sharpbai commited on
Commit
a7e566d
1 Parent(s): 266e28e

Upload BaiChuanForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sharpbai/Baichuan-7B",
3
+ "architectures": [
4
+ "BaiChuanForCausalLM"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_baichuan.BaiChuanConfig",
8
+ "AutoModelForCausalLM": "modeling_baichuan.BaiChuanForCausalLM"
9
+ },
10
+ "bos_token_id": 1,
11
+ "eos_token_id": 2,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 4096,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 11008,
16
+ "max_position_embeddings": 4096,
17
+ "model_type": "baichuan",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "pad_token_id": 0,
21
+ "rms_norm_eps": 1e-06,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "float16",
24
+ "transformers_version": "4.30.2",
25
+ "use_cache": true,
26
+ "vocab_size": 64000
27
+ }
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": "4.30.2"
7
+ }
pytorch_model-00001-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf02c4d7b83fa495ef73f290168a195ea899d0744f0fe32194046846bd87efe0
3
+ size 537
pytorch_model-00002-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aff8e9aa72626b49788fd10b0190a35779e5443c7571355b81f937320c06b10
3
+ size 524288938
pytorch_model-00003-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:165a1b52f07880508d750d2ea689a848fbdfe6823d959fa9ab3f8509c15d2c88
3
+ size 404770081
pytorch_model-00004-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:257a98b8e1a90d7cbefe525f2d4a7f44206f529e885efaac425eba25af995318
3
+ size 404770081
pytorch_model-00005-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63cec13ae8b6c09386f622ef8b99d6309652bfa57c2b4baa769d8a1a664e07f2
3
+ size 404770081
pytorch_model-00006-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75904899e0507e7ba4717f59bb81dc327f335b0abff5f1579d9f754dcbbb518c
3
+ size 404770081
pytorch_model-00007-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03e9e6fceed54c314c311982cc12f4b6b0fa14f108dc6d3575bd10afc7f6243f
3
+ size 404770081
pytorch_model-00008-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28a8f678eb6089a63559eb758ba67dd2760f9206546141eb6f77c39a37a77d4d
3
+ size 404770081
pytorch_model-00009-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8eae231300f967af5d710f75f779792f1f65c24d527ad5b8ee76111ca40a177
3
+ size 404770081
pytorch_model-00010-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c54bdee8c8481c622cee6126f13b80d8c1d8a4b8166a2c973d9f1cde9f3e69c4
3
+ size 404770081
pytorch_model-00011-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69c7a5d31b6609971c6fbc956ea81158c2fd49b93f4b8e8856bcba29fc949409
3
+ size 404770081
pytorch_model-00012-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b63565001d8d760e011240349d5a10057c96543bdc54c09459b6e12485faaf91
3
+ size 404770081
pytorch_model-00013-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11aa46a9512bc6a375ff7c9af5482e2390b8d2383dbdc3a974b87f8f2c209462
3
+ size 404770145
pytorch_model-00014-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfd4b1e3545bff3527b47924e8b89befe73434c62cff503032f81c13a01b5cbe
3
+ size 404770145
pytorch_model-00015-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c618f43e9e4eb03231cb9d49a0b8bd083f905e3bb2cbf4134c5f4b69367b40ad
3
+ size 404770145
pytorch_model-00016-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fc8fb7508d8471a6221d9d40014725f3eea3007bb5ec25de48f0af3126108f7
3
+ size 404770145
pytorch_model-00017-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:240e7eeeb6fcdd5f7abfd019216eea0e0273fff7f9182f86b3bb842a4bc088f8
3
+ size 404770145
pytorch_model-00018-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e2461005e9692766cba28e9763e6a62594c9fa0f5cfc6e28f60f0aa1677f90d
3
+ size 404770145
pytorch_model-00019-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4383b171cc84b015d54450cdee3a7c862ebb701a08c86fa1d824ce98f5db3e9
3
+ size 404770145
pytorch_model-00020-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc111534af81249f501236ab2879f195f2c06007a6c8dca9333abf3c0d3ed476
3
+ size 404770145
pytorch_model-00021-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25f027f668eb0e0520e434a9bf22f0b947384a44b842fa32a63feeb50a915687
3
+ size 404770145
pytorch_model-00022-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c3c5571d868e636e02e293bbde43da179ea8aecab2deec4862b473bc619195e
3
+ size 404770145
pytorch_model-00023-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93c520e0cc022703c2d2df2b3e3cb550e9d43956a3e40359c0cf176c00e8f1fa
3
+ size 404770145
pytorch_model-00024-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbd0502f9538f4b8362dbce4dce743bf3ff536ee292c2185f39c2962deefe21c
3
+ size 404770145
pytorch_model-00025-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c5c94073da5639f4b7033188a4861196268fbd0c5d12f6639c63f1d737cd5ea
3
+ size 404770145
pytorch_model-00026-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41fec1041e1fd03ac77c318148845c665ab81b1a437c193686ce1d52e2baf922
3
+ size 404770145
pytorch_model-00027-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fc3039c09d4cb06e7ecf60011928cccbce65fab5fbb612e3a692b48f7b0e0a4
3
+ size 404770145
pytorch_model-00028-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3de19a551675ec2bb125c0cd006345b17bf82ca25c89170d1e9a15db98b045d
3
+ size 404770145
pytorch_model-00029-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0dc7dd8842cd59768585ff29d66be2c8e1eecfa1fdc2f5e5aacf3fff83cd868
3
+ size 404770145
pytorch_model-00030-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d1be928100f85b7538f7bba9706e1b9eabd1de9de2253ee511133b0434453b3
3
+ size 404770145
pytorch_model-00031-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67abf02ec2bca60b6e18351627368f312294c18bd9f34be33ce922d8bc706c97
3
+ size 404770145
pytorch_model-00032-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cc51fc0d9a5c195b52cd83a8ae00029dfb4a8b6e5724cf191cdbd5f76e4cec7
3
+ size 404770145
pytorch_model-00033-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd4b51f1158d24f8ec33413e3a01bb415db923ee4a9fcac42a7ee07428199099
3
+ size 404770145
pytorch_model-00034-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c1eab4cdbb0b00cab806b78753c35c1f56a7cb6f64d17a196fb61fe005df384
3
+ size 404778610
pytorch_model-00035-of-00035.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:587eaed49ee9e8ca1e5dac03ee8621ddfc3d3a7d1eae18e895d5134fedb079ca
3
+ size 524288938
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,266 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14001127424
