Yukang commited on
Commit
8e96c26
1 Parent(s): ca13fe3

update to alpaca-13b

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 32000
3
+ }
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/dataset/yukangchen/hf_models/sft-models/Llama-2-13b-chat-longlora-32k-sft",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -14,11 +14,15 @@
14
  "num_attention_heads": 40,
15
  "num_hidden_layers": 40,
16
  "num_key_value_heads": 40,
 
17
  "pretraining_tp": 1,
18
  "rms_norm_eps": 1e-05,
19
- "rope_scaling": null,
 
 
 
20
  "tie_word_embeddings": false,
21
- "torch_dtype": "float16",
22
  "transformers_version": "4.31.0",
23
  "use_cache": true,
24
  "vocab_size": 32001
 
1
  {
2
+ "_name_or_path": "/dataset/pretrained-models/Llama-2-13b-chat-hf",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
14
  "num_attention_heads": 40,
15
  "num_hidden_layers": 40,
16
  "num_key_value_heads": 40,
17
+ "pad_token_id": 0,
18
  "pretraining_tp": 1,
19
  "rms_norm_eps": 1e-05,
20
+ "rope_scaling": {
21
+ "factor": 8.0,
22
+ "type": "linear"
23
+ },
24
  "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
  "transformers_version": "4.31.0",
27
  "use_cache": true,
28
  "vocab_size": 32001
generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 2,
5
- "transformers_version": "4.31.0"
6
- }
 
 
 
 
 
 
 
