sharpbai commited on
Commit
7dfbe29
·
1 Parent(s): cb927f3

Upload LlamaForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sharpbai/open_llama_7b",
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": "4.30.1",
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": "4.30.1"
7
+ }
pytorch_model-00001-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fb3ade8ad6e7cded084182473792dc81631e43cd0d6989eb3ff60172edee2c7
3
+ size 396364479
pytorch_model-00002-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b050f25dea7cef22f5d3aac4aa6b78527dcf31fcb2da1c6df4c1211be78d7b40
3
+ size 404770755
pytorch_model-00003-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39dcec8573f09dccf8d99e9c8b2226dad588ba8f4755c59de52088ee693bac61
3
+ size 404770755
pytorch_model-00004-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d86d0b4b3c0d73cd684c69c32e119513337dfed090e6cfe5986d4d15d41920a6
3
+ size 404770755
pytorch_model-00005-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3115aa1981823fd8e1e320f99bd7b91e862b96fc66f00b0f9df6aa83d35d8edc
3
+ size 404770755
pytorch_model-00006-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d83041eb94d75f0a6d0db402bc3dced9fbde3fa36880ee2a013bd05950121a39
3
+ size 404770755
pytorch_model-00007-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3afbae3324cf2e1e02718188c2786c768777a4b6ec62ae111beb60f3901412d5
3
+ size 404770755
pytorch_model-00008-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb2c57e77ec77b87518f68f03150858a20cfe83f6f977ac41869f4c6601291f7
3
+ size 404770755
pytorch_model-00009-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:482bbdd5b39b0cf2618ddc57d2ecbf28b2a583ff4066cba2bbc500545dd53435
3
+ size 404770755
pytorch_model-00010-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07ac75818db308d32d79340b9d26de1a809d6f5e7a3290be87f14719f160d27e
3
+ size 404770755
pytorch_model-00011-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:227d73d64eb050e59088ce2c9fc57caf543cac7f3e32045e717b5882ea1dc396
3
+ size 404770755
pytorch_model-00012-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9b609aac5df28af81ec17e44613763186fed9f19fa36b2908d79cd44949060d
3
+ size 404770755
pytorch_model-00013-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4464d5ba470e5be2095f8224269b2da2edf8baf3cb5f6b936cca9d6f7f8d2f4
3
+ size 404770755
pytorch_model-00014-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5da4be66f549d851d5f4b9cf9707afc75894e8ad8bbefe135a3d1c81aeb0a95
3
+ size 404770755
pytorch_model-00015-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:040c1e2c3350c865f751708548759494bd9cc43f9ae30b9e4b5ebee30bbdaa68
3
+ size 404770755
pytorch_model-00016-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70bb062e6278021b636d044be03bce8f347243956b65b2ef68db558d29d06b28
3
+ size 404770755
pytorch_model-00017-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aae520d21419355f3a47ba8bb328fea5814f62001b3306fbb4577d6235708147
3
+ size 404770755
pytorch_model-00018-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfc25c0f9417551c77ecd5d54b13eef9549d3bb3f30a0ac7ff5defbe3a74a0bb
3
+ size 404770755
pytorch_model-00019-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64516d21f6c0a56f5dd5d2f966ed0749f2857a35cf30435f34edd29ddaf0833d
3
+ size 404770755
pytorch_model-00020-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c56979165300ccd4e3852edf325b9c1c0bd0a7ee63f5fe43a30975efe773faa1
3
+ size 404770755
pytorch_model-00021-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d465a495782478c2e97090b1258c33a3cd760addfddbfba08277f1ebbc17f09c
3
+ size 404770755
pytorch_model-00022-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9cbc2bdf98b81065ea6004294fbeee0546c160ccc7091c54917da54cb7f7f6b
3
+ size 404770755
pytorch_model-00023-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26096dc4e5b63f51ee0005e61d96d6c325c557fe5288bf08f24eefd6f8871d00
3
+ size 404770755
pytorch_model-00024-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e28e7368f6b106c860f12cc6f737737ed3485b2bfe6403ee30d4f8eba6810165
3
+ size 404770755
pytorch_model-00025-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0700f037621eb32e08009ef92f256ac5e9c46264adf73abbfb68eff79940a4d
3
+ size 404770755
pytorch_model-00026-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4d103a60269a6a902e1f56c083fa90200ca470755ed025810017b4f1f3498d6
3
+ size 404770755
pytorch_model-00027-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b5456e1e8b072ad38ce34bb56f6d330fce5aed59b18ffef222ae9e39dbd84ff
3
+ size 404770755
pytorch_model-00028-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:302a0dd85dab49551cda34d7596b73e24024f29d715293d948df1c8728f652b2
3
+ size 404770755
pytorch_model-00029-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e482c08041662a0194df1874d6d0cf67203ef832a15e398a676da74e3448d2f
3
+ size 404770755
pytorch_model-00030-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35bbb1ee4391aaa614f2a2bb308f9c933dc713cfc7a776e26becc1439dbc7d45
3
+ size 404770755
pytorch_model-00031-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d40a8f734ee0b6a9336ee6f8d9831cc905d86fbfe6a548cbe4ca59c89f4863a9
3
+ size 404770755
pytorch_model-00032-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80a7f70ec5a53e20faf83a0bf3bd6a1fe974327e9823d5a82ac1448ed2b30845
3
+ size 404770755
pytorch_model-00033-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:044ba706736f0517e024acc35f88abd00d24ecd6ce7d3bbd7f148625eafbb736
3
+ size 270559679
pytorch_model-00034-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04ffc13fe918f135f466a04d5042bf933476be5f32b4210a3bbdf2e6bc5a8c7d
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-00034-of-00034.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00034.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00034.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00034.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00034.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00034.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00034.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00034.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00034.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00034.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00034.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00034.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00034.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00003-of-00034.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00003-of-00034.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00003-of-00034.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00034.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00034.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00034.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00034.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00034.bin",
27
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00034.bin",
28
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00012-of-00034.bin",
29
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00012-of-00034.bin",
30
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00012-of-00034.bin",
31
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00012-of-00034.bin",
32
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00012-of-00034.bin",
33
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00011-of-00034.bin",
