Hugging Face's logo

ctranslate2-4you
/
InternLM3-8b-Instruct-ct2-AWQ

Safetensors
ctranslate2
internlm3
chat
Model card Files Community
ctranslate2-4you commited on
Commit
65cfed6
·
verified ·
1 Parent(s): b29349b

Upload 9 files

Browse files
Files changed (9) hide show
  1. config.json +10 -0
  2. generation_config.json +10 -0
  3. model.bin +3 -0
  4. model.safetensors.index.json +1114 -0
  5. special_tokens_map.json +54 -0
  6. tokenization_internlm3.py +294 -0
  7. tokenizer.model +3 -0
  8. tokenizer_config.json +249 -0
  9. vocabulary.json +0 -0
config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "layer_norm_epsilon": 1e-05,
5
+ "multi_query_attention": true,
6
+ "quantization_bits": 4,
7
+ "quantization_group_size": 128,
8
+ "quantization_type": 1,
9
+ "unk_token": "<unk>"
10
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 2,
6
+ 128131
7
+ ],
8
+ "pad_token_id": 2,
9
+ "transformers_version": "4.47.1"
10
+ }
model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c7ffac12a9bbebace615f1c5fb4220d658de51be78251ad3ad8fb8966f94e2b
3
+ size 6133330999
model.safetensors.index.json ADDED
@@ -0,0 +1,1114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6133260288
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
20
+ "model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
21
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
22
+ "model.layers.0.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
23
+ "model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
24
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
25
+ "model.layers.0.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
26
+ "model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
27
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
28
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
31
+ "model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
32
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
33
+ "model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
34
+ "model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
35
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
36
+ "model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
37
+ "model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
38
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
39
+ "model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
40
+ "model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
41
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
42
+ "model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
43
+ "model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
44
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
45
+ "model.layers.1.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
46
+ "model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
47
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
48
+ "model.layers.1.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
49
+ "model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
50
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
51
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
54
+ "model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
55
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
56
+ "model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
57
+ "model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
58
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
59
+ "model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
60
+ "model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
61
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
62
+ "model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
63
+ "model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
64
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
65
+ "model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
66
+ "model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
67
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
68
+ "model.layers.2.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
69
+ "model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
70
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
71
+ "model.layers.2.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
72
+ "model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
73
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
74
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
77
+ "model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
78
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
79
+ "model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
80
+ "model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
81
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
82
+ "model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
83
+ "model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
84
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
85
+ "model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
86
+ "model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
87
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
88
+ "model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
89
+ "model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
90
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
91
+ "model.layers.3.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
92
+ "model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
93
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
94
+ "model.layers.3.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
95
+ "model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
96
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
97
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
100
+ "model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
101
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
102
+ "model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
103
+ "model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
104
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
105
+ "model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
106
+ "model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
107
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
108
+ "model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
109
+ "model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
110
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
111
+ "model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
112
+ "model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
113
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
114
+ "model.layers.4.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
115
+ "model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
116
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
117
+ "model.layers.4.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
118
+ "model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
119
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
120
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
123
+ "model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
124
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
125
+ "model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
126
+ "model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
127
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
128
+ "model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
129
+ "model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
130
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
131
+ "model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
132
+ "model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
133
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
134
+ "model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
135
+ "model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
136
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
137
+ "model.layers.5.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
138
+ "model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
139
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
140
+ "model.layers.5.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
141
+ "model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
142
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
143
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
146
+ "model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
147
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
148
+ "model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
149
+ "model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
150
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
151
+ "model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
152
+ "model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
153
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
154
+ "model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
155
+ "model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
156
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
157
+ "model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
158
+ "model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
159
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
160
+ "model.layers.6.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
161
+ "model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
162
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
163
+ "model.layers.6.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
164
+ "model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
165
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
166
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
169
+ "model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
170
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
171
+ "model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
172
+ "model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
173
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
174
+ "model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
175
+ "model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
176
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
177
+ "model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
178
+ "model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
179
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
180
+ "model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
181
+ "model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
182
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
183
+ "model.layers.7.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
184
+ "model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
185
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
186
+ "model.layers.7.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
187
+ "model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
188
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
189
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
192
+ "model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
193
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
194
+ "model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
195
+ "model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
196
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
197
+ "model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
198
+ "model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
199
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
200
+ "model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
201
+ "model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
202
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
203
+ "model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
204
+ "model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
205
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
206
+ "model.layers.8.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
207
+ "model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
208
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
209
+ "model.layers.8.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
210
+ "model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
211
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
212
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
215
+ "model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
216
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
217
+ "model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
218
+ "model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
219
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
220
+ "model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
221
+ "model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
222
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
223
+ "model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
224
+ "model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
225
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
226
+ "model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
227
+ "model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
228
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
229
+ "model.layers.9.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
230
+ "model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
231
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
232
+ "model.layers.9.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
233
+ "model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
234
