minnmamin commited on
Commit
e48b23f
1 Parent(s): 00d602d

Upload LlamaForCausalLM

Browse files
README.md CHANGED
@@ -4,6 +4,7 @@ tags:
4
  - llama3
5
  - flying-manual
6
  - ai-tutoring
 
7
  ---
8
 
9
  # Model Card for Llama3-8b-FlyingManual-Tutor
 
4
  - llama3
5
  - flying-manual
6
  - ai-tutoring
7
+ - llama-factory
8
  ---
9
 
10
  # Model Card for Llama3-8b-FlyingManual-Tutor
config.json CHANGED
@@ -1,17 +1,17 @@
1
  {
2
- "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 128000,
9
- "eos_token_id": 128009,
10
  "hidden_act": "silu",
11
  "hidden_size": 4096,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 14336,
14
- "max_position_embeddings": 8192,
15
  "mlp_bias": false,
16
  "model_type": "llama",
17
  "num_attention_heads": 32,
@@ -19,11 +19,17 @@
19
  "num_key_value_heads": 8,
20
  "pretraining_tp": 1,
21
  "rms_norm_eps": 1e-05,
22
- "rope_scaling": null,
 
 
 
 
 
 
23
  "rope_theta": 500000.0,
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
- "transformers_version": "4.42.4",
27
  "use_cache": true,
28
  "vocab_size": 128256
29
  }
 
1
  {
2
+ "_name_or_path": "meta-llama/Meta-Llama-3.1-8B",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
  "hidden_act": "silu",
11
  "hidden_size": 4096,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 14336,
14
+ "max_position_embeddings": 131072,
15
  "mlp_bias": false,
16
  "model_type": "llama",
17
  "num_attention_heads": 32,
 
19
  "num_key_value_heads": 8,
20
  "pretraining_tp": 1,
21
  "rms_norm_eps": 1e-05,
22
+ "rope_scaling": {
23
+ "factor": 8.0,
24
+ "high_freq_factor": 4.0,
25
+ "low_freq_factor": 1.0,
26
+ "original_max_position_embeddings": 8192,
27
+ "rope_type": "llama3"
28
+ },
29
  "rope_theta": 500000.0,
30
  "tie_word_embeddings": false,
31
  "torch_dtype": "bfloat16",
32
+ "transformers_version": "4.43.1",
33
  "use_cache": true,
34
  "vocab_size": 128256
35
  }
generation_config.json CHANGED
@@ -1,12 +1,9 @@
1
  {
 
2
  "bos_token_id": 128000,
3
  "do_sample": true,
4
- "eos_token_id": [
5
- 128001,
6
- 128009
7
- ],
8
- "max_length": 4096,
9
  "temperature": 0.6,
10
  "top_p": 0.9,
11
- "transformers_version": "4.42.4"
12
  }
 
1
  {
2
+ "_from_model_config": true,
3
  "bos_token_id": 128000,
4
  "do_sample": true,
5
+ "eos_token_id": 128001,
 
 
 
 
6
  "temperature": 0.6,
7
  "top_p": 0.9,
8
+ "transformers_version": "4.43.1"
9
  }
model-00001-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66e5e13670a5f2a07378fd521c50483e1727252df07b0bd871e22a7fc1108789
3
+ size 1050673296
model-00002-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcee88643c7bd91ac1643917992705e3e8017f9ce631d58c98bc03b9444ba849
3
+ size 956336616
model-00003-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f84509cf6e3b0323debf5ab48826cbc17430fe004961795b9387be1bf58a65ff
3
+ size 989890696
model-00004-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb13387d9beaf901b346237dcffd19b37994afe7554e7798eac3daea35fb559f
3
+ size 989890696
model-00005-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe501e7ea682999ef4692143f5ef76c1c56bf04dc6dac652853aff13fc0d14f3
3
+ size 989907312
model-00006-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f3c657b1e0b4872e0dc0fa79dc01095c2f50aacaa599d751ae57bfb67b506b7
3
+ size 956336624
model-00007-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8b274d10a0de44095267fcb490635ff9d00bc53f2cd5197c4e4d4018f0aa8ba
3
+ size 989890720
model-00008-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efc800bde79f7cbea8ef398219e0d8b80e754948b4113fcdcf2fed729918b96a
3
+ size 989890712
model-00009-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70461ca59793d50b5f54688e679451c0cacacea4da55aa5692be2eb97ea2fec9
3
+ size 989907328
model-00010-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36877890391b4ccaa961b7f174ccc1cd83f60d2afcf220059c8ccc686c195e31
3
+ size 956336632
model-00011-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37271f16a7d51576c89eb888af36234b63847d020d0dc9347680827bc19e3772
3
+ size 989890720
model-00012-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3925f0c283149dad3fb19c263f09a08bd37a3c6f207ff088617cebe9d2a781dc
3
+ size 989890712
model-00013-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64a6459244702a87d63b8f5b40652808df706f44ce3d4d6c887f7abe7edd6557
3
+ size 989907328
model-00014-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1199dce60739e71b5579ba3a6f63938cde8bcda9d3fb09d9d07242019a86ed04
3
+ size 956336632
model-00015-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79ab3708fd02951386c201ce2be7d983ee201e323d86b05a83c9065770446654
3
+ size 989890720
model-00016-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6feef628d893df7809d975f4c3a109a655e5e4126ac4ee28e8e0464504c86b12
3
+ size 1050673280
model-00017-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:868399f22814870751dfbf6d453e955f6e9902b688a37131355f36033f43da33
3
+ size 234906168
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00016-of-00017.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00017.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00002-of-00017.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00002-of-00017.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00006-of-00017.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00007-of-00017.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00007-of-00017.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00008-of-00017.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00008-of-00017.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00009-of-00017.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00009-of-00017.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00009-of-00017.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00010-of-00017.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00010-of-00017.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00003-of-00017.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00011-of-00017.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00011-of-00017.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00012-of-00017.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00012-of-00017.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00013-of-00017.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00013-of-00017.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00013-of-00017.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00014-of-00017.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00014-of-00017.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00015-of-00017.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00003-of-00017.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00015-of-00017.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00017-of-00017.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00017-of-00017.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00017-of-00017.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00004-of-00017.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00004-of-00017.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00005-of-00017.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00005-of-00017.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00005-of-00017.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00006-of-00017.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
296
+ "model.norm.weight": "model-00017-of-00017.safetensors"
297
+ }
298
+ }