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7004f96184372b0d7f8615bbea40dde597d9dc2644bd4cd739bb55108e77602d
3
+ size 9956547112
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a29ae775bdb4f5504ddb6f2d68c413bc670a47e4a12f99f1a4086d0fee940233
3
+ size 9940838856
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a8d40ee13184b7381f70f0416b32601ab65d4762a45935489bcf987348c2be7
3
+ size 9940839248
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9772c2bae2cf86070b4aea601f1bb0e2e0b3b16b84babb2dc0a2d01a839fb1dc
3
+ size 9867397864
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43a99188500fea557549bd052d6841cf3e156572d969cd7cf64d22a150e20f69
3
+ size 9867439056
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fe91cef23013939dee1d382877b612c359daff7a632feb9c53cda39a13b6c84
3
+ size 2490492968
model.safetensors.index.json ADDED
@@ -0,0 +1,410 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 52063508480
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00006-of-00006.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
17
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
18
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
19
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
20
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
21
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
22
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
23
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
24
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
25
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
27
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
28
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
29
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
30
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
31
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
32
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
33
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
34
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
35
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
37
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
38
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
39
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
40
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
41
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
42
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
43
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
44
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
45
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
47
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
48
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
49
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
50
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
51
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
52
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
53
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
54
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
55
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
57
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
58
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
59
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
60
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
61
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
62
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
63
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
64
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
65
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
67
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
68
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
69
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
70
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
71
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
72
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
73
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
74
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
75
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
77
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
78
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
79
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
80
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
81
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
82
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
83
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
84
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
85
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
87
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
88
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
89
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
90
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
91
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
92
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
93
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
94
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
95
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
97
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
98
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
99
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
100
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
101
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
102
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
103
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
104
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
105
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
107
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
108
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
109
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
110
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
111
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
112
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
113
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
114
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
115
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
117
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
118
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
119
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
120
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
121
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
122
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
123
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
124
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
125
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
127
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
128
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
129
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
130
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
131
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
132
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
133
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
134
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
135
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
137
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
138
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
139
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
140
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
141
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
142
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
143
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
144
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
145
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
147
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
148
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
149
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
150
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
151
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
152
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
153
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
154
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
155
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
157
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
158
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
159
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
160
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
161
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
162
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
163
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
164
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
165
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
167
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
168
+ "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
169
+ "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
170
+ "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
171
+ "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
172
+ "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
173
+ "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
174
+ "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
175
+ "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
177
+ "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
178
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
179
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
180
+ "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
181
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
182
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
183
+ "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
184
+ "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
185
+ "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
187
+ "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
188
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
189
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
190
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
191
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
192
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
193
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
194
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
195
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
197
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
198
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
199
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
200
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
201
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
202
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
203
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
204
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
205
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
207
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
208
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
209
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
210
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
211
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
212
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
213
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
214
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
215
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
217
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
218
+ "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
219
+ "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
220
+ "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
221
+ "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
222
+ "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
223
+ "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
224
+ "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
225
+ "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
227
+ "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
228
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
229
+ "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
230
+ "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
231
+ "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
232
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
233
+ "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
234
+ "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
235
+ "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
237
+ "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
238
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
239
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
240
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
241
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
242
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
243
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
244
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
245
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
247
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
248
+ "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
249
+ "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
250
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
251
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
252
+ "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
253
+ "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
254
+ "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
255
+ "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
257
+ "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
258
+ "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
259
+ "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
260
+ "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
261
+ "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
262
+ "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
263
+ "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
264
+ "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
265
+ "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
267
+ "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
268
+ "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
269
+ "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
270
+ "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
271
+ "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
272
+ "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
273
+ "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
274
+ "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
275
+ "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
276
+ "model.layers.32.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
277
+ "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
278
+ "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
279
+ "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
280
+ "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
281
+ "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
282
+ "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
283
+ "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
284
+ "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
285
+ "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
286
+ "model.layers.33.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
287
+ "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
288
+ "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
289
+ "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
290
+ "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
291
+ "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
292
+ "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
293
+ "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
294
+ "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
295
+ "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
296
+ "model.layers.34.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
297
+ "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
298
+ "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
299
+ "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
300
+ "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
301
+ "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
302
+ "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
303
+ "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
304
+ "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
305
+ "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
306
+ "model.layers.35.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
307
+ "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
308
+ "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
309
+ "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
310
+ "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
311
+ "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
312
+ "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
313
+ "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
314
+ "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
315
+ "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
316
+ "model.layers.36.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
317
+ "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
318
+ "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
319
+ "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
320
+ "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
321
+ "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
322
+ "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
323
+ "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
324
+ "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
325
+ "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
326
+ "model.layers.37.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
327
+ "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
328
+ "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
329
+ "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
330
+ "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
331
+ "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
332
+ "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
333
+ "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
334
+ "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
335
+ "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
336
+ "model.layers.38.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
337
+ "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
338
+ "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
339
+ "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
340
+ "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
341
+ "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
342
+ "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
343
+ "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
344
+ "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
345
+ "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
346
+ "model.layers.39.self_attn.rotary_emb.inv_freq": "model-00006-of-00006.safetensors",
347
+ "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
348
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
349
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
350
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
351
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
352
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
353
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
354
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
355
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
356
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
357
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
358
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
359
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
360
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
361
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
362
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
363
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
364
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
365
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
366
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
367
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
368
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00006.safetensors",
369
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
370
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
371
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
372
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
373
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
374
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
375
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
376
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
377
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
378
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
379
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
380
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
381
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
382
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
383
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
384
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
385
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
386
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
387
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
388
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
389
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
390
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
391
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
392
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
393
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
394
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
395
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
396
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
397
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