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
235
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
236
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
238
+ "model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
239
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
240
+ "model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
241
+ "model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
242
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
243
+ "model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
244
+ "model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
245
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
246
+ "model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
247
+ "model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
248
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
249
+ "model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
250
+ "model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
251
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
252
+ "model.layers.10.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
253
+ "model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
254
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
255
+ "model.layers.10.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
256
+ "model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
257
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
258
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
261
+ "model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
262
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
263
+ "model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
264
+ "model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
265
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
266
+ "model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
267
+ "model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
268
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
269
+ "model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
270
+ "model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
271
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
272
+ "model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
273
+ "model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
274
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
275
+ "model.layers.11.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
276
+ "model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
277
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
278
+ "model.layers.11.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
279
+ "model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
280
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
281
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
282
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
284
+ "model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
285
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
286
+ "model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
287
+ "model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
288
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
289
+ "model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
290
+ "model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
291
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
292
+ "model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
293
+ "model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
294
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
295
+ "model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
296
+ "model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
297
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
298
+ "model.layers.12.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
299
+ "model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
300
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
301
+ "model.layers.12.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
302
+ "model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
303
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
304
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
305
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
306
+ "model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
307
+ "model.layers.13.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
308
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
309
+ "model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
310
+ "model.layers.13.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
311
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
312
+ "model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
313
+ "model.layers.13.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
314
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
315
+ "model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
316
+ "model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
317
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
318
+ "model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
319
+ "model.layers.13.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
320
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
321
+ "model.layers.13.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
322
+ "model.layers.13.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
323
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
324
+ "model.layers.13.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
325
+ "model.layers.13.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
326
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
327
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
328
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
329
+ "model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
330
+ "model.layers.14.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
331
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
332
+ "model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
333
+ "model.layers.14.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
334
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
335
+ "model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
336
+ "model.layers.14.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
337
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
338
+ "model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
339
+ "model.layers.14.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
340
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
341
+ "model.layers.14.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
342
+ "model.layers.14.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
343
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
344
+ "model.layers.14.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
345
+ "model.layers.14.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
346
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
347
+ "model.layers.14.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
348
+ "model.layers.14.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
349
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
350
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
351
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
352
+ "model.layers.15.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
353
+ "model.layers.15.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
354
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
355
+ "model.layers.15.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
356
+ "model.layers.15.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
357
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
358
+ "model.layers.15.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
359
+ "model.layers.15.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
360
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
361
+ "model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
362
+ "model.layers.15.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
363
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
364
+ "model.layers.15.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
365
+ "model.layers.15.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
366
+ "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
367
+ "model.layers.15.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
368
+ "model.layers.15.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
369
+ "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
370
+ "model.layers.15.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
371
+ "model.layers.15.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
372
+ "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
373
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
374
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
375
+ "model.layers.16.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
376
+ "model.layers.16.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
377
+ "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
378
+ "model.layers.16.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
379
+ "model.layers.16.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
380
+ "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
381
+ "model.layers.16.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
382
+ "model.layers.16.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
383
+ "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
384
+ "model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
385
+ "model.layers.16.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
386
+ "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
387
+ "model.layers.16.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
388
+ "model.layers.16.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
389
+ "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
390
+ "model.layers.16.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
391
+ "model.layers.16.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
392
+ "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
393
+ "model.layers.16.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
394
+ "model.layers.16.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
395
+ "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
396
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
397
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
398
+ "model.layers.17.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
399
+ "model.layers.17.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
400
+ "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
401
+ "model.layers.17.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
402
+ "model.layers.17.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
403
+ "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
404
+ "model.layers.17.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
405
+ "model.layers.17.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
406
+ "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
407
+ "model.layers.17.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
408
+ "model.layers.17.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
409
+ "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
410
+ "model.layers.17.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
411
+ "model.layers.17.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
412
+ "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
413
+ "model.layers.17.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
414
+ "model.layers.17.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
415
+ "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
416
+ "model.layers.17.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
417
+ "model.layers.17.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
418
+ "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
419
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
420
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
421
+ "model.layers.18.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
422
+ "model.layers.18.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
423
+ "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
424
+ "model.layers.18.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
425
+ "model.layers.18.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
426
+ "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
427
+ "model.layers.18.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
428
+ "model.layers.18.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
429
+ "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
430
+ "model.layers.18.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
431
+ "model.layers.18.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
432
+ "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
433
+ "model.layers.18.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
434
+ "model.layers.18.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
435
+ "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
436
+ "model.layers.18.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
437
+ "model.layers.18.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
438
+ "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
439
+ "model.layers.18.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
440
+ "model.layers.18.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
441
+ "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
442
