qianguo sun
commited on
Commit
•
e2fe3c4
1
Parent(s):
8bd2731
ziya-v1.1模型参数
Browse files- added_tokens.json +4 -0
- config.json +23 -0
- generation_config.json +7 -0
- pytorch_model-00001-of-00028.bin +3 -0
- pytorch_model-00002-of-00028.bin +3 -0
- pytorch_model-00003-of-00028.bin +3 -0
- pytorch_model-00004-of-00028.bin +3 -0
- pytorch_model-00005-of-00028.bin +3 -0
- pytorch_model-00006-of-00028.bin +3 -0
- pytorch_model-00007-of-00028.bin +3 -0
- pytorch_model-00008-of-00028.bin +3 -0
- pytorch_model-00009-of-00028.bin +3 -0
- pytorch_model-00010-of-00028.bin +3 -0
- pytorch_model-00011-of-00028.bin +3 -0
- pytorch_model-00012-of-00028.bin +3 -0
- pytorch_model-00013-of-00028.bin +3 -0
- pytorch_model-00014-of-00028.bin +3 -0
- pytorch_model-00015-of-00028.bin +3 -0
- pytorch_model-00016-of-00028.bin +3 -0
- pytorch_model-00017-of-00028.bin +3 -0
- pytorch_model-00018-of-00028.bin +3 -0
- pytorch_model-00019-of-00028.bin +3 -0
- pytorch_model-00020-of-00028.bin +3 -0
- pytorch_model-00021-of-00028.bin +3 -0
- pytorch_model-00022-of-00028.bin +3 -0
- pytorch_model-00023-of-00028.bin +3 -0
- pytorch_model-00024-of-00028.bin +3 -0
- pytorch_model-00025-of-00028.bin +3 -0
- pytorch_model-00026-of-00028.bin +3 -0
- pytorch_model-00027-of-00028.bin +3 -0
- pytorch_model-00028-of-00028.bin +3 -0
- pytorch_model.bin.index.json +410 -0
- special_tokens_map.json +27 -0
- tokenizer.model +3 -0
- tokenizer_config.json +33 -0
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<bot>": 39409,
|
3 |
+
"<human>": 39408
|
4 |
+
}
|
config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/cognitive_comp/wanghao/models/llama_sft/llama_13B_v2_S2.2_S3_S3.1_rlhf_0601_RM13B0525_step44_hf/",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 5120,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 13824,
|
12 |
+
"max_position_embeddings": 2048,
|
13 |
+
"model_type": "llama",
|
14 |
+
"num_attention_heads": 40,
|
15 |
+
"num_hidden_layers": 40,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"rms_norm_eps": 1e-06,
|
18 |
+
"tie_word_embeddings": false,
|
19 |
+
"torch_dtype": "float16",
|
20 |
+
"transformers_version": "4.29.0.dev0",
|
21 |
+
"use_cache": true,
|
22 |
+
"vocab_size": 39424
|
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": "4.29.0.dev0"
|
7 |
+
}
|
pytorch_model-00001-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d78d35589e250bad91b6987da35ac7f7f27d6e994cb2ebc737e6d57404e3237
|
3 |
+
size 896534991
|
pytorch_model-00002-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e1ba40369183bf4564504d273d5c1714fad5ae32f9c9244446fcc7152975fa8
|
3 |
+
size 985707823
|
pytorch_model-00003-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c138ad796ecbedf85b644ae7d9f4f4bd938ec464ef97f3c568bc284da8920b09
|
3 |
+
size 917528001
|
pytorch_model-00004-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54dcfca44f9ac0bfda7bfc2e25c9826c6881186ac18a3d2cc7996512628362c1
|
3 |
+
size 985707823
|
pytorch_model-00005-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b553a8f0bbb5ae4834f1007e76a325319078a00827a5a256c063a0bd0ca442fc
|
3 |
+
size 917528001
|
pytorch_model-00006-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf0d535f65041b80696c374f948a8861cd6b561f6d471b7cb9b2b506f284a653
|
3 |
+
size 985707823
|
pytorch_model-00007-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5e8eb0ec9b9f3a65c35c87ccad214a1855287d0e9f1e405aaa7eaed55a073aa
|
3 |
+
size 917528001
|
pytorch_model-00008-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8514efe195a7918cbca0e3273a85aaccb9cfe427bc9bc499a7436510846f9d5d
|
3 |
+
size 985707823
|
pytorch_model-00009-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efcfb0ed11534724b4c1ace92afad27f54f7ed434a1a5b930d8145d18fe74abd
|
3 |
+
size 917528001
|
pytorch_model-00010-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b8b4cdf6cb8953ea14aa922b7ded60211cfb1d4b0b0e9fefaf8f99e15c52298
|
3 |
+
size 985707823
|
pytorch_model-00011-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24536b6511a11a24647a9e186b2b10cf9d9e5c281854204d9cb22dcec71685aa
|
3 |
+
size 917528001
|
pytorch_model-00012-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57f574a3f0467714fe292c05bdf3f5f1bab6921a3704647fcb8ae25950bcc2af
|
3 |
+
size 985707823
|
pytorch_model-00013-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41757aaf8aea91ab203d3d79e058ab31ea64b6d5deeed7264f413128db8a56d9
|
3 |
+
size 917528001
|
pytorch_model-00014-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd9a0d17f9fe75c18664abc74dd58166e7e32a39dd50d1e0231331f825e0aa43
|
3 |
+
size 985707823
|
pytorch_model-00015-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a54a244d00c03e631a0dfa5301acd38e07ab59f654874ad10fbaee282ecae3b9
|
3 |
+
size 917528001
|
pytorch_model-00016-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4acf0d9320e5da2ffdbae1a045c32006933e4d14be9b7bcfae3da74c8c2e0f9
|
3 |
+
size 985707823
|
pytorch_model-00017-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:804dae5572173db7ffb6e81f8875fe904174c5c46492293c554c689284be6743
|
3 |
+
size 917528001
|
pytorch_model-00018-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83c9429d501250508e587ce194e877e476a0c3674f9e1b769207d214ab42caf7
|
3 |
+
size 985707823
|
pytorch_model-00019-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c56aa1a50e7f35e46016b9500d737b1998bd1dd1f393e2e6a97cc1cd2e172c0
|
3 |
+
size 917528001
|
pytorch_model-00020-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7b3894faa56d2f01862a3b6ed2722845720b35a026a2ebc1526d3bd8d7fd78b
|
3 |
+
size 985707823
|
pytorch_model-00021-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a69b190c3901db14e7856129ab6900220009e81cf068ed2d486ade4c9a906ff
|
3 |
+
size 917528001
|
pytorch_model-00022-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b9cefca3b3a7155e0a7ffe04e6c07d29c4e7a5cc16c81439c845de6c978dbed
|
3 |
+
size 985707823
|
pytorch_model-00023-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f96de3d3e2f0ddafef3899d7cb8672fc6086050e7b042acb7fa4165ac232ce8
|
3 |
+
size 917528001
|
pytorch_model-00024-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d1b573351e66777bae369d2d7e422c72d69c7ed70cf894e31990f8bebdbc3e6
|
3 |
+
size 985707823
|
pytorch_model-00025-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ab910abbff94003ea8c32628dbc184529401af6367fc937735df0e221ddf258
|
3 |
+
size 917528001
|
pytorch_model-00026-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:086ae2fa7cc13f16ea25003d5df693a2f262af4ea8101b0adb77bd9fe3fa2964
|
3 |
+
size 985707823
|
