",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00036-of-00040.bin",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00036-of-00040.bin",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00035-of-00040.bin",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00036-of-00040.bin",
|
215 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00006-of-00040.bin",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00006-of-00040.bin",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00006-of-00040.bin",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00006-of-00040.bin",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00006-of-00040.bin",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00005-of-00040.bin",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00006-of-00040.bin",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00005-of-00040.bin",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00005-of-00040.bin",
|
224 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00038-of-00040.bin",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00038-of-00040.bin",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00037-of-00040.bin",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00037-of-00040.bin",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00038-of-00040.bin",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00037-of-00040.bin",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00037-of-00040.bin",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00037-of-00040.bin",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00037-of-00040.bin",
|
233 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00039-of-00040.bin",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00039-of-00040.bin",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00038-of-00040.bin",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00039-of-00040.bin",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00039-of-00040.bin",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00038-of-00040.bin",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00038-of-00040.bin",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00038-of-00040.bin",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00038-of-00040.bin",
|
242 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00007-of-00040.bin",
|
243 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00007-of-00040.bin",
|
244 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00007-of-00040.bin",
|
245 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00007-of-00040.bin",
|
246 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00007-of-00040.bin",
|
247 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00006-of-00040.bin",
|
248 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00007-of-00040.bin",
|
249 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00006-of-00040.bin",
|
250 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00007-of-00040.bin",
|
251 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00008-of-00040.bin",
|
252 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00008-of-00040.bin",
|
253 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00008-of-00040.bin",
|
254 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00008-of-00040.bin",
|
255 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00008-of-00040.bin",
|
256 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00008-of-00040.bin",
|
257 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00008-of-00040.bin",
|
258 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00007-of-00040.bin",
|
259 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00008-of-00040.bin",
|
260 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00010-of-00040.bin",
|
261 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00010-of-00040.bin",
|
262 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00009-of-00040.bin",
|
263 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00009-of-00040.bin",
|
264 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00010-of-00040.bin",
|
265 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00009-of-00040.bin",
|
266 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00009-of-00040.bin",
|
267 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00009-of-00040.bin",
|
268 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00009-of-00040.bin",
|
269 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00011-of-00040.bin",
|
270 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00011-of-00040.bin",
|
271 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00010-of-00040.bin",
|
272 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00011-of-00040.bin",
|
273 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00011-of-00040.bin",
|
274 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00010-of-00040.bin",
|
275 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00010-of-00040.bin",
|
276 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00010-of-00040.bin",
|
277 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00010-of-00040.bin",
|
278 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00012-of-00040.bin",
|
279 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00012-of-00040.bin",
|
280 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00012-of-00040.bin",
|
281 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00012-of-00040.bin",
|
282 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00012-of-00040.bin",
|
283 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00011-of-00040.bin",
|
284 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00011-of-00040.bin",
|
285 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00011-of-00040.bin",
|
286 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00011-of-00040.bin",
|
287 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00013-of-00040.bin",
|
288 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00013-of-00040.bin",
|
289 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00013-of-00040.bin",
|
290 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00013-of-00040.bin",
|
291 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00013-of-00040.bin",
|
292 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00012-of-00040.bin",
|
293 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00013-of-00040.bin",
|
294 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00012-of-00040.bin",
|
295 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00012-of-00040.bin",
|
296 |
+
"model.norm.weight": "pytorch_model-00039-of-00040.bin"
|
297 |
+
}
|
298 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d5981dd688587f9a3c627d7efcdcba36395bf0225a0d96dab25deca55ae02f4
|
3 |
+
size 1168686
|
tokenizer_config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": false,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"model_max_length": 1000000000000000019884624838656,
|
22 |
+
"pad_token": null,
|
23 |
+
"sp_model_kwargs": {},
|
24 |
+
"tokenizer_class": "LlamaTokenizer",
|
25 |
+
"unk_token": {
|
26 |
+
"__type": "AddedToken",
|
27 |
+
"content": "<unk>",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": true,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
}
|
33 |
+
}
|