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
443
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
444
+ "model.layers.19.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
445
+ "model.layers.19.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
446
+ "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
447
+ "model.layers.19.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
448
+ "model.layers.19.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
449
+ "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
450
+ "model.layers.19.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
451
+ "model.layers.19.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
452
+ "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
453
+ "model.layers.19.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
454
+ "model.layers.19.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
455
+ "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
456
+ "model.layers.19.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
457
+ "model.layers.19.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
458
+ "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
459
+ "model.layers.19.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
460
+ "model.layers.19.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
461
+ "model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
462
+ "model.layers.19.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
463
+ "model.layers.19.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
464
+ "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
465
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
466
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
467
+ "model.layers.20.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
468
+ "model.layers.20.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
469
+ "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
470
+ "model.layers.20.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
471
+ "model.layers.20.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
472
+ "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
473
+ "model.layers.20.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
474
+ "model.layers.20.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
475
+ "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
476
+ "model.layers.20.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
477
+ "model.layers.20.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
478
+ "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
479
+ "model.layers.20.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
480
+ "model.layers.20.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
481
+ "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
482
+ "model.layers.20.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
483
+ "model.layers.20.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
484
+ "model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
485
+ "model.layers.20.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
486
+ "model.layers.20.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
487
+ "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
488
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
489
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
490
+ "model.layers.21.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
491
+ "model.layers.21.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
492
+ "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
493
+ "model.layers.21.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
494
+ "model.layers.21.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
495
+ "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
496
+ "model.layers.21.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
497
+ "model.layers.21.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
498
+ "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
499
+ "model.layers.21.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
500
+ "model.layers.21.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
501
+ "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
502
+ "model.layers.21.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
503
+ "model.layers.21.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
504
+ "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
505
+ "model.layers.21.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
506
+ "model.layers.21.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
507
+ "model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
508
+ "model.layers.21.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
509
+ "model.layers.21.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
510
+ "model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
511
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
512
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
513
+ "model.layers.22.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
514
+ "model.layers.22.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
515
+ "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
516
+ "model.layers.22.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
517
+ "model.layers.22.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
518
+ "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
519
+ "model.layers.22.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
520
+ "model.layers.22.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
521
+ "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
522
+ "model.layers.22.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
523
+ "model.layers.22.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
524
+ "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
525
+ "model.layers.22.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
526
+ "model.layers.22.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
527
+ "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
528
+ "model.layers.22.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
529
+ "model.layers.22.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
530
+ "model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
531
+ "model.layers.22.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
532
+ "model.layers.22.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
533
+ "model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
534
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
535
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
536
+ "model.layers.23.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
537
+ "model.layers.23.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
538
+ "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
539
+ "model.layers.23.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
540
+ "model.layers.23.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
541
+ "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
542
+ "model.layers.23.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
543
+ "model.layers.23.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
544
+ "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
545
+ "model.layers.23.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
546
+ "model.layers.23.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
547
+ "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
548
+ "model.layers.23.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
549
+ "model.layers.23.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
550
+ "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
551
+ "model.layers.23.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
552
+ "model.layers.23.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
553
+ "model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
554
+ "model.layers.23.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
555
+ "model.layers.23.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
556
+ "model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
557
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
558
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
559
+ "model.layers.24.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
560
+ "model.layers.24.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
561
+ "model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
562
+ "model.layers.24.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
563
+ "model.layers.24.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
564
+ "model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
565
+ "model.layers.24.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
566
+ "model.layers.24.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
567
+ "model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
568
+ "model.layers.24.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
569
+ "model.layers.24.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
570
+ "model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
571
+ "model.layers.24.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
572
+ "model.layers.24.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
573
+ "model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
574
+ "model.layers.24.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
575
+ "model.layers.24.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
576
+ "model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
577
+ "model.layers.24.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
578
+ "model.layers.24.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
579
+ "model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
580
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
581
+ "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
582
+ "model.layers.25.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
583
+ "model.layers.25.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
584
+ "model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
585
+ "model.layers.25.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
586
+ "model.layers.25.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
587
+ "model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
588
+ "model.layers.25.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
589
+ "model.layers.25.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
590
+ "model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
591
+ "model.layers.25.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
592
+ "model.layers.25.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
593
+ "model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
594
+ "model.layers.25.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
595
+ "model.layers.25.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
596
+ "model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
597
+ "model.layers.25.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
598
+ "model.layers.25.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
599
+ "model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
600
+ "model.layers.25.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
601
+ "model.layers.25.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
602
+ "model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
603
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
604
+ "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
605
+ "model.layers.26.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
606
+ "model.layers.26.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
607
+ "model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
608
+ "model.layers.26.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
609
+ "model.layers.26.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
610
+ "model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
611
+ "model.layers.26.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
612
+ "model.layers.26.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
613
+ "model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
614
+ "model.layers.26.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
615
+ "model.layers.26.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
616
+ "model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
617
+ "model.layers.26.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
618
+ "model.layers.26.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
619
+ "model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
620
+ "model.layers.26.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
621
+ "model.layers.26.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
622
+ "model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
623
+ "model.layers.26.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
624
+ "model.layers.26.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
625
+ "model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
626
+ "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
627
+ "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
628
+ "model.layers.27.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
629
+ "model.layers.27.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
630
+ "model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
631
+ "model.layers.27.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
632
+ "model.layers.27.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
633
+ "model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
634
+ "model.layers.27.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
635