398
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
399
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
400
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
401
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
402
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
403
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
404
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
405
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
406
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
407
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
408
+ "model.norm.weight": "model-00006-of-00006.safetensors"
409
+ }
410
+ }
pytorch_model-00001-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:612dfb98f13599d992ffc50b0e58fe2e88d9d086616b29afa4c221f92f30efac
3
+ size 9956565387
pytorch_model-00002-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3787b2fbfb678f78be7a68c4f8bb459c5b9edbd138a70d8f8e57c10b4e7f587c
3
+ size 9940857409
pytorch_model-00003-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab4508d3162ab16a9b150ffd1ffacd424df01d99749d9750e73f8f410b0a8f68
3
+ size 9940858031
pytorch_model-00004-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f34a9ebec64c75079758082fafe0dd24f3af2a63d6b14e9ecde2639184be6327
3
+ size 9867416377
pytorch_model-00005-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ca970ac3061ff91911d9394241a667d11dd4aa21fcd3f602a264eab18d2d7ae
3
+ size 9867458049
pytorch_model-00006-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:274f28f24117c10842f3623342f1cb9e3aa1c5913da1a05304663442784ea2b7
3
+ size 2490496879
pytorch_model.bin.index.json CHANGED
@@ -1,370 +1,410 @@
1
  {
2
  "metadata": {
3
- "total_size": 26031749120
4
  },
5
  "weight_map": {
6
- "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
- "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
8
- "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
9
- "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
10
- "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
11
- "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
12
- "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
13
- "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
14
- "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
15
- "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
16
- "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
17
- "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
18
- "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
19
- "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
20
- "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
21
- "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
22
- "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
23
- "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
24
- "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
25
- "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
26
- "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
27
- "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
28
- "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
29
- "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
30
- "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
31
- "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
32
- "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
33
- "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
34
- "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
35
- "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
36
- "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
37
- "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
38
- "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
39
- "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
40
- "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
41
- "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
42
- "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
43
- "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
44
- "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
45
- "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
46
- "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
47
- "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
48
- "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
49
- "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
50
- "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
51
- "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
52
- "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
53
- "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
54
- "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
55
- "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
56
- "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
57
- "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
58
- "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
59
- "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
60
- "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
61
- "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
62
- "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
63
- "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
64
- "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
65
- "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
66
- "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
67
- "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
68
- "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
69
- "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
70
- "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
71
- "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
72
- "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
73
- "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
74
- "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
75
- "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
76
- "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
77
- "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
78
- "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
79
- "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
80
- "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
81
- "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
82
- "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
83
- "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
84
- "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
85
- "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
86
- "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
87
- "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
88
- "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
89
- "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
90
- "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
91
- "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
92
- "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
93
- "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
94
- "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
95
- "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
96
- "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
97
- "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
98
- "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
99
- "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
100
- "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
101
- "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
102
- "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
103
- "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
104
- "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
105
- "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
106
- "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
107
- "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
108
- "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
109
- "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
110
- "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
111
- "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
112
- "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
113
- "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
114
- "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
115
- "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
116
- "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
117
- "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
118
- "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
119
- "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
120
- "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
121
- "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
122
- "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
123
- "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
124
- "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
125
- "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
126
- "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
127
- "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
128
- "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
129
- "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
130
- "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
131
- "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
132
- "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
133
- "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
134
- "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
135
- "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
136
- "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
137
- "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
138
- "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
139
- "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
140
- "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
141
- "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
142
- "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
143
- "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
144
- "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
145
- "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
146
- "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
147
- "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
148
- "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
149
- "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
150
- "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
151
- "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
152
- "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
153
- "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
154
- "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
155
- "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
156
- "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
157
- "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
158
- "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
159
- "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
160
- "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
161
- "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
162
- "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
163
- "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
164
- "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
165
- "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
166
- "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
167
- "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
168
- "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
169
- "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
170
- "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
171
- "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
172
- "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
173
- "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
174
- "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
175
- "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
176
- "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
177
- "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
178
- "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
179
- "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
180
- "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
181
- "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
182
- "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
183
- "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
184
- "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
185
- "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
186
- "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
187
- "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
188
- "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
189
- "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
190
- "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
191
- "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
192
- "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
193
- "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
194
- "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
195
- "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
196
- "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
197
- "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
198
- "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
199
- "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
200
- "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
201
- "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
202
- "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
203
- "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
204
- "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
205
- "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
206
- "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
207
- "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
208
- "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
209
- "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
210
- "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
211
- "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
212
- "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
213
- "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
214
- "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
215
- "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
216
- "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
217
- "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
218
- "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
219
- "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
220
- "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
221
- "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
222
- "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
223
- "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
224
- "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
225
- "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
226
- "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
227
- "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
228
- "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
229
- "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
230
- "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
231
- "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
232
- "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
233
- "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
234
- "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
235
- "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
236
- "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
237
- "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
238
- "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
239
- "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
240
- "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
241
- "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
242
- "model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
243
- "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
244
- "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
245
- "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
246
- "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
247
- "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
248
- "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
249
- "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
250
- "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
251
- "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
252
- "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
253
- "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
254
- "model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
255
- "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
256
- "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
257
- "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
258
- "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
259
- "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
260
- "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
261
- "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
262
- "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
263
- "model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
264
- "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
265
- "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
266
- "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
267
- "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
268
- "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
269
- "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
270
- "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
271
- "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
272
- "model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
273
- "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
274
- "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
275
- "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
276
- "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
277
- "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
278
- "model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
279
- "model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
280
- "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
281
- "model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
282
- "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
283
- "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
284
- "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
285
- "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
286
- "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
287
- "model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
288
- "model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
289
- "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
290
- "model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
291
- "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
292
- "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
293
- "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
294
- "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
295
- "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
296
- "model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
297
- "model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
298
- "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
299
- "model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
300
- "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
301
- "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
302
- "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
303
- "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
304
- "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
305
- "model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
306
- "model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
307
- "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
308
- "model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
309
- "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
310
- "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
311
- "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
312
- "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
313
- "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
314
- "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
315
- "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
316
- "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
317
- "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
318
- "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
319
- "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
320
- "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
321
- "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
322
- "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
323
- "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
324
- "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
325
- "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
326
- "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
327
- "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
328
- "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
329
- "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
330
- "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
331
- "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
332
- "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
333
- "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
334
- "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
335
- "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
336
- "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
337
- "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
338
- "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
339
- "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
340
- "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
