Hugging Face's logo

mlc-ai
/
Qwen2-0.5B-Instruct-q0f16-MLC

MLC-LLM
web-llm
Model card Files Community
riczhou commited on
Commit
586caa8
•
1 Parent(s): 9106c6f

Initial commit

Browse files
Files changed (32) hide show
  1. logs.txt +0 -0
  2. merges.txt +0 -0
  3. mlc-chat-config.json +81 -0
  4. ndarray-cache.json +2006 -0
  5. params_shard_0.bin +3 -0
  6. params_shard_1.bin +3 -0
  7. params_shard_10.bin +3 -0
  8. params_shard_11.bin +3 -0
  9. params_shard_12.bin +3 -0
  10. params_shard_13.bin +3 -0
  11. params_shard_14.bin +3 -0
  12. params_shard_15.bin +3 -0
  13. params_shard_16.bin +3 -0
  14. params_shard_17.bin +3 -0
  15. params_shard_18.bin +3 -0
  16. params_shard_19.bin +3 -0
  17. params_shard_2.bin +3 -0
  18. params_shard_20.bin +3 -0
  19. params_shard_21.bin +3 -0
  20. params_shard_22.bin +3 -0
  21. params_shard_23.bin +3 -0
  22. params_shard_24.bin +3 -0
  23. params_shard_3.bin +3 -0
  24. params_shard_4.bin +3 -0
  25. params_shard_5.bin +3 -0
  26. params_shard_6.bin +3 -0
  27. params_shard_7.bin +3 -0
  28. params_shard_8.bin +3 -0
  29. params_shard_9.bin +3 -0
  30. tokenizer.json +0 -0
  31. tokenizer_config.json +40 -0
  32. vocab.json +0 -0
logs.txt ADDED
The diff for this file is too large to render. See raw diff
 
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
mlc-chat-config.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.1.0",
3
+ "model_type": "qwen2",
4
+ "quantization": "q0f16",
5
+ "model_config": {
6
+ "hidden_act": "silu",
7
+ "hidden_size": 896,
8
+ "intermediate_size": 4864,
9
+ "num_attention_heads": 14,
10
+ "num_hidden_layers": 24,
11
+ "num_key_value_heads": 2,
12
+ "rms_norm_eps": 1e-06,
13
+ "rope_theta": 1000000.0,
14
+ "vocab_size": 151936,
15
+ "tie_word_embeddings": true,
16
+ "context_window_size": 32768,
17
+ "prefill_chunk_size": 2048,
18
+ "tensor_parallel_shards": 1,
19
+ "head_dim": 64,
20
+ "dtype": "float32",
21
+ "max_batch_size": 80
22
+ },
23
+ "vocab_size": 151936,
24
+ "context_window_size": 32768,
25
+ "sliding_window_size": -1,
26
+ "prefill_chunk_size": 2048,
27
+ "attention_sink_size": -1,
28
+ "tensor_parallel_shards": 1,
29
+ "temperature": 0.7,
30
+ "presence_penalty": 0.0,
31
+ "frequency_penalty": 0.0,
32
+ "repetition_penalty": 1.1,
33
+ "top_p": 0.8,
34
+ "tokenizer_files": [
35
+ "tokenizer.json",
36
+ "vocab.json",
37
+ "merges.txt",
38
+ "tokenizer_config.json"
39
+ ],
40
+ "tokenizer_info": {
41
+ "token_postproc_method": "byte_level",
42
+ "prepend_space_in_encode": false,
43
+ "strip_space_in_decode": false
44
+ },
45
+ "conv_template": {
46
+ "name": "chatml",
47
+ "system_template": "<|im_start|>system\n{system_message}",
48
