Upload 45 files
Browse files- config.json +23 -0
- generation_config.json +7 -0
- pytorch_model-00001-of-00039.bin +3 -0
- pytorch_model-00002-of-00039.bin +3 -0
- pytorch_model-00003-of-00039.bin +3 -0
- pytorch_model-00004-of-00039.bin +3 -0
- pytorch_model-00005-of-00039.bin +3 -0
- pytorch_model-00006-of-00039.bin +3 -0
- pytorch_model-00007-of-00039.bin +3 -0
- pytorch_model-00008-of-00039.bin +3 -0
- pytorch_model-00009-of-00039.bin +3 -0
- pytorch_model-00010-of-00039.bin +3 -0
- pytorch_model-00011-of-00039.bin +3 -0
- pytorch_model-00012-of-00039.bin +3 -0
- pytorch_model-00013-of-00039.bin +3 -0
- pytorch_model-00014-of-00039.bin +3 -0
- pytorch_model-00015-of-00039.bin +3 -0
- pytorch_model-00016-of-00039.bin +3 -0
- pytorch_model-00017-of-00039.bin +3 -0
- pytorch_model-00018-of-00039.bin +3 -0
- pytorch_model-00019-of-00039.bin +3 -0
- pytorch_model-00020-of-00039.bin +3 -0
- pytorch_model-00021-of-00039.bin +3 -0
- pytorch_model-00022-of-00039.bin +3 -0
- pytorch_model-00023-of-00039.bin +3 -0
- pytorch_model-00024-of-00039.bin +3 -0
- pytorch_model-00025-of-00039.bin +3 -0
- pytorch_model-00026-of-00039.bin +3 -0
- pytorch_model-00027-of-00039.bin +3 -0
- pytorch_model-00028-of-00039.bin +3 -0
- pytorch_model-00029-of-00039.bin +3 -0
- pytorch_model-00030-of-00039.bin +3 -0
- pytorch_model-00031-of-00039.bin +3 -0
- pytorch_model-00032-of-00039.bin +3 -0
- pytorch_model-00033-of-00039.bin +3 -0
- pytorch_model-00034-of-00039.bin +3 -0
- pytorch_model-00035-of-00039.bin +3 -0
- pytorch_model-00036-of-00039.bin +3 -0
- pytorch_model-00037-of-00039.bin +3 -0
- pytorch_model-00038-of-00039.bin +3 -0
- pytorch_model-00039-of-00039.bin +3 -0
- pytorch_model.bin.index.json +330 -0
- special_tokens_map.json +1 -0
- tokenizer.model +3 -0
- tokenizer_config.json +1 -0
config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/karajan/labzone/textgen/alpaca-lora/open_llama_7b_preview_200bt_transformers_weights",
|
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": 2048,
|
13 |
+
"model_type": "llama",
|
14 |
+
"num_attention_heads": 32,
|
15 |
+
"num_hidden_layers": 32,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"rms_norm_eps": 1e-06,
|
18 |
+
"tie_word_embeddings": false,
|
19 |
+
"torch_dtype": "float16",
|
20 |
+
"transformers_version": "4.28.1",
|
21 |
+
"use_cache": true,
|
22 |
+
"vocab_size": 32000
|
23 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.28.1"
|
7 |
+
}
|
pytorch_model-00001-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81a9b01165a5bf04feaadaef38b566319f997d0c5ff4d2a11f672166de68de38
|
3 |
+
size 396364479
|
pytorch_model-00002-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82baa0e29df9372c18641f0d6a18de7d8e4bc102c1659094b0a86a74360199d6
|
3 |
+
size 371215393
|
pytorch_model-00003-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b92ddc0ec08253a874aba005922edffa4439a29d9d1f20668c9fb7c2893de46
|
3 |
+
size 371215986
|
pytorch_model-00004-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1496e4362f2f73386b77fc1c4a60ab9e0830edd715da36137adc4be747a5a439
|
3 |
+
size 371215986
|
pytorch_model-00005-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0b29d102521d50b6324f496d5786967b8b14c870a7e0838afa96b7aad61e472
|
3 |
+
size 371215986
|
pytorch_model-00006-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb542a4bee094419082368dc87deef6554f880a579c77686eac856fa8996bce3
|
3 |
+
size 314575888
|
pytorch_model-00007-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d09daf1e949d11ef625e7b94836dd777dae7505b549a31d633aa134218a67a3
|
3 |
+
size 314592882
|
pytorch_model-00008-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f173b845fe8446eb104820dc27a2e4f05e1a2b665fe361d39e09da7fc175ad25
|
3 |
+
size 314592882
|
pytorch_model-00009-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dcf89039f6136558ff443322d724bf0d199be519501ebe7c356e61f3c545456
|
3 |
+
size 371215393
|
pytorch_model-00010-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4263bf4a9b9d223e6a44382841f3ebc6c5ee7860df69566e5c69d1a32d7c1335
|
3 |
+
size 371215986
|
pytorch_model-00011-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64ac25183d859526bfedfa82142f96e86c898ec54f7619361d517579ca11e556
|
3 |
+
size 371215986
|
pytorch_model-00012-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3eac7a8541660eb95a05f3455950f664932aca252b7fb41b3c07c8561fd2450c
|
3 |
+
size 371215986
|
pytorch_model-00013-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7752683150b4dd1cdc71638ccf307bef03152a575e533d9d26c9924d1bb5bf5
|
3 |
+
size 314575888
|
pytorch_model-00014-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dfc81e9a37c7f476f42e94e8ceb5d7dc9030a10dcc084906aeba2b742c218df
|
3 |
+
size 314592882
|
pytorch_model-00015-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:937623fa0388b1f367aeb7cfb934f4c39304369a9af5103150397fe7ed12695c
|
3 |
+
size 314592882
|
pytorch_model-00016-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb5360c0acfca433d0fe8b794bac8ab7cc4ba24d444cf5203538d54b622fa2e7
|
3 |
+
size 371215393
|
pytorch_model-00017-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a50801a01bf93b40adc6e4fd6b914702e4b936e9c6bb04cbcb94e96f6f029a33
|
3 |
+
size 371215986
|
pytorch_model-00018-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5547a7b93e1feab17ccd087ebcd1a5f8e233519a6aef550ead8b90a1ebd47e2
|
3 |
+
size 371215986
|
pytorch_model-00019-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa7b3f1487ca3f8db0c56d8e2d13355fb713b5256569ff86c7f06c4680722c92
|
3 |
+
size 371215986
|
pytorch_model-00020-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40a4b17afe511d7d408b8a8b712299ee31ff0290890aef55de90751f1372a897
|
3 |
+
size 314575888
|
pytorch_model-00021-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0616550fc7ecaf2eb4bbd4ebe5b00dcb5a9f5be1bb08b9c3f4f5956d5e503df8