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00035-of-00035.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00002-of-00035.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00003-of-00035.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00003-of-00035.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00003-of-00035.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00003-of-00035.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00003-of-00035.bin",
13
+ "model.layers.0.self_attn.W_pack.weight": "pytorch_model-00003-of-00035.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00003-of-00035.bin",
15
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00035.bin",
16
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00004-of-00035.bin",
17
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00004-of-00035.bin",
18
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00004-of-00035.bin",
19
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00004-of-00035.bin",
20
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00004-of-00035.bin",
21
+ "model.layers.1.self_attn.W_pack.weight": "pytorch_model-00004-of-00035.bin",
22
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00004-of-00035.bin",
23
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00035.bin",
24
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00013-of-00035.bin",
25
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00013-of-00035.bin",
26
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00013-of-00035.bin",
27
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00013-of-00035.bin",
28
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00013-of-00035.bin",
29
+ "model.layers.10.self_attn.W_pack.weight": "pytorch_model-00013-of-00035.bin",
30
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00013-of-00035.bin",
31
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00035.bin",
32
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00014-of-00035.bin",
33
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00014-of-00035.bin",
34
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00014-of-00035.bin",
35
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00014-of-00035.bin",
36
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00014-of-00035.bin",
37
+ "model.layers.11.self_attn.W_pack.weight": "pytorch_model-00014-of-00035.bin",
38
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00014-of-00035.bin",
39
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00035.bin",
40
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00015-of-00035.bin",
41
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00015-of-00035.bin",
42
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00015-of-00035.bin",
43
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00015-of-00035.bin",
44
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00015-of-00035.bin",
45
+ "model.layers.12.self_attn.W_pack.weight": "pytorch_model-00015-of-00035.bin",
46
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00015-of-00035.bin",
47
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00035.bin",
48
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00016-of-00035.bin",
49
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00016-of-00035.bin",
50
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00016-of-00035.bin",
51
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00016-of-00035.bin",
52
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00016-of-00035.bin",
53
+ "model.layers.13.self_attn.W_pack.weight": "pytorch_model-00016-of-00035.bin",
54
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00016-of-00035.bin",
55
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00035.bin",
56
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00017-of-00035.bin",
57
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00017-of-00035.bin",
58
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00017-of-00035.bin",
59
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00017-of-00035.bin",
60
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00017-of-00035.bin",
61
+ "model.layers.14.self_attn.W_pack.weight": "pytorch_model-00017-of-00035.bin",
62
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00017-of-00035.bin",
63
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00035.bin",
64
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00018-of-00035.bin",
65
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00018-of-00035.bin",
66
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00018-of-00035.bin",
67
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00018-of-00035.bin",
68
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00018-of-00035.bin",
69
+ "model.layers.15.self_attn.W_pack.weight": "pytorch_model-00018-of-00035.bin",
70
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00018-of-00035.bin",
71
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00035.bin",
72
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00019-of-00035.bin",
73
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00019-of-00035.bin",
74
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00019-of-00035.bin",
75
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00019-of-00035.bin",
76
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00019-of-00035.bin",
77
+ "model.layers.16.self_attn.W_pack.weight": "pytorch_model-00019-of-00035.bin",
78
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00019-of-00035.bin",
79
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00035.bin",
80
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00020-of-00035.bin",
81
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00020-of-00035.bin",
82
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00020-of-00035.bin",
83
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00020-of-00035.bin",
84
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00020-of-00035.bin",
85
+ "model.layers.17.self_attn.W_pack.weight": "pytorch_model-00020-of-00035.bin",
86
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00020-of-00035.bin",
87
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00035.bin",
88
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00021-of-00035.bin",
89
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00021-of-00035.bin",
90
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00021-of-00035.bin",
91
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00021-of-00035.bin",
92
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00021-of-00035.bin",
93
+ "model.layers.18.self_attn.W_pack.weight": "pytorch_model-00021-of-00035.bin",
94
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00021-of-00035.bin",