pytorch_model-00027-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64f1e07dd86cc7f944bb4e1c26c9db60e3caa3a3e15c3a385c0b9e43b78446e2
|
3 |
+
size 917528001
|
pytorch_model-00028-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fd11030c08cc0426293de186109d908efd9c5297fcb83053d12db1a20cba314
|
3 |
+
size 545291867
|
pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,410 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 26183777280
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "pytorch_model-00028-of-00028.bin",
|
7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00028.bin",
|
8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00028.bin",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00028.bin",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00028.bin",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00028.bin",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00028.bin",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00028.bin",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00028.bin",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00028.bin",
|
16 |
+
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00028.bin",
|
17 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00028.bin",
|
18 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00028.bin",
|
19 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00028.bin",
|
20 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00028.bin",
|
21 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00028.bin",
|
22 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00028.bin",
|
23 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00028.bin",
|
24 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00028.bin",
|
25 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00028.bin",
|
26 |
+
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00028.bin",
|
27 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00028.bin",
|
28 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00008-of-00028.bin",
|
29 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00008-of-00028.bin",
|
30 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00008-of-00028.bin",
|
31 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00008-of-00028.bin",
|
32 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00008-of-00028.bin",
|
33 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00008-of-00028.bin",
|
34 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00008-of-00028.bin",
|
35 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00008-of-00028.bin",
|
36 |
+
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00028.bin",
|
37 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00008-of-00028.bin",
|
38 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00009-of-00028.bin",
|
39 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00009-of-00028.bin",
|
40 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00009-of-00028.bin",
|
41 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00009-of-00028.bin",
|
42 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00009-of-00028.bin",
|
43 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00008-of-00028.bin",
|
44 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00008-of-00028.bin",
|
45 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00008-of-00028.bin",
|
46 |
+
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00028.bin",
|
47 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00008-of-00028.bin",
|
48 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00010-of-00028.bin",
|
49 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00009-of-00028.bin",
|
50 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00009-of-00028.bin",
|
51 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00010-of-00028.bin",
|
52 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00010-of-00028.bin",
|
53 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00009-of-00028.bin",
|
54 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00009-of-00028.bin",
|
55 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00009-of-00028.bin",
|
56 |
+
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00028.bin",
|
57 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00009-of-00028.bin",
|
58 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00010-of-00028.bin",
|
59 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00010-of-00028.bin",
|
60 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00010-of-00028.bin",
|
61 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00010-of-00028.bin",
|
62 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00010-of-00028.bin",
|
63 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00010-of-00028.bin",
|
64 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00010-of-00028.bin",
|
65 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00010-of-00028.bin",
|
66 |
+
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00028.bin",
|
67 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00010-of-00028.bin",
|
68 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00011-of-00028.bin",
|
69 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00011-of-00028.bin",
|
70 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00011-of-00028.bin",
|
71 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00011-of-00028.bin",
|
72 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00011-of-00028.bin",
|
73 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00010-of-00028.bin",
|
74 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00010-of-00028.bin",
|
75 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00010-of-00028.bin",
|
76 |
+
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00028.bin",
|
77 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00010-of-00028.bin",
|
78 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00012-of-00028.bin",
|
79 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00011-of-00028.bin",
|
80 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00011-of-00028.bin",
|
81 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00012-of-00028.bin",
|
82 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00012-of-00028.bin",
|
83 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00011-of-00028.bin",
|
84 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00011-of-00028.bin",
|
85 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00011-of-00028.bin",
|
86 |
+
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00028.bin",
|
87 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00011-of-00028.bin",