+ "system_message": "A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.",
49
+ "system_prefix_token_ids": null,
50
+ "add_role_after_system_message": true,
51
+ "roles": {
52
+ "user": "<|im_start|>user",
53
+ "assistant": "<|im_start|>assistant"
54
+ },
55
+ "role_templates": {
56
+ "user": "{user_message}",
57
+ "assistant": "{assistant_message}",
58
+ "tool": "{tool_message}"
59
+ },
60
+ "messages": [],
61
+ "seps": [
62
+ "<|im_end|>\n"
63
+ ],
64
+ "role_content_sep": "\n",
65
+ "role_empty_sep": "\n",
66
+ "stop_str": [
67
+ "<|im_end|>"
68
+ ],
69
+ "stop_token_ids": [
70
+ 2
71
+ ],
72
+ "function_string": "",
73
+ "use_function_calling": false
74
+ },
75
+ "pad_token_id": 151643,
76
+ "bos_token_id": 151643,
77
+ "eos_token_id": [
78
+ 151645,
79
+ 151643
80
+ ]
81
+ }
ndarray-cache.json ADDED
@@ -0,0 +1,2006 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "ParamSize": 170,
4
+ "ParamBytes": 988065536.0,
5
+ "BitsPerParam": 16.0
6
+ },
7
+ "records": [
8
+ {
9
+ "dataPath": "params_shard_0.bin",
10
+ "format": "raw-shard",
11
+ "nbytes": 272269312,
12
+ "records": [
13
+ {
14
+ "name": "model.embed_tokens.weight",
15
+ "shape": [
16
+ 151936,
17
+ 896
18
+ ],
19
+ "dtype": "float16",
20
+ "format": "f32-to-bf16",
21
+ "nbytes": 272269312,
22
+ "byteOffset": 0
23
+ }
24
+ ],
25
+ "md5sum": "9c2276977b80f698556816421622352a"
26
+ },
27
+ {
28
+ "dataPath": "params_shard_1.bin",
29
+ "format": "raw-shard",
30
+ "nbytes": 29826560,
31
+ "records": [
32
+ {
33
+ "name": "model.layers.0.input_layernorm.weight",
34
+ "shape": [
35
+ 896
36
+ ],
37
+ "dtype": "float16",
38
+ "format": "f32-to-bf16",
39
+ "nbytes": 1792,
40
+ "byteOffset": 0
41
+ },
42
+ {
43
+ "name": "model.layers.0.mlp.down_proj.weight",
44
+ "shape": [
45
+ 896,
46
+ 4864
47
+ ],
48
+ "dtype": "float16",
49
+ "format": "f32-to-bf16",
50
+ "nbytes": 8716288,
51
+ "byteOffset": 1792
52
+ },
53
+ {
54
+ "name": "model.layers.0.mlp.gate_up_proj.weight",
55
+ "shape": [
56
+ 9728,
57
+ 896
58
+ ],
59
+ "dtype": "float16",
60
+ "format": "f32-to-bf16",
61
+ "nbytes": 17432576,
62
+ "byteOffset": 8718080
63
+ },
64
+ {
65
+ "name": "model.layers.0.post_attention_layernorm.weight",
66
+ "shape": [
67
+ 896
68
+ ],
69
+ "dtype": "float16",
70
+ "format": "f32-to-bf16",
71
+ "nbytes": 1792,
72
+ "byteOffset": 26150656
73
+ },
74
+ {
75
+ "name": "model.layers.0.self_attn.c_attn.bias",
76
+ "shape": [
77
+ 1152
78
+ ],
79
+ "dtype": "float16",
80
+ "format": "f32-to-bf16",
81
+ "nbytes": 2304,
82
+ "byteOffset": 26152448
83
+ },
84
+ {
85
+ "name": "model.layers.0.self_attn.c_attn.weight",
86
+ "shape": [
87
+ 1152,
88
+ 896
89
+ ],
90
+ "dtype": "float16",
91
+ "format": "f32-to-bf16",
92