34
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00011-of-00034.bin",
35
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00011-of-00034.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00034.bin",
37
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00011-of-00034.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00013-of-00034.bin",
39
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00013-of-00034.bin",
40
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00013-of-00034.bin",
41
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00013-of-00034.bin",
42
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00013-of-00034.bin",
43
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00012-of-00034.bin",
44
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00012-of-00034.bin",
45
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00012-of-00034.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00034.bin",
47
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00012-of-00034.bin",
48
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00014-of-00034.bin",
49
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00014-of-00034.bin",
50
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00014-of-00034.bin",
51
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00014-of-00034.bin",
52
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00014-of-00034.bin",
53
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00013-of-00034.bin",
54
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00013-of-00034.bin",
55
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00013-of-00034.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00034.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00013-of-00034.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00015-of-00034.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00015-of-00034.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00015-of-00034.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00015-of-00034.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00015-of-00034.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00014-of-00034.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00014-of-00034.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00014-of-00034.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00034.bin",
67
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00014-of-00034.bin",
68
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00016-of-00034.bin",
69
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00016-of-00034.bin",
70
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00016-of-00034.bin",
71
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00016-of-00034.bin",
72
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00016-of-00034.bin",
73
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00015-of-00034.bin",
74
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00015-of-00034.bin",
75
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00015-of-00034.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00034.bin",
77
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00015-of-00034.bin",
78
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00017-of-00034.bin",
79
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00017-of-00034.bin",
80
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00017-of-00034.bin",
81
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00017-of-00034.bin",
82
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00017-of-00034.bin",
83
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00016-of-00034.bin",
84
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00016-of-00034.bin",
85
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00016-of-00034.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00034.bin",
87
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00016-of-00034.bin",
88
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00018-of-00034.bin",
89
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00018-of-00034.bin",
90
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00018-of-00034.bin",
91
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00018-of-00034.bin",
92
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00018-of-00034.bin",
93
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00017-of-00034.bin",
94
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00017-of-00034.bin",
95
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00017-of-00034.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00034.bin",
97
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00017-of-00034.bin",
98
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00019-of-00034.bin",
99
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00019-of-00034.bin",
100
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00019-of-00034.bin",
101
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00019-of-00034.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00019-of-00034.bin",
103
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00018-of-00034.bin",
104
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00018-of-00034.bin",
105
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00018-of-00034.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00034.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00018-of-00034.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00020-of-00034.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00020-of-00034.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00020-of-00034.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00020-of-00034.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00020-of-00034.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00019-of-00034.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00019-of-00034.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00019-of-00034.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00034.bin",
117
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00019-of-00034.bin",
118
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00021-of-00034.bin",
119
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00021-of-00034.bin",
120
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00021-of-00034.bin",
121
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00021-of-00034.bin",
122
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00021-of-00034.bin",
123
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00020-of-00034.bin",
124
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00020-of-00034.bin",
125
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00020-of-00034.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00034.bin",
127
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00020-of-00034.bin",
128
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00004-of-00034.bin",
129
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00004-of-00034.bin",
130
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00004-of-00034.bin",
131
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00004-of-00034.bin",
132
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00004-of-00034.bin",
133
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00034.bin",
134
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00003-of-00034.bin",