|
88 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00012-of-00028.bin",
|
89 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00012-of-00028.bin",
|
90 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00012-of-00028.bin",
|
91 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00012-of-00028.bin",
|
92 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00012-of-00028.bin",
|
93 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00012-of-00028.bin",
|
94 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00012-of-00028.bin",
|
95 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00012-of-00028.bin",
|
96 |
+
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00028.bin",
|
97 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00012-of-00028.bin",
|
98 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00013-of-00028.bin",
|
99 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00013-of-00028.bin",
|
100 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00013-of-00028.bin",
|
101 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00013-of-00028.bin",
|
102 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00013-of-00028.bin",
|
103 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00012-of-00028.bin",
|
104 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00012-of-00028.bin",
|
105 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00012-of-00028.bin",
|
106 |
+
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00028.bin",
|
107 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00012-of-00028.bin",
|
108 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00014-of-00028.bin",
|
109 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00013-of-00028.bin",
|
110 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00013-of-00028.bin",
|
111 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00014-of-00028.bin",
|
112 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00014-of-00028.bin",
|
113 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00013-of-00028.bin",
|
114 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00013-of-00028.bin",
|
115 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00013-of-00028.bin",
|
116 |
+
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00028.bin",
|
117 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00013-of-00028.bin",
|
118 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00014-of-00028.bin",
|
119 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00014-of-00028.bin",
|
120 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00014-of-00028.bin",
|
121 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00014-of-00028.bin",
|
122 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00014-of-00028.bin",
|
123 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00014-of-00028.bin",
|
124 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00014-of-00028.bin",
|
125 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00014-of-00028.bin",
|
126 |
+
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00028.bin",
|
127 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00014-of-00028.bin",
|
128 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00003-of-00028.bin",
|
129 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00003-of-00028.bin",
|
130 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00003-of-00028.bin",
|
131 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00003-of-00028.bin",
|
132 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00003-of-00028.bin",
|
133 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00028.bin",
|
134 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00028.bin",
|
135 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00028.bin",
|
136 |
+
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00028.bin",
|
137 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00028.bin",
|
138 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00015-of-00028.bin",
|
139 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00015-of-00028.bin",
|
140 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00015-of-00028.bin",
|
141 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00015-of-00028.bin",
|
142 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00015-of-00028.bin",
|
143 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00014-of-00028.bin",
|
144 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00014-of-00028.bin",
|
145 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00014-of-00028.bin",
|
146 |
+
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00028.bin",
|
147 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00014-of-00028.bin",
|
148 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00016-of-00028.bin",
|
149 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00015-of-00028.bin",
|
150 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00015-of-00028.bin",
|
151 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00016-of-00028.bin",
|
152 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00016-of-00028.bin",
|
153 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00015-of-00028.bin",
|
154 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00015-of-00028.bin",
|
155 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00015-of-00028.bin",
|
156 |
+
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00028.bin",
|
157 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00015-of-00028.bin",
|
158 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00016-of-00028.bin",
|
159 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00016-of-00028.bin",
|
160 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00016-of-00028.bin",
|
161 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00016-of-00028.bin",
|
162 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00016-of-00028.bin",
|
163 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00016-of-00028.bin",
|
164 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00016-of-00028.bin",
|
165 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00016-of-00028.bin",
|
166 |
+
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00028.bin",
|
167 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00016-of-00028.bin",
|
168 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00017-of-00028.bin",
|
169 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00017-of-00028.bin",
|
170 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00017-of-00028.bin",
|