+ "nbytes": 2064384,
93
+ "byteOffset": 26154752
94
+ },
95
+ {
96
+ "name": "model.layers.0.self_attn.o_proj.weight",
97
+ "shape": [
98
+ 896,
99
+ 896
100
+ ],
101
+ "dtype": "float16",
102
+ "format": "f32-to-bf16",
103
+ "nbytes": 1605632,
104
+ "byteOffset": 28219136
105
+ },
106
+ {
107
+ "name": "model.layers.1.input_layernorm.weight",
108
+ "shape": [
109
+ 896
110
+ ],
111
+ "dtype": "float16",
112
+ "format": "f32-to-bf16",
113
+ "nbytes": 1792,
114
+ "byteOffset": 29824768
115
+ }
116
+ ],
117
+ "md5sum": "7aa56db3316a36fecc827f1134159fc3"
118
+ },
119
+ {
120
+ "dataPath": "params_shard_2.bin",
121
+ "format": "raw-shard",
122
+ "nbytes": 29824768,
123
+ "records": [
124
+ {
125
+ "name": "model.layers.1.mlp.down_proj.weight",
126
+ "shape": [
127
+ 896,
128
+ 4864
129
+ ],
130
+ "dtype": "float16",
131
+ "format": "f32-to-bf16",
132
+ "nbytes": 8716288,
133
+ "byteOffset": 0
134
+ },
135
+ {
136
+ "name": "model.layers.1.mlp.gate_up_proj.weight",
137
+ "shape": [
138
+ 9728,
139
+ 896
140
+ ],
141
+ "dtype": "float16",
142
+ "format": "f32-to-bf16",
143
+ "nbytes": 17432576,
144
+ "byteOffset": 8716288
145
+ },
146
+ {
147
+ "name": "model.layers.1.post_attention_layernorm.weight",
148
+ "shape": [
149
+ 896
150
+ ],
151
+ "dtype": "float16",
152
+ "format": "f32-to-bf16",
153
+ "nbytes": 1792,
154
+ "byteOffset": 26148864
155
+ },
156
+ {
157
+ "name": "model.layers.1.self_attn.c_attn.bias",
158
+ "shape": [
159
+ 1152
160
+ ],
161
+ "dtype": "float16",
162
+ "format": "f32-to-bf16",
163
+ "nbytes": 2304,
164
+ "byteOffset": 26150656
165
+ },
166
+ {
167
+ "name": "model.layers.1.self_attn.c_attn.weight",
168
+ "shape": [
169
+ 1152,
170
+ 896
171
+ ],
172
+ "dtype": "float16",
173
+ "format": "f32-to-bf16",
174
+ "nbytes": 2064384,
175
+ "byteOffset": 26152960
176
+ },
177
+ {
178
+ "name": "model.layers.1.self_attn.o_proj.weight",
179
+ "shape": [
180
+ 896,
181
+ 896
182
+ ],
183
+ "dtype": "float16",
184
+ "format": "f32-to-bf16",
185
+ "nbytes": 1605632,
186
+ "byteOffset": 28217344
187
+ },
188
+ {
189
+ "name": "model.layers.10.input_layernorm.weight",
190
+ "shape": [
191
+ 896
192
+ ],
193
+ "dtype": "float16",
194
+ "format": "f32-to-bf16",
195
+ "nbytes": 1792,
196
+ "byteOffset": 29822976
197
+ }
198
+ ],
199
+ "md5sum": "6a00a74fef6caa9f59a24baef57bdc2c"
200
+ },
201
+ {
202
+ "dataPath": "params_shard_3.bin",
203
+ "format": "raw-shard",
204
+ "nbytes": 29824768,
205
+ "records": [
206
+ {
207
+ "name": "model.layers.10.mlp.down_proj.weight",
208
+ "shape": [
209
+ 896,
210
+ 4864
211
+ ],
212
+ "dtype": "float16",
213
+ "format": "f32-to-bf16",
214
+ "nbytes": 8716288,
215
+ "byteOffset": 0
216
+ },
217
+ {
218