135
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00034.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00034.bin",
137
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00034.bin",
138
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00022-of-00034.bin",
139
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00022-of-00034.bin",
140
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00022-of-00034.bin",
141
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00022-of-00034.bin",
142
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00022-of-00034.bin",
143
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00021-of-00034.bin",
144
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00021-of-00034.bin",
145
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00021-of-00034.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00034.bin",
147
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00021-of-00034.bin",
148
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00023-of-00034.bin",
149
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00023-of-00034.bin",
150
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00023-of-00034.bin",
151
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00023-of-00034.bin",
152
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00023-of-00034.bin",
153
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00022-of-00034.bin",
154
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00022-of-00034.bin",
155
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00022-of-00034.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00034.bin",
157
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00022-of-00034.bin",
158
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00024-of-00034.bin",
159
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00024-of-00034.bin",
160
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00024-of-00034.bin",
161
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00024-of-00034.bin",
162
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00024-of-00034.bin",
163
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00023-of-00034.bin",
164
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00023-of-00034.bin",
165
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00023-of-00034.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00034.bin",
167
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00023-of-00034.bin",
168
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00025-of-00034.bin",
169
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00025-of-00034.bin",
170
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00025-of-00034.bin",
171
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00025-of-00034.bin",
172
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00025-of-00034.bin",
173
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00024-of-00034.bin",
174
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00024-of-00034.bin",
175
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00024-of-00034.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00034.bin",
177
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00024-of-00034.bin",
178
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00026-of-00034.bin",
179
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00026-of-00034.bin",
180
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00026-of-00034.bin",
181
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00026-of-00034.bin",
182
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00026-of-00034.bin",
183
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00025-of-00034.bin",
184
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00025-of-00034.bin",
185
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00025-of-00034.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00034.bin",
187
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00025-of-00034.bin",
188
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00027-of-00034.bin",
189
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00027-of-00034.bin",
190
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00027-of-00034.bin",
191
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00027-of-00034.bin",
192
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00027-of-00034.bin",
193
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00026-of-00034.bin",
194
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00026-of-00034.bin",
195
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00026-of-00034.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00034.bin",
197
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00026-of-00034.bin",
198
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00028-of-00034.bin",
199
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00028-of-00034.bin",
200
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00028-of-00034.bin",
201
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00028-of-00034.bin",
202
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00028-of-00034.bin",
203
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00027-of-00034.bin",
204
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00027-of-00034.bin",
205
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00027-of-00034.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00034.bin",
207
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00027-of-00034.bin",
208
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00029-of-00034.bin",
209
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00029-of-00034.bin",
210
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00029-of-00034.bin",
211
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00029-of-00034.bin",
212
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00029-of-00034.bin",
213
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00028-of-00034.bin",
214
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00028-of-00034.bin",
215
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00028-of-00034.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00028-of-00034.bin",
217
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00028-of-00034.bin",
218
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00030-of-00034.bin",
219
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00030-of-00034.bin",
220
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00030-of-00034.bin",
221
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00030-of-00034.bin",
222
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00030-of-00034.bin",
223
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00029-of-00034.bin",
224
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00029-of-00034.bin",
225
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00029-of-00034.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00034.bin",
227
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00029-of-00034.bin",
228
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00031-of-00034.bin",
229
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00031-of-00034.bin",
230
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00031-of-00034.bin",
231
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00031-of-00034.bin",
232