171 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00017-of-00028.bin",
|
172 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00017-of-00028.bin",
|
173 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00016-of-00028.bin",
|
174 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00016-of-00028.bin",
|
175 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00016-of-00028.bin",
|
176 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00028.bin",
|
177 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00016-of-00028.bin",
|
178 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00018-of-00028.bin",
|
179 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00017-of-00028.bin",
|
180 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00017-of-00028.bin",
|
181 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00018-of-00028.bin",
|
182 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00018-of-00028.bin",
|
183 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00017-of-00028.bin",
|
184 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00017-of-00028.bin",
|
185 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00017-of-00028.bin",
|
186 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00028.bin",
|
187 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00017-of-00028.bin",
|
188 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00018-of-00028.bin",
|
189 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00018-of-00028.bin",
|
190 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00018-of-00028.bin",
|
191 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00018-of-00028.bin",
|
192 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00018-of-00028.bin",
|
193 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00018-of-00028.bin",
|
194 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00018-of-00028.bin",
|
195 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00018-of-00028.bin",
|
196 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00028.bin",
|
197 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00018-of-00028.bin",
|
198 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00019-of-00028.bin",
|
199 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00019-of-00028.bin",
|
200 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00019-of-00028.bin",
|
201 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00019-of-00028.bin",
|
202 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00019-of-00028.bin",
|
203 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00018-of-00028.bin",
|
204 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00018-of-00028.bin",
|
205 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00018-of-00028.bin",
|
206 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00028.bin",
|
207 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00018-of-00028.bin",
|
208 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00020-of-00028.bin",
|
209 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00019-of-00028.bin",
|
210 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00019-of-00028.bin",
|
211 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00020-of-00028.bin",
|
212 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00020-of-00028.bin",
|
213 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00019-of-00028.bin",
|
214 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00019-of-00028.bin",
|
215 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00019-of-00028.bin",
|
216 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00028.bin",
|
217 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00019-of-00028.bin",
|
218 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00020-of-00028.bin",
|
219 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00020-of-00028.bin",
|
220 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00020-of-00028.bin",
|
221 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00020-of-00028.bin",
|
222 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00020-of-00028.bin",
|
223 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00020-of-00028.bin",
|
224 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00020-of-00028.bin",
|
225 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00020-of-00028.bin",
|
226 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00028.bin",
|
227 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00020-of-00028.bin",
|
228 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00021-of-00028.bin",
|
229 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00021-of-00028.bin",
|
230 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00021-of-00028.bin",
|
231 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00021-of-00028.bin",
|
232 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00021-of-00028.bin",
|
233 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00020-of-00028.bin",
|
234 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00020-of-00028.bin",
|
235 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00020-of-00028.bin",
|
236 |
+
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00028.bin",
|
237 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00020-of-00028.bin",
|
238 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00004-of-00028.bin",
|
239 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00003-of-00028.bin",
|
240 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00003-of-00028.bin",
|
241 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00004-of-00028.bin",
|
242 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00004-of-00028.bin",
|
243 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00028.bin",
|
244 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00003-of-00028.bin",
|
245 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00028.bin",
|
246 |
+
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00028.bin",
|
247 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00028.bin",
|
248 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00022-of-00028.bin",
|
249 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00021-of-00028.bin",
|
250 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00021-of-00028.bin",
|
251 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00022-of-00028.bin",
|
252 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00022-of-00028.bin",
|
253 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00021-of-00028.bin",
|
254 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00021-of-00028.bin",
|