+ "name": "model.layers.10.mlp.gate_up_proj.weight",
219
+ "shape": [
220
+ 9728,
221
+ 896
222
+ ],
223
+ "dtype": "float16",
224
+ "format": "f32-to-bf16",
225
+ "nbytes": 17432576,
226
+ "byteOffset": 8716288
227
+ },
228
+ {
229
+ "name": "model.layers.10.post_attention_layernorm.weight",
230
+ "shape": [
231
+ 896
232
+ ],
233
+ "dtype": "float16",
234
+ "format": "f32-to-bf16",
235
+ "nbytes": 1792,
236
+ "byteOffset": 26148864
237
+ },
238
+ {
239
+ "name": "model.layers.10.self_attn.c_attn.bias",
240
+ "shape": [
241
+ 1152
242
+ ],
243
+ "dtype": "float16",
244
+ "format": "f32-to-bf16",
245
+ "nbytes": 2304,
246
+ "byteOffset": 26150656
247
+ },
248
+ {
249
+ "name": "model.layers.10.self_attn.c_attn.weight",
250
+ "shape": [
251
+ 1152,
252
+ 896
253
+ ],
254
+ "dtype": "float16",
255
+ "format": "f32-to-bf16",
256
+ "nbytes": 2064384,
257
+ "byteOffset": 26152960
258
+ },
259
+ {
260
+ "name": "model.layers.10.self_attn.o_proj.weight",
261
+ "shape": [
262
+ 896,
263
+ 896
264
+ ],
265
+ "dtype": "float16",
266
+ "format": "f32-to-bf16",
267
+ "nbytes": 1605632,
268
+ "byteOffset": 28217344
269
+ },
270
+ {
271
+ "name": "model.layers.11.input_layernorm.weight",
272
+ "shape": [
273
+ 896
274
+ ],
275
+ "dtype": "float16",
276
+ "format": "f32-to-bf16",
277
+ "nbytes": 1792,
278
+ "byteOffset": 29822976
279
+ }
280
+ ],
281
+ "md5sum": "9be229aa9f9c26442c7d3e7fbc17db2a"
282
+ },
283
+ {
284
+ "dataPath": "params_shard_4.bin",
285
+ "format": "raw-shard",
286
+ "nbytes": 29824768,
287
+ "records": [
288
+ {
289
+ "name": "model.layers.11.mlp.down_proj.weight",
290
+ "shape": [
291
+ 896,
292
+ 4864
293
+ ],
294
+ "dtype": "float16",
295
+ "format": "f32-to-bf16",
296
+ "nbytes": 8716288,
297
+ "byteOffset": 0
298
+ },
299
+ {
300
+ "name": "model.layers.11.mlp.gate_up_proj.weight",
301
+ "shape": [
302
+ 9728,
303
+ 896
304
+ ],
305
+ "dtype": "float16",
306
+ "format": "f32-to-bf16",
307
+ "nbytes": 17432576,
308
+ "byteOffset": 8716288
309
+ },
310
+ {
311
+ "name": "model.layers.11.post_attention_layernorm.weight",
312
+ "shape": [
313
+ 896
314
+ ],
315
+ "dtype": "float16",
316
+ "format": "f32-to-bf16",
317
+ "nbytes": 1792,
318
+ "byteOffset": 26148864
319
+ },
320
+ {
321
+ "name": "model.layers.11.self_attn.c_attn.bias",
322
+ "shape": [
323
+ 1152
324
+ ],
325
+ "dtype": "float16",
326
+ "format": "f32-to-bf16",
327
+ "nbytes": 2304,
328
+ "byteOffset": 26150656
329
+ },
330
+ {
331
+ "name": "model.layers.11.self_attn.c_attn.weight",
332
+ "shape": [
333
+ 1152,
334
+ 896
335
+ ],
336
+ "dtype": "float16",
337
+ "format": "f32-to-bf16",
338
+ "nbytes": 2064384,
339
+ "byteOffset": 26152960
340
+ },
341
+ {
342