|
3 |
+
size 314592882
|
pytorch_model-00022-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb426dd234ae5f001f8ef89798db374d7932340962f87d886f54b8935a8995d0
|
3 |
+
size 314592882
|
pytorch_model-00023-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f392c4fb4b5603e53aae4efdd081637fbb19a86c2589e621c1833a0fbd17a33
|
3 |
+
size 371215393
|
pytorch_model-00024-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c83085e6505f05305f757bb9c9bb5d2268826d3910150ee5bde8ede5bf2a23b1
|
3 |
+
size 371215986
|
pytorch_model-00025-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f34c696580639fb9f959fb6350153d7e39f7a02f999126fcea97e79fcd2926da
|
3 |
+
size 371215986
|
pytorch_model-00026-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d8f7de9bcdacd81b26d98a18a2ba758025815afb192e224676ca9f38f051c54
|
3 |
+
size 371215986
|
pytorch_model-00027-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb0130f152666f811e6a647d6b3579cad5f9da2d6540bf2833b9d6c99f399491
|
3 |
+
size 314575888
|
pytorch_model-00028-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df86c9e49c0de27c7d124981f98761dca4d0eb6fddb503c0423f26b73d4e8850
|
3 |
+
size 314592882
|
pytorch_model-00029-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d7236f00014bd16b038b79868a2549e8a4721354722f8660331492033a89b24
|
3 |
+
size 314592882
|
pytorch_model-00030-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b62aeeff3e30b75acfb65fe14127a21b7b89e13afdf8582e5389757e69a0f2e
|
3 |
+
size 371215393
|
pytorch_model-00031-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2e30b67cc8e3a7661feb8ea71d17456c19b10f9de3e4367fd90ead17a964a83
|
3 |
+
size 371215986
|
pytorch_model-00032-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72aed1ca1ae7d15f878b74cc5fce5351fcb5ccfd7bcb330640916360788b419c
|
3 |
+
size 371215986
|
pytorch_model-00033-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2107332e4bc65f0197b4afd184f122387077b34511359fdd2fff60d0a17b3bc8
|
3 |
+
size 371215986
|
pytorch_model-00034-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fce04e7d120322a35563443db6225796fbe91924526a20b73d090275dd8917c2
|
3 |
+
size 314575888
|
pytorch_model-00035-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7516127f72eb1932b91a829473b110ffe8ef6891a5e8dae02c43a76576061c1
|
3 |
+
size 314592882
|
pytorch_model-00036-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42c1b5a7e32d3ddeecb314ec9d0c7654957763942edfa7c3561ed43e5de9c0bb
|
3 |
+
size 314592882
|
pytorch_model-00037-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5325b1272cf15bed665e377691d4d053240e36e8ed15fed56489f12d4c99c892
|
3 |
+
size 371215393
|
pytorch_model-00038-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0e5d95b451d23141917b99defae6699ec131a9cb705fc4003f3dce1dc83377b
|
3 |
+
size 304114977
|
pytorch_model-00039-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ac1bf32a1ea644875c20900e8bbc0e75f79794a630d5c70fe71f3624405ba84
|
3 |
+
size 262144938
|
pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,330 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 13476839424
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "pytorch_model-00039-of-00039.bin",
|
7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00039.bin",
|
8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00039.bin",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00039.bin",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00039.bin",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00039.bin",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00039.bin",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00039.bin",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00039.bin",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00039.bin",
|
16 |
+
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00039.bin",
|
17 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00039.bin",
|
18 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00039.bin",
|
19 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00003-of-00039.bin",
|
20 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00003-of-00039.bin",
|
21 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00003-of-00039.bin",
|
22 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00039.bin",
|
23 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00039.bin",
|
24 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00003-of-00039.bin",
|
25 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00039.bin",
|
26 |
+
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00039.bin",
|
27 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00039.bin",
|
28 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00014-of-00039.bin",
|
29 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00013-of-00039.bin",
|
30 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00013-of-00039.bin",
|
31 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00014-of-00039.bin",
|
32 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00014-of-00039.bin",
|
33 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00013-of-00039.bin",
|
34 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00013-of-00039.bin",
|
35 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00013-of-00039.bin",
|
36 |
+
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00039.bin",
|
37 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00013-of-00039.bin",
|
38 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00015-of-00039.bin",
|
39 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00015-of-00039.bin",
|
40 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00014-of-00039.bin",
|
41 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00015-of-00039.bin",
