himmeow commited on
Commit
9bb7e11
1 Parent(s): 4802eab

(Trained with Unsloth)

Browse files
config.json CHANGED
@@ -22,9 +22,9 @@
22
  "rms_norm_eps": 1e-06,
23
  "rope_scaling": null,
24
  "rope_theta": 10000.0,
25
- "torch_dtype": "bfloat16",
26
- "transformers_version": "4.42.4",
27
- "unsloth_version": "2024.7",
28
  "use_cache": true,
29
  "vocab_size": 256000
30
  }
 
22
  "rms_norm_eps": 1e-06,
23
  "rope_scaling": null,
24
  "rope_theta": 10000.0,
25
+ "torch_dtype": "float16",
26
+ "transformers_version": "4.43.3",
27
+ "unsloth_version": "2024.8",
28
  "use_cache": true,
29
  "vocab_size": 256000
30
  }
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "bos_token_id": 2,
4
  "eos_token_id": 1,
5
  "pad_token_id": 0,
6
- "transformers_version": "4.42.4"
7
  }
 
3
  "bos_token_id": 2,
4
  "eos_token_id": 1,
5
  "pad_token_id": 0,
6
+ "transformers_version": "4.43.3"
7
  }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4948b29e6f7782fc0e75229d706c71553f8b6cabf32d318e9b1f6918ad5ff141
3
+ size 4945280638
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73b5cf18d79a9e77d82bd007704e2e7088f6a64db64a89d52f7649115bc5b8e4
3
+ size 67123512
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5012344832
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
7
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
8
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
9
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
10
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
11
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
12
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
13
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
14
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
15
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
16
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
17
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
18
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
19
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
20
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
21
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
22
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
23
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
24
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
25
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
26
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
27
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
28
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
29
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
30
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
31
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
32
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
33
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
34
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
35
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
36
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
37
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
38
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
39
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
40
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
41
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
42
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
43
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
44
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
45
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
46
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
47
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
48
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
49
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
50
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
51
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
52
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
53
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
54
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
55
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
56
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
57
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
58
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
59
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
60
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
61
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
62
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
63
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
64
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
65
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
66
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
67
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
68
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
69
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
70
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
71
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
72
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
73
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
74
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
75
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
76
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
77
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
78
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
79
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
80
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
81
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
82
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
83
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
84
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
85
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
86
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
87
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
88
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
89
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
90
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
91
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
92
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
93
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
94
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
95
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
96
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
97
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
98
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
99
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
100
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
101
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
102
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
103
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
104
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
105
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
106
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
107
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
108
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
109
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
110
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
111
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
112
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
113
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
114
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
115
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
116
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
117
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
118
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
119
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
120
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
121
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
122
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
123
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
124
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
125
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
126
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
127
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
128
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
129
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
130
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
131
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
132
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
133
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
134
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
135
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
136
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
137
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
138
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
139
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
140
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
141
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
142
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
143
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
144
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
145
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
146
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
147
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
148
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
149
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
150
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
151
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
152
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
153
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
154
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
155
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
156
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
157
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
158
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
159
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
160
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
161
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
162
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
163
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
164
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
165
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
166
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
167
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
168
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
169
+ "model.norm.weight": "pytorch_model-00002-of-00002.bin"
170
+ }
171
+ }