+ "model.layers.27.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
636
+ "model.layers.27.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
637
+ "model.layers.27.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
638
+ "model.layers.27.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
639
+ "model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
640
+ "model.layers.27.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
641
+ "model.layers.27.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
642
+ "model.layers.27.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
643
+ "model.layers.27.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
644
+ "model.layers.27.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
645
+ "model.layers.27.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
646
+ "model.layers.27.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
647
+ "model.layers.27.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
648
+ "model.layers.27.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
649
+ "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
650
+ "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
651
+ "model.layers.28.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
652
+ "model.layers.28.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
653
+ "model.layers.28.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
654
+ "model.layers.28.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
655
+ "model.layers.28.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
656
+ "model.layers.28.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
657
+ "model.layers.28.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
658
+ "model.layers.28.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
659
+ "model.layers.28.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
660
+ "model.layers.28.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
661
+ "model.layers.28.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
662
+ "model.layers.28.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
663
+ "model.layers.28.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
664
+ "model.layers.28.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
665
+ "model.layers.28.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
666
+ "model.layers.28.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
667
+ "model.layers.28.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
668
+ "model.layers.28.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
669
+ "model.layers.28.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
670
+ "model.layers.28.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
671
+ "model.layers.28.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
672
+ "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
673
+ "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
674
+ "model.layers.29.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
675
+ "model.layers.29.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
676
+ "model.layers.29.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
677
+ "model.layers.29.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
678
+ "model.layers.29.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
679
+ "model.layers.29.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
680
+ "model.layers.29.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
681
+ "model.layers.29.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
682
+ "model.layers.29.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
683
+ "model.layers.29.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
684
+ "model.layers.29.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
685
+ "model.layers.29.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
686
+ "model.layers.29.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
687
+ "model.layers.29.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
688
+ "model.layers.29.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
689
+ "model.layers.29.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
690
+ "model.layers.29.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
691
+ "model.layers.29.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
692
+ "model.layers.29.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
693
+ "model.layers.29.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
694
+ "model.layers.29.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
695
+ "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
696
+ "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
697
+ "model.layers.30.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
698
+ "model.layers.30.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
699
+ "model.layers.30.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
700
+ "model.layers.30.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
701
+ "model.layers.30.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
702
+ "model.layers.30.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
703
+ "model.layers.30.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
704
+ "model.layers.30.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
705
+ "model.layers.30.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
706
+ "model.layers.30.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
707
+ "model.layers.30.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
708
+ "model.layers.30.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
709
+ "model.layers.30.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
710
+ "model.layers.30.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
711
+ "model.layers.30.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
712
+ "model.layers.30.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
713
+ "model.layers.30.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
714
+ "model.layers.30.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
715
+ "model.layers.30.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
716
+ "model.layers.30.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
717
+ "model.layers.30.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
718
+ "model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
719
+ "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
720
+ "model.layers.31.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
721
+ "model.layers.31.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
722
+ "model.layers.31.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
723
+ "model.layers.31.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
724
+ "model.layers.31.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
725
+ "model.layers.31.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
726
+ "model.layers.31.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
727
+ "model.layers.31.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
728
+ "model.layers.31.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
729
+ "model.layers.31.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
730
+ "model.layers.31.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
731
+ "model.layers.31.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
732
+ "model.layers.31.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
733
+ "model.layers.31.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
734
+ "model.layers.31.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
735
+ "model.layers.31.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
736
+ "model.layers.31.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
737
+ "model.layers.31.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
738
+ "model.layers.31.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
739
+ "model.layers.31.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
740
+ "model.layers.31.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
741
+ "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
742
+ "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
743
+ "model.layers.32.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
744
+ "model.layers.32.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
745
+ "model.layers.32.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
746
+ "model.layers.32.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
747
+ "model.layers.32.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
748
+ "model.layers.32.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
749
+ "model.layers.32.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
750
+ "model.layers.32.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
751
+ "model.layers.32.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
752
+ "model.layers.32.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
753
+ "model.layers.32.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
754
+ "model.layers.32.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
755
+ "model.layers.32.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
756
+ "model.layers.32.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
757
+ "model.layers.32.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
758
+ "model.layers.32.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
759
+ "model.layers.32.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
760
+ "model.layers.32.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
761
+ "model.layers.32.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
762
+ "model.layers.32.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
763
+ "model.layers.32.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
764
+ "model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
765
+ "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
766
+ "model.layers.33.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
767
+ "model.layers.33.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
768
+ "model.layers.33.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
769
+ "model.layers.33.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
770
+ "model.layers.33.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
771
+ "model.layers.33.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
772
+ "model.layers.33.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
773
+ "model.layers.33.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
774
+ "model.layers.33.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
775
+ "model.layers.33.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
776
+ "model.layers.33.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
777
+ "model.layers.33.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
778
+ "model.layers.33.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
779
+ "model.layers.33.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
780
+ "model.layers.33.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
781
+ "model.layers.33.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
782
+ "model.layers.33.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
783
+ "model.layers.33.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
784
+ "model.layers.33.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
785
+ "model.layers.33.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
786
+ "model.layers.33.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
787
+ "model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
788
+ "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
789
+ "model.layers.34.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
790
+ "model.layers.34.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
791
+ "model.layers.34.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
792
+ "model.layers.34.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
793
+ "model.layers.34.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
794
+ "model.layers.34.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
795
+ "model.layers.34.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
796
+ "model.layers.34.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
797
+ "model.layers.34.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
798
+ "model.layers.34.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
799
+ "model.layers.34.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
800
+ "model.layers.34.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
801
+ "model.layers.34.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
802
+ "model.layers.34.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
803
+ "model.layers.34.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
804
+ "model.layers.34.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
805
+ "model.layers.34.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
806
+ "model.layers.34.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
807
+ "model.layers.34.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
808
+ "model.layers.34.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
809
+ "model.layers.34.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
810
+ "model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
811
+ "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
812
+ "model.layers.35.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
813
+ "model.layers.35.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
814
+ "model.layers.35.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
815
+ "model.layers.35.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
816
+ "model.layers.35.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
817