+ "name": "model.layers.11.self_attn.o_proj.weight",
343
+ "shape": [
344
+ 896,
345
+ 896
346
+ ],
347
+ "dtype": "float16",
348
+ "format": "f32-to-bf16",
349
+ "nbytes": 1605632,
350
+ "byteOffset": 28217344
351
+ },
352
+ {
353
+ "name": "model.layers.12.input_layernorm.weight",
354
+ "shape": [
355
+ 896
356
+ ],
357
+ "dtype": "float16",
358
+ "format": "f32-to-bf16",
359
+ "nbytes": 1792,
360
+ "byteOffset": 29822976
361
+ }
362
+ ],
363
+ "md5sum": "6e4cdce7c71f7b492b9bc49e2439a98c"
364
+ },
365
+ {
366
+ "dataPath": "params_shard_5.bin",
367
+ "format": "raw-shard",
368
+ "nbytes": 29824768,
369
+ "records": [
370
+ {
371
+ "name": "model.layers.12.mlp.down_proj.weight",
372
+ "shape": [
373
+ 896,
374
+ 4864
375
+ ],
376
+ "dtype": "float16",
377
+ "format": "f32-to-bf16",
378
+ "nbytes": 8716288,
379
+ "byteOffset": 0
380
+ },
381
+ {
382
+ "name": "model.layers.12.mlp.gate_up_proj.weight",
383
+ "shape": [
384
+ 9728,
385
+ 896
386
+ ],
387
+ "dtype": "float16",
388
+ "format": "f32-to-bf16",
389
+ "nbytes": 17432576,
390
+ "byteOffset": 8716288
391
+ },
392
+ {
393
+ "name": "model.layers.12.post_attention_layernorm.weight",
394
+ "shape": [
395
+ 896
396
+ ],
397
+ "dtype": "float16",
398
+ "format": "f32-to-bf16",
399
+ "nbytes": 1792,
400
+ "byteOffset": 26148864
401
+ },
402
+ {
403
+ "name": "model.layers.12.self_attn.c_attn.bias",
404
+ "shape": [
405
+ 1152
406
+ ],
407
+ "dtype": "float16",
408
+ "format": "f32-to-bf16",
409
+ "nbytes": 2304,
410
+ "byteOffset": 26150656
411
+ },
412
+ {
413
+ "name": "model.layers.12.self_attn.c_attn.weight",
414
+ "shape": [
415
+ 1152,
416
+ 896
417
+ ],
418
+ "dtype": "float16",
419
+ "format": "f32-to-bf16",
420
+ "nbytes": 2064384,
421
+ "byteOffset": 26152960
422
+ },
423
+ {
424
+ "name": "model.layers.12.self_attn.o_proj.weight",
425
+ "shape": [
426
+ 896,
427
+ 896
428
+ ],
429
+ "dtype": "float16",
430
+ "format": "f32-to-bf16",
431
+ "nbytes": 1605632,
432
+ "byteOffset": 28217344
433
+ },
434
+ {
435
+ "name": "model.layers.13.input_layernorm.weight",
436
+ "shape": [
437
+ 896
438
+ ],
439
+ "dtype": "float16",
440
+ "format": "f32-to-bf16",
441
+ "nbytes": 1792,
442
+ "byteOffset": 29822976
443
+ }
444
+ ],
445
+ "md5sum": "6b0de293079e94b9ce911a65aee7a5e9"
446
+ },
447
+ {
448
+ "dataPath": "params_shard_6.bin",
449
+ "format": "raw-shard",
450
+ "nbytes": 29824768,
451
+ "records": [
452
+ {
453
+ "name": "model.layers.13.mlp.down_proj.weight",
454
+ "shape": [
455
+ 896,
456
+ 4864
457
+ ],
458
+ "dtype": "float16",
459
+ "format": "f32-to-bf16",
460
+ "nbytes": 8716288,
461
+ "byteOffset": 0
462
+ },
463
+ {
464
+ "name": "model.layers.13.mlp.gate_up_proj.weight",
465
+ "shape": [
466
+ 9728,
467