95
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00035.bin",
96
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00022-of-00035.bin",
97
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00022-of-00035.bin",
98
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00022-of-00035.bin",
99
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00022-of-00035.bin",
100
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00022-of-00035.bin",
101
+ "model.layers.19.self_attn.W_pack.weight": "pytorch_model-00022-of-00035.bin",
102
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00022-of-00035.bin",
103
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00035.bin",
104
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00005-of-00035.bin",
105
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00005-of-00035.bin",
106
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00005-of-00035.bin",
107
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00005-of-00035.bin",
108
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00005-of-00035.bin",
109
+ "model.layers.2.self_attn.W_pack.weight": "pytorch_model-00005-of-00035.bin",
110
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00005-of-00035.bin",
111
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00035.bin",
112
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00023-of-00035.bin",
113
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00023-of-00035.bin",
114
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00023-of-00035.bin",
115
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00023-of-00035.bin",
116
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00023-of-00035.bin",
117
+ "model.layers.20.self_attn.W_pack.weight": "pytorch_model-00023-of-00035.bin",
118
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00023-of-00035.bin",
119
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00035.bin",
120
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00024-of-00035.bin",
121
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00024-of-00035.bin",
122
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00024-of-00035.bin",
123
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00024-of-00035.bin",
124
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00024-of-00035.bin",
125
+ "model.layers.21.self_attn.W_pack.weight": "pytorch_model-00024-of-00035.bin",
126
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00024-of-00035.bin",
127
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00035.bin",
128
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00025-of-00035.bin",
129
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00025-of-00035.bin",
130
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00025-of-00035.bin",
131
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00025-of-00035.bin",
132
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00025-of-00035.bin",
133
+ "model.layers.22.self_attn.W_pack.weight": "pytorch_model-00025-of-00035.bin",
134
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00025-of-00035.bin",
135
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00035.bin",
136
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00026-of-00035.bin",
137
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00026-of-00035.bin",
138
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00026-of-00035.bin",
139
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00026-of-00035.bin",
140
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00026-of-00035.bin",
141
+ "model.layers.23.self_attn.W_pack.weight": "pytorch_model-00026-of-00035.bin",
142
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00026-of-00035.bin",
143
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00035.bin",
144
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00027-of-00035.bin",
145
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00027-of-00035.bin",
146
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00027-of-00035.bin",
147
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00027-of-00035.bin",
148
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00027-of-00035.bin",
149
+ "model.layers.24.self_attn.W_pack.weight": "pytorch_model-00027-of-00035.bin",
150
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00027-of-00035.bin",
151
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00035.bin",
152
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00028-of-00035.bin",
153
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00028-of-00035.bin",
154
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00028-of-00035.bin",
155
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00028-of-00035.bin",
156
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00028-of-00035.bin",
157
+ "model.layers.25.self_attn.W_pack.weight": "pytorch_model-00028-of-00035.bin",
158
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00028-of-00035.bin",
159
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00028-of-00035.bin",
160
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00029-of-00035.bin",
161
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00029-of-00035.bin",
162
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00029-of-00035.bin",
163
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00029-of-00035.bin",
164
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00029-of-00035.bin",
165
+ "model.layers.26.self_attn.W_pack.weight": "pytorch_model-00029-of-00035.bin",
166
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00029-of-00035.bin",
167
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00035.bin",
168
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00030-of-00035.bin",
169
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00030-of-00035.bin",
170
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00030-of-00035.bin",
171
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00030-of-00035.bin",
172
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00030-of-00035.bin",
173
+ "model.layers.27.self_attn.W_pack.weight": "pytorch_model-00030-of-00035.bin",
174
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00030-of-00035.bin",
175
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00030-of-00035.bin",
176
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00031-of-00035.bin",
177
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00031-of-00035.bin",
178
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00031-of-00035.bin",
179
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00031-of-00035.bin",