+ "model.layers.35.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
818
+ "model.layers.35.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
819
+ "model.layers.35.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
820
+ "model.layers.35.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
821
+ "model.layers.35.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
822
+ "model.layers.35.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
823
+ "model.layers.35.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
824
+ "model.layers.35.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
825
+ "model.layers.35.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
826
+ "model.layers.35.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
827
+ "model.layers.35.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
828
+ "model.layers.35.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
829
+ "model.layers.35.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
830
+ "model.layers.35.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
831
+ "model.layers.35.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
832
+ "model.layers.35.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
833
+ "model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
834
+ "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
835
+ "model.layers.36.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
836
+ "model.layers.36.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
837
+ "model.layers.36.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
838
+ "model.layers.36.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
839
+ "model.layers.36.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
840
+ "model.layers.36.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
841
+ "model.layers.36.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
842
+ "model.layers.36.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
843
+ "model.layers.36.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
844
+ "model.layers.36.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
845
+ "model.layers.36.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
846
+ "model.layers.36.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
847
+ "model.layers.36.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
848
+ "model.layers.36.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
849
+ "model.layers.36.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
850
+ "model.layers.36.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
851
+ "model.layers.36.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
852
+ "model.layers.36.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
853
+ "model.layers.36.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
854
+ "model.layers.36.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
855
+ "model.layers.36.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
856
+ "model.layers.36.input_layernorm.weight": "model-00001-of-00002.safetensors",
857
+ "model.layers.36.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
858
+ "model.layers.37.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
859
+ "model.layers.37.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
860
+ "model.layers.37.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
861
+ "model.layers.37.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
862
+ "model.layers.37.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
863
+ "model.layers.37.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
864
+ "model.layers.37.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
865
+ "model.layers.37.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
866
+ "model.layers.37.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
867
+ "model.layers.37.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
868
+ "model.layers.37.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
869
+ "model.layers.37.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
870
+ "model.layers.37.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
871
+ "model.layers.37.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
872
+ "model.layers.37.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
873
+ "model.layers.37.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
874
+ "model.layers.37.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
875
+ "model.layers.37.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
876
+ "model.layers.37.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
877
+ "model.layers.37.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
878
+ "model.layers.37.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
879
+ "model.layers.37.input_layernorm.weight": "model-00001-of-00002.safetensors",
880
+ "model.layers.37.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
881
+ "model.layers.38.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
882
+ "model.layers.38.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
883
+ "model.layers.38.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
884
+ "model.layers.38.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
885
+ "model.layers.38.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
886
+ "model.layers.38.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
887
+ "model.layers.38.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
888
+ "model.layers.38.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
889
+ "model.layers.38.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
890
+ "model.layers.38.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
891
+ "model.layers.38.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
892
+ "model.layers.38.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
893
+ "model.layers.38.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
894
+ "model.layers.38.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
895
+ "model.layers.38.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
896
+ "model.layers.38.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
897
+ "model.layers.38.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
898
+ "model.layers.38.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
899
+ "model.layers.38.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
900
+ "model.layers.38.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
901
+ "model.layers.38.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
902
+ "model.layers.38.input_layernorm.weight": "model-00001-of-00002.safetensors",
903
+ "model.layers.38.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
904
+ "model.layers.39.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
905
+ "model.layers.39.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
906
+ "model.layers.39.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
907
+ "model.layers.39.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
908
+ "model.layers.39.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
909
+ "model.layers.39.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
910
+ "model.layers.39.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
911
+ "model.layers.39.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
912
+ "model.layers.39.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
913
+ "model.layers.39.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
914
+ "model.layers.39.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
915
+ "model.layers.39.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
916
+ "model.layers.39.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
917
+ "model.layers.39.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
918
+ "model.layers.39.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
919
+ "model.layers.39.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
920
+ "model.layers.39.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
921
+ "model.layers.39.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
922
+ "model.layers.39.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
923
+ "model.layers.39.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
924
+ "model.layers.39.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
925
+ "model.layers.39.input_layernorm.weight": "model-00001-of-00002.safetensors",
926
+ "model.layers.39.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
927
+ "model.layers.40.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
928
+ "model.layers.40.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
929
+ "model.layers.40.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
930
+ "model.layers.40.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
931
+ "model.layers.40.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
932
+ "model.layers.40.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
933
+ "model.layers.40.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
934
+ "model.layers.40.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
935
+ "model.layers.40.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
936
+ "model.layers.40.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
937
+ "model.layers.40.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
938
+ "model.layers.40.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
939
+ "model.layers.40.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
940
+ "model.layers.40.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
941
+ "model.layers.40.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
942
+ "model.layers.40.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
943
+ "model.layers.40.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
944
+ "model.layers.40.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
945
+ "model.layers.40.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
946
+ "model.layers.40.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
947
+ "model.layers.40.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
948
+ "model.layers.40.input_layernorm.weight": "model-00001-of-00002.safetensors",
949
+ "model.layers.40.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
950
+ "model.layers.41.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
951
+ "model.layers.41.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
952
+ "model.layers.41.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
953
+ "model.layers.41.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
954
+ "model.layers.41.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
955
+ "model.layers.41.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
956
+ "model.layers.41.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
957
+ "model.layers.41.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
958
+ "model.layers.41.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
959
+ "model.layers.41.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
960
+ "model.layers.41.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
961
+ "model.layers.41.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
962
+ "model.layers.41.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
963
+ "model.layers.41.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
964
+ "model.layers.41.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
965
+ "model.layers.41.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
966
+ "model.layers.41.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
967
+ "model.layers.41.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
968
+ "model.layers.41.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
969
+ "model.layers.41.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
970
+ "model.layers.41.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
971
+ "model.layers.41.input_layernorm.weight": "model-00001-of-00002.safetensors",
972
+ "model.layers.41.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
973
+ "model.layers.42.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
974
+ "model.layers.42.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
975
+ "model.layers.42.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
976
+ "model.layers.42.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
977
+ "model.layers.42.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
978
+ "model.layers.42.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
979
+ "model.layers.42.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
980
+ "model.layers.42.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
981
+ "model.layers.42.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
982
+ "model.layers.42.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
983
+ "model.layers.42.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
984
+ "model.layers.42.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
985
+ "model.layers.42.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
986
+ "model.layers.42.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
987
+ "model.layers.42.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
988
+ "model.layers.42.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
989
+ "model.layers.42.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
990
+ "model.layers.42.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
991
+ "model.layers.42.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
992
+ "model.layers.42.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
993
+ "model.layers.42.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
994
+ "model.layers.42.input_layernorm.weight": "model-00001-of-00002.safetensors",
995