255 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00021-of-00028.bin",
|
256 |
+
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00028.bin",
|
257 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00021-of-00028.bin",
|
258 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00022-of-00028.bin",
|
259 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00022-of-00028.bin",
|
260 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00022-of-00028.bin",
|
261 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00022-of-00028.bin",
|
262 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00022-of-00028.bin",
|
263 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00022-of-00028.bin",
|
264 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00022-of-00028.bin",
|
265 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00022-of-00028.bin",
|
266 |
+
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00028.bin",
|
267 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00022-of-00028.bin",
|
268 |
+
"model.layers.32.input_layernorm.weight": "pytorch_model-00023-of-00028.bin",
|
269 |
+
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00023-of-00028.bin",
|
270 |
+
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00023-of-00028.bin",
|
271 |
+
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00023-of-00028.bin",
|
272 |
+
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00023-of-00028.bin",
|
273 |
+
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00022-of-00028.bin",
|
274 |
+
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00022-of-00028.bin",
|
275 |
+
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00022-of-00028.bin",
|
276 |
+
"model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00028.bin",
|
277 |
+
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00022-of-00028.bin",
|
278 |
+
"model.layers.33.input_layernorm.weight": "pytorch_model-00024-of-00028.bin",
|
279 |
+
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00023-of-00028.bin",
|
280 |
+
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00023-of-00028.bin",
|
281 |
+
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00024-of-00028.bin",
|
282 |
+
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00024-of-00028.bin",
|
283 |
+
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00023-of-00028.bin",
|
284 |
+
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00023-of-00028.bin",
|
285 |
+
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00023-of-00028.bin",
|
286 |
+
"model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00028.bin",
|
287 |
+
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00023-of-00028.bin",
|
288 |
+
"model.layers.34.input_layernorm.weight": "pytorch_model-00024-of-00028.bin",
|
289 |
+
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00024-of-00028.bin",
|
290 |
+
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00024-of-00028.bin",
|
291 |
+
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00024-of-00028.bin",
|
292 |
+
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00024-of-00028.bin",
|
293 |
+
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00024-of-00028.bin",
|
294 |
+
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00024-of-00028.bin",
|
295 |
+
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00024-of-00028.bin",
|
296 |
+
"model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00028.bin",
|
297 |
+
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00024-of-00028.bin",
|
298 |
+
"model.layers.35.input_layernorm.weight": "pytorch_model-00025-of-00028.bin",
|
299 |
+
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00025-of-00028.bin",
|
300 |
+
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00025-of-00028.bin",
|
301 |
+
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00025-of-00028.bin",
|
302 |
+
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00025-of-00028.bin",
|
303 |
+
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00024-of-00028.bin",
|
304 |
+
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00024-of-00028.bin",
|
305 |
+
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00024-of-00028.bin",
|
306 |
+
"model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00028.bin",
|
307 |
+
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00024-of-00028.bin",
|
308 |
+
"model.layers.36.input_layernorm.weight": "pytorch_model-00026-of-00028.bin",
|
309 |
+
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00025-of-00028.bin",
|
310 |
+
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00025-of-00028.bin",
|
311 |
+
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00026-of-00028.bin",
|
312 |
+
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00026-of-00028.bin",
|
313 |
+
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00025-of-00028.bin",
|
314 |
+
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00025-of-00028.bin",
|
315 |
+
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00025-of-00028.bin",
|
316 |
+
"model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00028.bin",
|
317 |
+
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00025-of-00028.bin",
|
318 |
+
"model.layers.37.input_layernorm.weight": "pytorch_model-00026-of-00028.bin",
|
319 |
+
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00026-of-00028.bin",
|
320 |
+
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00026-of-00028.bin",
|
321 |
+
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00026-of-00028.bin",
|
322 |
+
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00026-of-00028.bin",
|
323 |
+
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00026-of-00028.bin",
|
324 |
+
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00026-of-00028.bin",
|
325 |
+
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00026-of-00028.bin",
|
326 |
+
"model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00028.bin",
|
327 |
+
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00026-of-00028.bin",
|
328 |
+
"model.layers.38.input_layernorm.weight": "pytorch_model-00027-of-00028.bin",
|
329 |
+
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00027-of-00028.bin",
|
330 |
+
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00027-of-00028.bin",
|
331 |
+
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00027-of-00028.bin",
|
332 |
+
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00027-of-00028.bin",
|
333 |
+
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00026-of-00028.bin",
|
334 |
+