|
42 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00015-of-00039.bin",
|
43 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00014-of-00039.bin",
|
44 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00014-of-00039.bin",
|
45 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00014-of-00039.bin",
|
46 |
+
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00039.bin",
|
47 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00014-of-00039.bin",
|
48 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00016-of-00039.bin",
|
49 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00016-of-00039.bin",
|
50 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00016-of-00039.bin",
|
51 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00016-of-00039.bin",
|
52 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00016-of-00039.bin",
|
53 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00015-of-00039.bin",
|
54 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00015-of-00039.bin",
|
55 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00015-of-00039.bin",
|
56 |
+
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00039.bin",
|
57 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00015-of-00039.bin",
|
58 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00017-of-00039.bin",
|
59 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00017-of-00039.bin",
|
60 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00017-of-00039.bin",
|
61 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00017-of-00039.bin",
|
62 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00017-of-00039.bin",
|
63 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00016-of-00039.bin",
|
64 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00017-of-00039.bin",
|
65 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00016-of-00039.bin",
|
66 |
+
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00039.bin",
|
67 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00016-of-00039.bin",
|
68 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00018-of-00039.bin",
|
69 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00018-of-00039.bin",
|
70 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00018-of-00039.bin",
|
71 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00018-of-00039.bin",
|
72 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00018-of-00039.bin",
|
73 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00017-of-00039.bin",
|
74 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00018-of-00039.bin",
|
75 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00017-of-00039.bin",
|
76 |
+
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00039.bin",
|
77 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00018-of-00039.bin",
|
78 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00019-of-00039.bin",
|
79 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00019-of-00039.bin",
|
80 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00019-of-00039.bin",
|
81 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00019-of-00039.bin",
|
82 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00019-of-00039.bin",
|
83 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00019-of-00039.bin",
|
84 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00019-of-00039.bin",
|
85 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00018-of-00039.bin",
|
86 |
+
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00039.bin",
|
87 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00019-of-00039.bin",
|
88 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00021-of-00039.bin",
|
89 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00020-of-00039.bin",
|
90 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00020-of-00039.bin",
|
91 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00021-of-00039.bin",
|
92 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00021-of-00039.bin",
|
93 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00020-of-00039.bin",
|
94 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00020-of-00039.bin",
|
95 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00020-of-00039.bin",
|
96 |
+
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00039.bin",
|
97 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00020-of-00039.bin",
|
98 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00022-of-00039.bin",
|
99 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00022-of-00039.bin",
|
100 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00021-of-00039.bin",
|
101 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00022-of-00039.bin",
|
102 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00022-of-00039.bin",
|
103 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00021-of-00039.bin",
|
104 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00021-of-00039.bin",
|
105 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00021-of-00039.bin",
|
106 |
+
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00039.bin",
|
107 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00021-of-00039.bin",
|
108 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00023-of-00039.bin",
|
109 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00023-of-00039.bin",
|
110 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00023-of-00039.bin",
|
111 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00023-of-00039.bin",
|
112 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00023-of-00039.bin",
|
113 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00022-of-00039.bin",
|
114 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00022-of-00039.bin",
|