+ "model.layers.42.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
996
+ "model.layers.43.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
997
+ "model.layers.43.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
998
+ "model.layers.43.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
999
+ "model.layers.43.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
1000
+ "model.layers.43.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
1001
+ "model.layers.43.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
1002
+ "model.layers.43.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
1003
+ "model.layers.43.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
1004
+ "model.layers.43.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
1005
+ "model.layers.43.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
1006
+ "model.layers.43.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
1007
+ "model.layers.43.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
1008
+ "model.layers.43.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
1009
+ "model.layers.43.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
1010
+ "model.layers.43.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
1011
+ "model.layers.43.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
1012
+ "model.layers.43.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
1013
+ "model.layers.43.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
1014
+ "model.layers.43.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
1015
+ "model.layers.43.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
1016
+ "model.layers.43.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
1017
+ "model.layers.43.input_layernorm.weight": "model-00001-of-00002.safetensors",
1018
+ "model.layers.43.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
1019
+ "model.layers.44.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
1020
+ "model.layers.44.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
1021
+ "model.layers.44.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
1022
+ "model.layers.44.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
1023
+ "model.layers.44.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
1024
+ "model.layers.44.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
1025
+ "model.layers.44.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
1026
+ "model.layers.44.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
1027
+ "model.layers.44.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
1028
+ "model.layers.44.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
1029
+ "model.layers.44.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
1030
+ "model.layers.44.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
1031
+ "model.layers.44.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
1032
+ "model.layers.44.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
1033
+ "model.layers.44.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
1034
+ "model.layers.44.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
1035
+ "model.layers.44.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
1036
+ "model.layers.44.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
1037
+ "model.layers.44.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
1038
+ "model.layers.44.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
1039
+ "model.layers.44.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
1040
+ "model.layers.44.input_layernorm.weight": "model-00001-of-00002.safetensors",
1041
+ "model.layers.44.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
1042
+ "model.layers.45.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
1043
+ "model.layers.45.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
1044
+ "model.layers.45.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
1045
+ "model.layers.45.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
1046
+ "model.layers.45.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
1047
+ "model.layers.45.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
1048
+ "model.layers.45.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
1049
+ "model.layers.45.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
1050
+ "model.layers.45.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
1051
+ "model.layers.45.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
1052
+ "model.layers.45.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
1053
+ "model.layers.45.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
1054
+ "model.layers.45.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
1055
+ "model.layers.45.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
1056
+ "model.layers.45.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
1057
+ "model.layers.45.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
1058
+ "model.layers.45.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
1059
+ "model.layers.45.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
1060
+ "model.layers.45.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
1061
+ "model.layers.45.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
1062
+ "model.layers.45.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
1063
+ "model.layers.45.input_layernorm.weight": "model-00001-of-00002.safetensors",
1064
+ "model.layers.45.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
1065
+ "model.layers.46.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
1066
+ "model.layers.46.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
1067
+ "model.layers.46.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
1068
+ "model.layers.46.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
1069
+ "model.layers.46.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
1070
+ "model.layers.46.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
1071
+ "model.layers.46.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
1072
+ "model.layers.46.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
1073
+ "model.layers.46.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
1074
+ "model.layers.46.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
1075
+ "model.layers.46.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
1076
+ "model.layers.46.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
1077
+ "model.layers.46.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
1078
+ "model.layers.46.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
1079
+ "model.layers.46.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
1080
+ "model.layers.46.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
1081
+ "model.layers.46.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
1082
+ "model.layers.46.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
1083
+ "model.layers.46.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
1084
+ "model.layers.46.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
1085
+ "model.layers.46.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
1086
+ "model.layers.46.input_layernorm.weight": "model-00001-of-00002.safetensors",
1087
+ "model.layers.46.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
1088
+ "model.layers.47.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
1089
+ "model.layers.47.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
1090
+ "model.layers.47.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
1091
+ "model.layers.47.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
1092
+ "model.layers.47.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
1093
+ "model.layers.47.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
1094
+ "model.layers.47.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
1095
+ "model.layers.47.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
1096
+ "model.layers.47.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
1097
+ "model.layers.47.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
1098
+ "model.layers.47.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
1099
+ "model.layers.47.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
1100
+ "model.layers.47.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
1101
+ "model.layers.47.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
1102
+ "model.layers.47.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
1103
+ "model.layers.47.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
1104
+ "model.layers.47.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
1105
+ "model.layers.47.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
1106
+ "model.layers.47.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
1107
+ "model.layers.47.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
1108
+ "model.layers.47.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
1109
+ "model.layers.47.input_layernorm.weight": "model-00002-of-00002.safetensors",
1110
+ "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
1111
+ "model.norm.weight": "model-00002-of-00002.safetensors",
1112
+ "lm_head.weight": "model-00002-of-00002.safetensors"
1113
+ }
1114
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|action_start|>",
6
+ "<|action_end|>",
7
+ "<|interpreter|>",
8
+ "<|plugin|>",
9
+ "<restate>",
10
+ "</restate>",
11
+ "<planning>",
12
+ "</planning>",
13
+ "<recollect>",
14
+ "</recollect>",
15
+ "<execution>",
16
+ "</execution>",
17
+ "<review>",
18
+ "</review>",
19
+ "<summarize>",
20
+ "</summarize>",
21
+ "<retry>",
22
+ "</retry>",
23
+ "<conclude>",
24
+ "</conclude>"
25
+ ],
26
+ "bos_token": {
27
+ "content": "<s>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "eos_token": {
34
+ "content": "</s>",
35
+ "lstrip": false,
36
+ "normalized": false,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ },
40
+ "pad_token": {
41
+ "content": "</s>",
42
+ "lstrip": false,
43
+ "normalized": false,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ },
47
+ "unk_token": {
48
+ "content": "<unk>",
49
+ "lstrip": false,
50
+ "normalized": false,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ }
54
+ }
tokenization_internlm3.py ADDED
@@ -0,0 +1,294 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import os
2
+ from shutil import copyfile
3
+ from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple
4
+
5
+ import sentencepiece as spm
6
+ from transformers.tokenization_utils import AddedToken, PreTrainedTokenizer
7
+ from transformers.utils import logging
8
+
9
+ if TYPE_CHECKING:
10
+ from transformers.tokenization_utils_base import TextInput
11
+
12
+ logger = logging.get_logger(__name__)
13
+
14
+ VOCAB_FILES_NAMES = {"vocab_file": "tokenizer.model"}
15
+
16
+ SPIECE_UNDERLINE = "▁"
17
+
18
+
19
+ class InternLM3Tokenizer(PreTrainedTokenizer):
20
+ """
21
+ Construct a InternLM3 tokenizer. Based on byte-level Byte-Pair-Encoding. The default padding token is unset as there is
22
+ no padding token in the original model.
23
+
24
+ Args:
25
+ vocab_file (`str`):
26
+ Path to the vocabulary file.
27
+ unk_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"<unk>"`):
28
+ The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
29
+ token instead.
30
+ bos_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"<s>"`):
31
+ The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.
32
+ eos_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"</s>"`):
33
+ The end of sequence token.
34
+ pad_token (`str` or `tokenizers.AddedToken`, *optional*):
35
+ A special token used to make arrays of tokens the same size for batching purpose. Will then be ignored by
36
+ attention mechanisms or loss computation.
37
+ sp_model_kwargs (`Dict[str, Any]`, `Optional`, *optional*):
38
+ Will be passed to the `SentencePieceProcessor.__init__()` method. The [Python wrapper for
39
+ SentencePiece](https://github.com/google/sentencepiece/tree/master/python) can be used, among other things,
40
+ to set:
41
+
42
+ - `enable_sampling`: Enable subword regularization.
43
+ - `nbest_size`: Sampling parameters for unigram. Invalid for BPE-Dropout.
44
+
45
+ - `nbest_size = {0,1}`: No sampling is performed.
46
+ - `nbest_size > 1`: samples from the nbest_size results.
47
+ - `nbest_size < 0`: assuming that nbest_size is infinite and samples from the all hypothesis (lattice)
48
+ using forward-filtering-and-backward-sampling algorithm.
49
+
50
+ - `alpha`: Smoothing parameter for unigram sampling, and dropout probability of merge operations for
51
+ BPE-dropout.
52
+
53
+ add_bos_token (`bool`, *optional*, defaults to `True`):
54
+ Whether or not to add an `bos_token` at the start of sequences.
55
+ add_eos_token (`bool`, *optional*, defaults to `False`):
56
+ Whether or not to add an `eos_token` at the end of sequences.
57
+ clean_up_tokenization_spaces (`bool`, *optional*, defaults to `False`):
58
+ Whether or not to cleanup spaces after decoding, cleanup consists in removing potential artifacts like
59
+ extra spaces.
60
+ use_default_system_prompt (`bool`, *optional*, defaults to `False`):
61
+ Whether or not the default system prompt for InternLM3 should be used.
62
+ spaces_between_special_tokens (`bool`, *optional*, defaults to `False`):
63
+ Whether or not to add spaces between special tokens.
64
+ spaces_for_interleaved_special_tokens (`bool`, *optional*, defaults to `False`):
65
+ Whether or not to add spaces between special tokens that are interleaved with normal tokens.
66
+ add_prefix_space (`bool`, *optional*, defaults to `True`):
67
+ Whether or not to add an initial space to the input. This allows to treat the leading word just as any
68
+ other word. Again, this should be set with `from_slow=True` to make sure it's taken into account.