341
- "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
342
- "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
343
- "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
344
- "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
345
- "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
346
- "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
347
- "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
348
- "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
349
- "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
350
- "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
351
- "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
352
- "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
353
- "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
354
- "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
355
- "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
356
- "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
357
- "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
358
- "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
359
- "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
360
- "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
361
- "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
362
- "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
363
- "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
364
- "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
365
- "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
366
- "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
367
- "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
368
- "model.norm.weight": "pytorch_model-00003-of-00003.bin"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
369
  }
370
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 52063508480
4
  },
5
  "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00006-of-00006.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
27
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
28
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
29
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
30
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
31
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
32
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
33
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
34
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
35
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
37
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
39
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
40
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
41
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
42
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
43
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
44
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
45
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
47
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
48
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
49
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
50
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
51
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
52
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
53
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
54
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
55
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
67
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
68
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
69
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
70
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
71
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
72
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
73
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
74
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
75
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
77
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
78
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
79
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
80
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
81
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
82
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
83
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
84
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
85
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
87
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
88
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
89
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
90
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
91
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
92
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
93
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
94
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
95
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
97
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
98
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
99
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
100
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
101
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
103
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
104
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
105
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
117
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
118
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
119
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
120
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
121
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
122
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
123
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
124
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
125
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
127
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
128
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
129
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
130
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
131
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
132
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
133
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
134
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
135
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
137
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
138
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
139
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
140
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
141
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
142
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
143
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
144
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
145
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
147
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
148
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
149
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
150
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
151
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
152
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
153
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
154
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
155
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
157
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
158
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
159
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
160
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
161
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
162
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
163
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
164
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
165
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
167
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
168
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
169
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
170
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
171
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
172
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
173
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
174
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
175
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
177
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
178
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
179
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
180
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
181
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
182
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
183
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
184
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
185
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
187
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
188
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
189
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
190
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
191
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
192
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
193
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
194
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
195
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
197
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
198
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
199
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
200
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
201
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
202
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
203
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
204
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
205
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
207
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
208
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
209
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
210
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
211
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
212
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
213
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
214
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
215
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
217
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
218
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
219
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
220
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
221
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
222
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
223
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
224
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
225
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
227
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
228
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
229
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
230
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
231
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
232
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
233
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
234
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
235
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
237
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
238
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
239
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
240
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
241
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
242
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
243
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
244
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
245
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
247
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
248
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
249
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
250
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
251
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
252
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
253
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
254
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
255
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
257
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
258
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
259
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
260
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
261
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
262
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
263
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
264
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
265
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
267
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
268
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
269
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
270
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
271
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
272
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
273
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
274
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
275
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
276
+ "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
277
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
278
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
279
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
280
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
281
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
282
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
283
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
284
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
285
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
286
+ "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
287
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
288
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
289
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
290
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
291
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
292
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
293
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
294
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
295
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
296
+ "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
297
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
298
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
299
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
300
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
301
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
302
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
303
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
304
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
305
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
306
+ "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
307
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
308
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
309
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
310
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
311
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
312
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
313
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
314
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
315
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
316
+ "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
317
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
318
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
319
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
320
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
321
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
322
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
323
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
324
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
325
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
326
+ "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
327
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
328
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
329
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
330
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
331
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
332
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
333
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
334
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
335
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
336
+ "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
337
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
338
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
339
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
340
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
341
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
342
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
343
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
344
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
345
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
346
+ "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00006.bin",
347
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
348
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
349
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
350
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
351
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
352
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
353
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
354
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
355
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
356
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
357
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
358
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
359
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
360
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
361
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
362
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
363
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
364
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
365
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
366
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
367
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
368
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
369
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
370
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
371
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
372
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
373
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
374
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
375
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
376
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
377
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
378
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
379
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
380
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
381
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
382
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
383
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
384
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
385
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
386
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
387
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
388
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
389
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
390
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
391
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
392
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
393
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
394
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
395
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
396
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
397
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
398
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
399
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
400
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
401
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
402
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
403
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
404
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
405
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
406
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
407
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
408
+ "model.norm.weight": "pytorch_model-00006-of-00006.bin"
409
  }
410
  }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "[PAD]",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
tokenizer.model CHANGED
File without changes
tokenizer_config.json CHANGED
@@ -19,7 +19,7 @@
19
  "single_word": false
20
  },
21
  "legacy": false,
22
- "model_max_length": 1000000000000000019884624838656,
23
  "pad_token": null,
24
  "padding_side": "right",
25
  "sp_model_kwargs": {},
 
19
  "single_word": false
20
  },
21
  "legacy": false,
22
+ "model_max_length": 32768,
23
  "pad_token": null,
24
  "padding_side": "right",
25
  "sp_model_kwargs": {},