+ 896
468
+ ],
469
+ "dtype": "float16",
470
+ "format": "f32-to-bf16",
471
+ "nbytes": 17432576,
472
+ "byteOffset": 8716288
473
+ },
474
+ {
475
+ "name": "model.layers.13.post_attention_layernorm.weight",
476
+ "shape": [
477
+ 896
478
+ ],
479
+ "dtype": "float16",
480
+ "format": "f32-to-bf16",
481
+ "nbytes": 1792,
482
+ "byteOffset": 26148864
483
+ },
484
+ {
485
+ "name": "model.layers.13.self_attn.c_attn.bias",
486
+ "shape": [
487
+ 1152
488
+ ],
489
+ "dtype": "float16",
490
+ "format": "f32-to-bf16",
491
+ "nbytes": 2304,
492
+ "byteOffset": 26150656
493
+ },
494
+ {
495
+ "name": "model.layers.13.self_attn.c_attn.weight",
496
+ "shape": [
497
+ 1152,
498
+ 896
499
+ ],
500
+ "dtype": "float16",
501
+ "format": "f32-to-bf16",
502
+ "nbytes": 2064384,
503
+ "byteOffset": 26152960
504
+ },
505
+ {
506
+ "name": "model.layers.13.self_attn.o_proj.weight",
507
+ "shape": [
508
+ 896,
509
+ 896
510
+ ],
511
+ "dtype": "float16",
512
+ "format": "f32-to-bf16",
513
+ "nbytes": 1605632,
514
+ "byteOffset": 28217344
515
+ },
516
+ {
517
+ "name": "model.layers.14.input_layernorm.weight",
518
+ "shape": [
519
+ 896
520
+ ],
521
+ "dtype": "float16",
522
+ "format": "f32-to-bf16",
523
+ "nbytes": 1792,
524
+ "byteOffset": 29822976
525
+ }
526
+ ],
527
+ "md5sum": "1bf604b0bac97f358a181e4e4ba49221"
528
+ },
529
+ {
530
+ "dataPath": "params_shard_7.bin",
531
+ "format": "raw-shard",
532
+ "nbytes": 29824768,
533
+ "records": [
534
+ {
535
+ "name": "model.layers.14.mlp.down_proj.weight",
536
+ "shape": [
537
+ 896,
538
+ 4864
539
+ ],
540
+ "dtype": "float16",
541
+ "format": "f32-to-bf16",
542
+ "nbytes": 8716288,
543
+ "byteOffset": 0
544
+ },
545
+ {
546
+ "name": "model.layers.14.mlp.gate_up_proj.weight",
547
+ "shape": [
548
+ 9728,
549
+ 896
550
+ ],
551
+ "dtype": "float16",
552
+ "format": "f32-to-bf16",
553
+ "nbytes": 17432576,
554
+ "byteOffset": 8716288
555
+ },
556
+ {
557
+ "name": "model.layers.14.post_attention_layernorm.weight",
558
+ "shape": [
559
+ 896
560
+ ],
561
+ "dtype": "float16",
562
+ "format": "f32-to-bf16",
563
+ "nbytes": 1792,
564
+ "byteOffset": 26148864
565
+ },
566
+ {
567
+ "name": "model.layers.14.self_attn.c_attn.bias",
568
+ "shape": [
569
+ 1152
570
+ ],
571
+ "dtype": "float16",
572
+ "format": "f32-to-bf16",
573
+ "nbytes": 2304,
574
+ "byteOffset": 26150656
575
+ },
576
+ {
577
+ "name": "model.layers.14.self_attn.c_attn.weight",
578
+ "shape": [
579
+ 1152,
580
+ 896
581
+ ],
582
+ "dtype": "float16",
583
+ "format": "f32-to-bf16",
584
+ "nbytes": 2064384,
585
+ "byteOffset": 26152960
586
+ },
587
+ {
588
+ "name": "model.layers.14.self_attn.o_proj.weight",
589
+ "shape": [
590
+ 896,
591
+ 896
592
+ ],
593