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00031-of-00034.bin",
233
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00030-of-00034.bin",
234
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00030-of-00034.bin",
235
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00030-of-00034.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00030-of-00034.bin",
237
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00030-of-00034.bin",
238
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00005-of-00034.bin",
239
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00005-of-00034.bin",
240
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00005-of-00034.bin",
241
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00005-of-00034.bin",
242
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00005-of-00034.bin",
243
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00004-of-00034.bin",
244
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00004-of-00034.bin",
245
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00004-of-00034.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00034.bin",
247
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00004-of-00034.bin",
248
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00032-of-00034.bin",
249
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00032-of-00034.bin",
250
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00032-of-00034.bin",
251
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00032-of-00034.bin",
252
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00032-of-00034.bin",
253
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00031-of-00034.bin",
254
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00031-of-00034.bin",
255
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00031-of-00034.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00034.bin",
257
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00031-of-00034.bin",
258
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00033-of-00034.bin",
259
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00033-of-00034.bin",
260
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00033-of-00034.bin",
261
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00033-of-00034.bin",
262
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00033-of-00034.bin",
263
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00032-of-00034.bin",
264
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00032-of-00034.bin",
265
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00032-of-00034.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00032-of-00034.bin",
267
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00032-of-00034.bin",
268
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00006-of-00034.bin",
269
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00006-of-00034.bin",
270
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00006-of-00034.bin",
271
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00006-of-00034.bin",
272
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00006-of-00034.bin",
273
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00005-of-00034.bin",
274
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00005-of-00034.bin",
275
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00005-of-00034.bin",
276
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00034.bin",
277
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00005-of-00034.bin",
278
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00007-of-00034.bin",
279
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00007-of-00034.bin",
280
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00007-of-00034.bin",
281
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00007-of-00034.bin",
282
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00007-of-00034.bin",
283
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00006-of-00034.bin",
284
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00006-of-00034.bin",
285
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00006-of-00034.bin",
286
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00034.bin",
287
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00006-of-00034.bin",
288
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00008-of-00034.bin",
289
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00008-of-00034.bin",
290
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00008-of-00034.bin",
291
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00008-of-00034.bin",
292
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00008-of-00034.bin",
293
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00007-of-00034.bin",
294
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00007-of-00034.bin",
295
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00007-of-00034.bin",
296
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00034.bin",
297
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00007-of-00034.bin",
298
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00009-of-00034.bin",
299
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00009-of-00034.bin",
300
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00009-of-00034.bin",
301
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00009-of-00034.bin",
302
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00009-of-00034.bin",
303
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00008-of-00034.bin",
304
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00008-of-00034.bin",
305
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00008-of-00034.bin",
306
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00034.bin",
307
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00008-of-00034.bin",
308
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00010-of-00034.bin",
309
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00010-of-00034.bin",
310
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00010-of-00034.bin",
311
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00010-of-00034.bin",
312
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00010-of-00034.bin",
313
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00009-of-00034.bin",
314
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00009-of-00034.bin",
315
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00009-of-00034.bin",
316
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00034.bin",
317
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00009-of-00034.bin",
318
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00011-of-00034.bin",
319
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00011-of-00034.bin",
320
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00011-of-00034.bin",
321
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00011-of-00034.bin",
322
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00011-of-00034.bin",
323
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00010-of-00034.bin",
324
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00010-of-00034.bin",
325
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00010-of-00034.bin",
326
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00034.bin",
327
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00010-of-00034.bin",
328
+ "model.norm.weight": "pytorch_model-00033-of-00034.bin"
329
+ }
330
+ }