115 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00022-of-00039.bin",
|
116 |
+
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00039.bin",
|
117 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00022-of-00039.bin",
|
118 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00024-of-00039.bin",
|
119 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00024-of-00039.bin",
|
120 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00024-of-00039.bin",
|
121 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00024-of-00039.bin",
|
122 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00024-of-00039.bin",
|
123 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00023-of-00039.bin",
|
124 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00024-of-00039.bin",
|
125 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00023-of-00039.bin",
|
126 |
+
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00039.bin",
|
127 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00023-of-00039.bin",
|
128 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00004-of-00039.bin",
|
129 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00004-of-00039.bin",
|
130 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00004-of-00039.bin",
|
131 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00004-of-00039.bin",
|
132 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00004-of-00039.bin",
|
133 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00039.bin",
|
134 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00004-of-00039.bin",
|
135 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00039.bin",
|
136 |
+
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00039.bin",
|
137 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00004-of-00039.bin",
|
138 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00025-of-00039.bin",
|
139 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00025-of-00039.bin",
|
140 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00025-of-00039.bin",
|
141 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00025-of-00039.bin",
|
142 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00025-of-00039.bin",
|
143 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00024-of-00039.bin",
|
144 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00025-of-00039.bin",
|
145 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00024-of-00039.bin",
|
146 |
+
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00039.bin",
|
147 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00025-of-00039.bin",
|
148 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00026-of-00039.bin",
|
149 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00026-of-00039.bin",
|
150 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00026-of-00039.bin",
|
151 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00026-of-00039.bin",
|
152 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00026-of-00039.bin",
|
153 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00026-of-00039.bin",
|
154 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00026-of-00039.bin",
|
155 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00025-of-00039.bin",
|
156 |
+
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00039.bin",
|
157 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00026-of-00039.bin",
|
158 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00028-of-00039.bin",
|
159 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00027-of-00039.bin",
|
160 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00027-of-00039.bin",
|
161 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00028-of-00039.bin",
|
162 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00028-of-00039.bin",
|
163 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00027-of-00039.bin",
|
164 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00027-of-00039.bin",
|
165 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00027-of-00039.bin",
|
166 |
+
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00039.bin",
|
167 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00027-of-00039.bin",
|
168 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00029-of-00039.bin",
|
169 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00029-of-00039.bin",
|
170 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00028-of-00039.bin",
|
171 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00029-of-00039.bin",
|
172 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00029-of-00039.bin",
|
173 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00028-of-00039.bin",
|
174 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00028-of-00039.bin",
|
175 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00028-of-00039.bin",
|
176 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00028-of-00039.bin",
|
177 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00028-of-00039.bin",
|
178 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00030-of-00039.bin",
|
179 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00030-of-00039.bin",
|
180 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00030-of-00039.bin",
|
181 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00030-of-00039.bin",
|
182 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00030-of-00039.bin",
|
183 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00029-of-00039.bin",
|
184 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00029-of-00039.bin",
|
185 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00029-of-00039.bin",
|
186 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00039.bin",
|
187 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00029-of-00039.bin",
|