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00026-of-00028.bin",
|
335 |
+
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00026-of-00028.bin",
|
336 |
+
"model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00028.bin",
|
337 |
+
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00026-of-00028.bin",
|
338 |
+
"model.layers.39.input_layernorm.weight": "pytorch_model-00028-of-00028.bin",
|
339 |
+
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00027-of-00028.bin",
|
340 |
+
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00027-of-00028.bin",
|
341 |
+
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00028-of-00028.bin",
|
342 |
+
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00028-of-00028.bin",
|
343 |
+
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00027-of-00028.bin",
|
344 |
+
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00027-of-00028.bin",
|
345 |
+
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00027-of-00028.bin",
|
346 |
+
"model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00028.bin",
|
347 |
+
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00027-of-00028.bin",
|
348 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00004-of-00028.bin",
|
349 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00004-of-00028.bin",
|
350 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00004-of-00028.bin",
|
351 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00004-of-00028.bin",
|
352 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00004-of-00028.bin",
|
353 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00004-of-00028.bin",
|
354 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00004-of-00028.bin",
|
355 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00004-of-00028.bin",
|
356 |
+
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00028.bin",
|
357 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00004-of-00028.bin",
|
358 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00005-of-00028.bin",
|
359 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00005-of-00028.bin",
|
360 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00005-of-00028.bin",
|
361 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00005-of-00028.bin",
|
362 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00005-of-00028.bin",
|
363 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00004-of-00028.bin",
|
364 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00004-of-00028.bin",
|
365 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00004-of-00028.bin",
|
366 |
+
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00028.bin",
|
367 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00004-of-00028.bin",
|
368 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00006-of-00028.bin",
|
369 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00005-of-00028.bin",
|
370 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00005-of-00028.bin",
|
371 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00006-of-00028.bin",
|
372 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00006-of-00028.bin",
|
373 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00005-of-00028.bin",
|
374 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00005-of-00028.bin",
|
375 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00005-of-00028.bin",
|
376 |
+
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00028.bin",
|
377 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00005-of-00028.bin",
|
378 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00006-of-00028.bin",
|
379 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00006-of-00028.bin",
|
380 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00006-of-00028.bin",
|
381 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00006-of-00028.bin",
|
382 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00006-of-00028.bin",
|
383 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00006-of-00028.bin",
|
384 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00006-of-00028.bin",
|
385 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00006-of-00028.bin",
|
386 |
+
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00028.bin",
|
387 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00006-of-00028.bin",
|
388 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00007-of-00028.bin",
|
389 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00007-of-00028.bin",
|
390 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00007-of-00028.bin",
|
391 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00007-of-00028.bin",
|
392 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00007-of-00028.bin",
|
393 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00006-of-00028.bin",
|
394 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00006-of-00028.bin",
|
395 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00006-of-00028.bin",
|
396 |
+
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00028.bin",
|
397 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00006-of-00028.bin",
|
398 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00008-of-00028.bin",
|
399 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00007-of-00028.bin",
|
400 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00007-of-00028.bin",
|
401 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00008-of-00028.bin",
|
402 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00008-of-00028.bin",
|
403 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00007-of-00028.bin",
|
404 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00007-of-00028.bin",
|
405 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00007-of-00028.bin",
|
406 |
+
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00028.bin",
|
407 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00007-of-00028.bin",
|
408 |
+
"model.norm.weight": "pytorch_model-00028-of-00028.bin"
|
409 |
+
}
|
410 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<human>",
|
4 |
+
"<bot>"
|
5 |
+
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<s>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"eos_token": {
|
14 |
+
"content": "</s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"unk_token": {
|
21 |
+
"content": "<unk>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
}
|
27 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fd7e445833dd0889206aba242c2a51ecbae2437fd328d1759a35475fd8c0423
|
3 |
+
size 588619
|
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 |
+
}
|