69
+ """
70
+
71
+ vocab_files_names = VOCAB_FILES_NAMES
72
+ model_input_names = ["input_ids", "attention_mask"]
73
+
74
+ def __init__(
75
+ self,
76
+ vocab_file,
77
+ unk_token="<unk>",
78
+ bos_token="<s>",
79
+ eos_token="</s>",
80
+ pad_token=None,
81
+ sp_model_kwargs: Optional[Dict[str, Any]] = None,
82
+ add_bos_token=True,
83
+ add_eos_token=False,
84
+ clean_up_tokenization_spaces=False,
85
+ use_default_system_prompt=False,
86
+ spaces_between_special_tokens=False,
87
+ spaces_for_interleaved_special_tokens=False,
88
+ add_prefix_space=True,
89
+ **kwargs,
90
+ ):
91
+ self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
92
+ bos_token = AddedToken(bos_token, normalized=False, special=True) if isinstance(bos_token, str) else bos_token
93
+ eos_token = AddedToken(eos_token, normalized=False, special=True) if isinstance(eos_token, str) else eos_token
94
+ unk_token = AddedToken(unk_token, normalized=False, special=True) if isinstance(unk_token, str) else unk_token
95
+ pad_token = AddedToken(pad_token, normalized=False, special=True) if isinstance(pad_token, str) else pad_token
96
+
97
+ self.vocab_file = vocab_file
98
+ self.add_bos_token = add_bos_token
99
+ self.add_eos_token = add_eos_token
100
+ self.use_default_system_prompt = use_default_system_prompt
101
+ self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
102
+ self.sp_model.Load(vocab_file)
103
+ self.add_prefix_space = add_prefix_space
104
+ self.spaces_for_interleaved_special_tokens = spaces_for_interleaved_special_tokens
105
+
106
+ vocab_size = self.sp_model.get_piece_size()
107
+ self.decoder = {i: self.sp_model.id_to_piece(i) for i in range(vocab_size)}
108
+
109
+ super().__init__(
110
+ bos_token=bos_token,
111
+ eos_token=eos_token,
112
+ unk_token=unk_token,
113
+ pad_token=pad_token,
114
+ add_bos_token=add_bos_token,
115
+ add_eos_token=add_eos_token,
116
+ sp_model_kwargs=sp_model_kwargs,
117
+ clean_up_tokenization_spaces=clean_up_tokenization_spaces,
118
+ use_default_system_prompt=use_default_system_prompt,
119
+ spaces_between_special_tokens=spaces_between_special_tokens,
120
+ add_prefix_space=add_prefix_space,
121
+ **kwargs,
122
+ )
123
+
124
+ def __getstate__(self):
125
+ state = self.__dict__.copy()
126
+ state["sp_model"] = None
127
+ state["sp_model_proto"] = self.sp_model.serialized_model_proto()
128
+ return state
129
+
130
+ def __setstate__(self, d):
131
+ self.__dict__.update(d)
132
+ self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
133
+ self.sp_model.LoadFromSerializedProto(self.sp_model_proto)
134
+
135
+ @property
136
+ def vocab_size(self):
137
+ """Returns vocab size"""
138
+ return self.sp_model.get_piece_size()
139
+
140
+ def get_vocab(self):
141
+ """Returns vocab as a dict"""
142
+ vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
143
+ vocab.update(self.added_tokens_encoder)
144
+ return vocab
145
+
146
+ def tokenize(self, text: "TextInput", **kwargs) -> List[str]:
147
+ """
148
+ Args:
149
+ text: TextInput
150
+ Simply calls PreTrainedTokenizer's method
151
+ """
152
+ return super().tokenize(text, **kwargs)
153
+
154
+ def _tokenize(self, text, **kwargs):
155
+ """
156
+ Args:
157
+ text: TextInput
158
+ Returns a tokenized string. The Gemma tokenizer never adds a prefix space.
159
+ """
160
+ return self.sp_model.encode(text, out_type=str)
161
+
162
+ def _convert_token_to_id(self, token):
163
+ """Converts a token (str) in an id using the vocab."""
164
+ return self.sp_model.piece_to_id(token)
165
+
166
+ def _convert_id_to_token(self, index):
167
+ """Converts an index (integer) in a token (str) using the vocab."""
168
+ return self.decoder.get(index, "")
169
+
170
+ def convert_tokens_to_string(self, tokens):
171
+ """Converts a sequence of tokens (string) in a single string."""
172
+ # since we manually add the prefix space, we have to remove it when decoding
173
+ if tokens[0].startswith(SPIECE_UNDERLINE) and self.add_prefix_space:
174
+ tokens[0] = tokens[0][1:]
175
+
176
+ current_sub_tokens = []
177
+ out_string = ""
178
+ prev_is_special = False
179
+ for i, token in enumerate(tokens):
180
+ # make sure that special tokens are not decoded using sentencepiece model
181
+ if token in self.all_special_tokens:
182
+ if not prev_is_special and i != 0 and self.spaces_for_interleaved_special_tokens:
183
+ out_string += " "
184
+ out_string += self.sp_model.decode(current_sub_tokens) + token
185
+ prev_is_special = True
186
+ current_sub_tokens = []
187
+ else:
188
+ if (
189
+ prev_is_special
190
+ and i == 1
191
+ and self.add_prefix_space
192
+ and not token.startswith(SPIECE_UNDERLINE)
193
+ and self.spaces_for_interleaved_special_tokens
194
+ ):
195
+ out_string += " "
196
+ current_sub_tokens.append(token)
197
+ prev_is_special = False
198
+ out_string += self.sp_model.decode(current_sub_tokens)
199
+ return out_string
200
+
201
+ def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
202
+ """
203
+ Save the vocabulary and special tokens file to a directory.
204
+
205
+ Args:
206
+ save_directory (`str`):
207
+ The directory in which to save the vocabulary.
208
+
209
+ Returns:
210
+ `Tuple(str)`: Paths to the files saved.