188 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00031-of-00039.bin",
|
189 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00031-of-00039.bin",
|
190 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00031-of-00039.bin",
|
191 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00031-of-00039.bin",
|
192 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00031-of-00039.bin",
|
193 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00030-of-00039.bin",
|
194 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00031-of-00039.bin",
|
195 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00030-of-00039.bin",
|
196 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00039.bin",
|
197 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00030-of-00039.bin",
|
198 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00032-of-00039.bin",
|
199 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00032-of-00039.bin",
|
200 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00032-of-00039.bin",
|
201 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00032-of-00039.bin",
|
202 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00032-of-00039.bin",
|
203 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00031-of-00039.bin",
|
204 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00032-of-00039.bin",
|
205 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00031-of-00039.bin",
|
206 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00032-of-00039.bin",
|
207 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00032-of-00039.bin",
|
208 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00033-of-00039.bin",
|
209 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00033-of-00039.bin",
|
210 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00033-of-00039.bin",
|
211 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00033-of-00039.bin",
|
212 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00033-of-00039.bin",
|
213 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00033-of-00039.bin",
|
214 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00033-of-00039.bin",
|
215 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00032-of-00039.bin",
|
216 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00033-of-00039.bin",
|
217 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00033-of-00039.bin",
|
218 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00035-of-00039.bin",
|
219 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00034-of-00039.bin",
|
220 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00034-of-00039.bin",
|
221 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00035-of-00039.bin",
|
222 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00035-of-00039.bin",
|
223 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00034-of-00039.bin",
|
224 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00034-of-00039.bin",
|
225 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00034-of-00039.bin",
|
226 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00034-of-00039.bin",
|
227 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00034-of-00039.bin",
|
228 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00036-of-00039.bin",
|
229 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00036-of-00039.bin",
|
230 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00035-of-00039.bin",
|
231 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00036-of-00039.bin",
|
232 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00036-of-00039.bin",
|
233 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00035-of-00039.bin",
|
234 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00035-of-00039.bin",
|
235 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00035-of-00039.bin",
|
236 |
+
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00035-of-00039.bin",
|
237 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00035-of-00039.bin",
|
238 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00005-of-00039.bin",
|
239 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00005-of-00039.bin",
|
240 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00005-of-00039.bin",
|
241 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00005-of-00039.bin",
|
242 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00005-of-00039.bin",
|
243 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00005-of-00039.bin",
|
244 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00005-of-00039.bin",
|
245 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00004-of-00039.bin",
|
246 |
+
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00039.bin",
|
247 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00005-of-00039.bin",
|
248 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00037-of-00039.bin",
|
249 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00037-of-00039.bin",
|
250 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00037-of-00039.bin",
|
251 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00037-of-00039.bin",
|
252 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00037-of-00039.bin",
|
253 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00036-of-00039.bin",
|
254 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00036-of-00039.bin",
|
255 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00036-of-00039.bin",
|
256 |
+
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00036-of-00039.bin",
|
257 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00036-of-00039.bin",
|
258 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00038-of-00039.bin",
|
259 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00038-of-00039.bin",
|