180
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00031-of-00035.bin",
181
+ "model.layers.28.self_attn.W_pack.weight": "pytorch_model-00031-of-00035.bin",
182
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00031-of-00035.bin",
183
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00035.bin",
184
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00032-of-00035.bin",
185
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00032-of-00035.bin",
186
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00032-of-00035.bin",
187
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00032-of-00035.bin",
188
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00032-of-00035.bin",
189
+ "model.layers.29.self_attn.W_pack.weight": "pytorch_model-00032-of-00035.bin",
190
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00032-of-00035.bin",
191
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00032-of-00035.bin",
192
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00006-of-00035.bin",
193
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00006-of-00035.bin",
194
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00006-of-00035.bin",
195
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00006-of-00035.bin",
196
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00006-of-00035.bin",
197
+ "model.layers.3.self_attn.W_pack.weight": "pytorch_model-00006-of-00035.bin",
198
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00006-of-00035.bin",
199
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00035.bin",
200
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00033-of-00035.bin",
201
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00033-of-00035.bin",
202
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00033-of-00035.bin",
203
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00033-of-00035.bin",
204
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00033-of-00035.bin",
205
+ "model.layers.30.self_attn.W_pack.weight": "pytorch_model-00033-of-00035.bin",
206
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00033-of-00035.bin",
207
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00033-of-00035.bin",
208
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00034-of-00035.bin",
209
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00034-of-00035.bin",
210
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00034-of-00035.bin",
211
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00034-of-00035.bin",
212
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00034-of-00035.bin",
213
+ "model.layers.31.self_attn.W_pack.weight": "pytorch_model-00034-of-00035.bin",
214
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00034-of-00035.bin",
215
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00034-of-00035.bin",
216
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00007-of-00035.bin",
217
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00007-of-00035.bin",
218
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00007-of-00035.bin",
219
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00007-of-00035.bin",
220
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00007-of-00035.bin",
221
+ "model.layers.4.self_attn.W_pack.weight": "pytorch_model-00007-of-00035.bin",
222
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00007-of-00035.bin",
223
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00035.bin",
224
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00008-of-00035.bin",
225
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00008-of-00035.bin",
226
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00008-of-00035.bin",
227
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00008-of-00035.bin",
228
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00008-of-00035.bin",
229
+ "model.layers.5.self_attn.W_pack.weight": "pytorch_model-00008-of-00035.bin",
230
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00008-of-00035.bin",
231
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00035.bin",
232
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00009-of-00035.bin",
233
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00009-of-00035.bin",
234
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00009-of-00035.bin",
235
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00009-of-00035.bin",
236
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00009-of-00035.bin",
237
+ "model.layers.6.self_attn.W_pack.weight": "pytorch_model-00009-of-00035.bin",
238
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00009-of-00035.bin",
239
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00035.bin",
240
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00010-of-00035.bin",
241
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00010-of-00035.bin",
242
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00010-of-00035.bin",
243
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00010-of-00035.bin",
244
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00010-of-00035.bin",
245
+ "model.layers.7.self_attn.W_pack.weight": "pytorch_model-00010-of-00035.bin",
246
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00010-of-00035.bin",
247
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00035.bin",
248
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00011-of-00035.bin",
249
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00011-of-00035.bin",
250
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00011-of-00035.bin",
251
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00011-of-00035.bin",
252
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00011-of-00035.bin",
253
+ "model.layers.8.self_attn.W_pack.weight": "pytorch_model-00011-of-00035.bin",
254
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00011-of-00035.bin",
255
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00035.bin",
256
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00012-of-00035.bin",
257
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00012-of-00035.bin",
258
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00012-of-00035.bin",
259
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00012-of-00035.bin",
260
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00012-of-00035.bin",
261
+ "model.layers.9.self_attn.W_pack.weight": "pytorch_model-00012-of-00035.bin",
262
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00012-of-00035.bin",
263
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00035.bin",
264
+ "model.norm.weight": "pytorch_model-00034-of-00035.bin"
265
+ }
266
+ }