211
+ """
212
+ if not os.path.isdir(save_directory):
213
+ logger.error(f"Vocabulary path ({save_directory}) should be a directory")
214
+ return
215
+ out_vocab_file = os.path.join(save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"])
216
+
217
+ if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
218
+ copyfile(self.vocab_file, out_vocab_file)
219
+ elif not os.path.isfile(self.vocab_file):
220
+ with open(out_vocab_file, "wb") as fi:
221
+ content_spiece_model = self.sp_model.serialized_model_proto()
222
+ fi.write(content_spiece_model)
223
+
224
+ return (out_vocab_file,)
225
+
226
+ def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
227
+ bos_token_id = [self.bos_token_id] if self.add_bos_token else []
228
+ eos_token_id = [self.eos_token_id] if self.add_eos_token else []
229
+
230
+ output = bos_token_id + token_ids_0 + eos_token_id
231
+
232
+ if token_ids_1 is not None:
233
+ output = output + bos_token_id + token_ids_1 + eos_token_id
234
+
235
+ return output
236
+
237
+ def get_special_tokens_mask(
238
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
239
+ ) -> List[int]:
240
+ """
241
+ Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
242
+ special tokens using the tokenizer `prepare_for_model` method.
243
+
244
+ Args:
245
+ token_ids_0 (`List[int]`):
246
+ List of IDs.
247
+ token_ids_1 (`List[int]`, *optional*):
248
+ Optional second list of IDs for sequence pairs.
249
+ already_has_special_tokens (`bool`, *optional*, defaults to `False`):
250
+ Whether or not the token list is already formatted with special tokens for the model.
251
+
252
+ Returns:
253
+ `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
254
+ """
255
+ if already_has_special_tokens:
256
+ return super().get_special_tokens_mask(token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True)
257
+
258
+ bos_token_id = [1] if self.add_bos_token else []
259
+ eos_token_id = [1] if self.add_eos_token else []
260
+
261
+ if token_ids_1 is None:
262
+ return bos_token_id + ([0] * len(token_ids_0)) + eos_token_id
263
+ return bos_token_id + ([0] * len(token_ids_0)) + eos_token_id + bos_token_id + ([0] * len(token_ids_1)) + eos_token_id
264
+
265
+ def create_token_type_ids_from_sequences(self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None) -> List[int]:
266
+ """
267
+ Creates a mask from the two sequences passed to be used in a sequence-pair classification task. An ALBERT
268
+ sequence pair mask has the following format:
269
+
270
+ ```
271
+ 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1
272
+ | first sequence | second sequence |
273
+ ```
274
+
275
+ if token_ids_1 is None, only returns the first portion of the mask (0s).
276
+
277
+ Args:
278
+ token_ids_0 (`List[int]`):
279
+ List of ids.
280
+ token_ids_1 (`List[int]`, *optional*):
281
+ Optional second list of IDs for sequence pairs.
282
+
283
+ Returns:
284
+ `List[int]`: List of [token type IDs](../glossary#token-type-ids) according to the given sequence(s).
285
+ """
286
+ bos_token_id = [self.bos_token_id] if self.add_bos_token else []
287
+ eos_token_id = [self.eos_token_id] if self.add_eos_token else []
288
+
289
+ output = [0] * len(bos_token_id + token_ids_0 + eos_token_id)
290
+
291
+ if token_ids_1 is not None:
292
+ output += [1] * len(bos_token_id + token_ids_1 + eos_token_id)
293
+
294
+ return output
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcacff3229854f5103ee7a85473a30ca9a8b3a68f3aae9b7479574b23ac2256b
3
+ size 2475075
tokenizer_config.json ADDED
@@ -0,0 +1,249 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "128111": {
31
+ "content": "<restate>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "128112": {
39
+ "content": "</restate>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "128113": {
47
+ "content": "<planning>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "128114": {
55
+ "content": "</planning>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "128115": {
63
+ "content": "<recollect>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "128116": {
71
+ "content": "</recollect>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "128117": {
79
+ "content": "<execution>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "128118": {
87
+ "content": "</execution>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "128119": {
95
+ "content": "<review>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "128120": {
103
+ "content": "</review>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "128121": {
111
+ "content": "<summarize>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "128122": {
119
+ "content": "</summarize>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "128123": {
127
+ "content": "<retry>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ },
134
+ "128124": {
135
+ "content": "</retry>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": true
141
+ },
142
+ "128125": {
143
+ "content": "<conclude>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": true
149
+ },
150
+ "128126": {
151
+ "content": "</conclude>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": true
157
+ },
158
+ "128127": {
159
+ "content": "<|plugin|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": true
165
+ },
166
+ "128128": {
167
+ "content": "<|interpreter|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": true
173
+ },
174
+ "128129": {
175
+ "content": "<|action_end|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": true
181
+ },
182
+ "128130": {
183
+ "content": "<|action_start|>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": true
189
+ },
190
+ "128131": {
191
+ "content": "<|im_end|>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": true
197
+ },
198
+ "128132": {
199
+ "content": "<|im_start|>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": true
205
+ }
206
+ },
207
+ "additional_special_tokens": [
208
+ "<|im_start|>",
209
+ "<|im_end|>",
210
+ "<|action_start|>",
211
+ "<|action_end|>",
212
+ "<|interpreter|>",
213
+ "<|plugin|>",
214
+ "<restate>",
215
+ "</restate>",
216
+ "<planning>",
217
+ "</planning>",
218
+ "<recollect>",
219
+ "</recollect>",
220
+ "<execution>",
221
+ "</execution>",
222
+ "<review>",
223
+ "</review>",
224
+ "<summarize>",
225
+ "</summarize>",
226
+ "<retry>",
227
+ "</retry>",
228
+ "<conclude>",
229
+ "</conclude>"
230
+ ],
231
+ "auto_map": {
232
+ "AutoTokenizer": [
233
+ "tokenization_internlm3.InternLM3Tokenizer",
234
+ null
235
+ ]
236
+ },
237
+ "bos_token": "<s>",
238
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
239
+ "clean_up_tokenization_spaces": false,
240
+ "eos_token": "</s>",
241
+ "extra_special_tokens": {},
242
+ "model_max_length": 1000000000000000019884624838656,
243
+ "pad_token": "</s>",
244
+ "sp_model_kwargs": {},
245
+ "spaces_between_special_tokens": false,
246
+ "tokenizer_class": "InternLM3Tokenizer",
247
+ "unk_token": "<unk>",
248
+ "use_default_system_prompt": false
249
+ }
vocabulary.json ADDED
The diff for this file is too large to render. See raw diff