260 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00038-of-00039.bin",
|
261 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00038-of-00039.bin",
|
262 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00038-of-00039.bin",
|
263 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00037-of-00039.bin",
|
264 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00038-of-00039.bin",
|
265 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00037-of-00039.bin",
|
266 |
+
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00038-of-00039.bin",
|
267 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00037-of-00039.bin",
|
268 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00007-of-00039.bin",
|
269 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00006-of-00039.bin",
|
270 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00006-of-00039.bin",
|
271 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00007-of-00039.bin",
|
272 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00007-of-00039.bin",
|
273 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00006-of-00039.bin",
|
274 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00006-of-00039.bin",
|
275 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00006-of-00039.bin",
|
276 |
+
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00039.bin",
|
277 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00006-of-00039.bin",
|
278 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00008-of-00039.bin",
|
279 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00008-of-00039.bin",
|
280 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00007-of-00039.bin",
|
281 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00008-of-00039.bin",
|
282 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00008-of-00039.bin",
|
283 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00007-of-00039.bin",
|
284 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00007-of-00039.bin",
|
285 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00007-of-00039.bin",
|
286 |
+
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00039.bin",
|
287 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00007-of-00039.bin",
|
288 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00009-of-00039.bin",
|
289 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00009-of-00039.bin",
|
290 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00009-of-00039.bin",
|
291 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00009-of-00039.bin",
|
292 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00009-of-00039.bin",
|
293 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00008-of-00039.bin",
|
294 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00008-of-00039.bin",
|
295 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00008-of-00039.bin",
|
296 |
+
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00039.bin",
|
297 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00008-of-00039.bin",
|
298 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00010-of-00039.bin",
|
299 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00010-of-00039.bin",
|
300 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00010-of-00039.bin",
|
301 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00010-of-00039.bin",
|
302 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00010-of-00039.bin",
|
303 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00009-of-00039.bin",
|
304 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00010-of-00039.bin",
|
305 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00009-of-00039.bin",
|
306 |
+
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00039.bin",
|
307 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00009-of-00039.bin",
|
308 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00011-of-00039.bin",
|
309 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00011-of-00039.bin",
|
310 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00011-of-00039.bin",
|
311 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00011-of-00039.bin",
|
312 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00011-of-00039.bin",
|
313 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00010-of-00039.bin",
|
314 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00011-of-00039.bin",
|
315 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00010-of-00039.bin",
|
316 |
+
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00039.bin",
|
317 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00011-of-00039.bin",
|
318 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00012-of-00039.bin",
|
319 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00012-of-00039.bin",
|
320 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00012-of-00039.bin",
|
321 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00012-of-00039.bin",
|
322 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00012-of-00039.bin",
|
323 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00012-of-00039.bin",
|
324 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00012-of-00039.bin",
|
325 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00011-of-00039.bin",
|
326 |
+
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00039.bin",
|
327 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00012-of-00039.bin",
|
328 |
+
"model.norm.weight": "pytorch_model-00038-of-00039.bin"
|
329 |
+
}
|
330 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc820fc43f4173d6362c16658c409ed423929a807e55a984af96cce1277d39a4
|
3 |
+
size 772031
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "", "eos_token": "", "model_max_length": 1000000000000000019884624838656, "tokenizer_class": "LlamaTokenizer", "unk_token": ""}
|