+ "dtype": "float16",
594
+ "format": "f32-to-bf16",
595
+ "nbytes": 1605632,
596
+ "byteOffset": 28217344
597
+ },
598
+ {
599
+ "name": "model.layers.15.input_layernorm.weight",
600
+ "shape": [
601
+ 896
602
+ ],
603
+ "dtype": "float16",
604
+ "format": "f32-to-bf16",
605
+ "nbytes": 1792,
606
+ "byteOffset": 29822976
607
+ }
608
+ ],
609
+ "md5sum": "7334eab63e02a09754db7edb4c2c79dd"
610
+ },
611
+ {
612
+ "dataPath": "params_shard_8.bin",
613
+ "format": "raw-shard",
614
+ "nbytes": 29824768,
615
+ "records": [
616
+ {
617
+ "name": "model.layers.15.mlp.down_proj.weight",
618
+ "shape": [
619
+ 896,
620
+ 4864
621
+ ],
622
+ "dtype": "float16",
623
+ "format": "f32-to-bf16",
624
+ "nbytes": 8716288,
625
+ "byteOffset": 0
626
+ },
627
+ {
628
+ "name": "model.layers.15.mlp.gate_up_proj.weight",
629
+ "shape": [
630
+ 9728,
631
+ 896
632
+ ],
633
+ "dtype": "float16",
634
+ "format": "f32-to-bf16",
635
+ "nbytes": 17432576,
636
+ "byteOffset": 8716288
637
+ },
638
+ {
639
+ "name": "model.layers.15.post_attention_layernorm.weight",
640
+ "shape": [
641
+ 896
642
+ ],
643
+ "dtype": "float16",
644
+ "format": "f32-to-bf16",
645
+ "nbytes": 1792,
646
+ "byteOffset": 26148864
647
+ },
648
+ {
649
+ "name": "model.layers.15.self_attn.c_attn.bias",
650
+ "shape": [
651
+ 1152
652
+ ],
653
+ "dtype": "float16",
654
+ "format": "f32-to-bf16",
655
+ "nbytes": 2304,
656
+ "byteOffset": 26150656
657
+ },
658
+ {
659
+ "name": "model.layers.15.self_attn.c_attn.weight",
660
+ "shape": [
661
+ 1152,
662
+ 896
663
+ ],
664
+ "dtype": "float16",
665
+ "format": "f32-to-bf16",
666
+ "nbytes": 2064384,
667
+ "byteOffset": 26152960
668
+ },
669
+ {
670
+ "name": "model.layers.15.self_attn.o_proj.weight",
671
+ "shape": [
672
+ 896,
673
+ 896
674
+ ],
675
+ "dtype": "float16",
676
+ "format": "f32-to-bf16",
677
+ "nbytes": 1605632,
678
+ "byteOffset": 28217344
679
+ },
680
+ {
681
+ "name": "model.layers.16.input_layernorm.weight",
682
+ "shape": [
683
+ 896
684
+ ],
685
+ "dtype": "float16",
686
+ "format": "f32-to-bf16",
687
+ "nbytes": 1792,
688
+ "byteOffset": 29822976
689
+ }
690
+ ],
691
+ "md5sum": "f574d5bc202cdc1aa7355bee5a80e934"
692
+ },
693
+ {
694
+ "dataPath": "params_shard_9.bin",
695
+ "format": "raw-shard",
696
+ "nbytes": 29824768,
697
+ "records": [
698
+ {
699
+ "name": "model.layers.16.mlp.down_proj.weight",
700
+ "shape": [
701
+ 896,
702
+ 4864
703
+ ],
704
+ "dtype": "float16",
705
+ "format": "f32-to-bf16",
706
+ "nbytes": 8716288,
707
+ "byteOffset": 0
708
+ },
709
+ {
710
+ "name": "model.layers.16.mlp.gate_up_proj.weight",
711
+ "shape": [
712
+ 9728,
713
+ 896
714
+ ],
715
+ "dtype": "float16",
716
+ "format": "f32-to-bf16",
717
+ "nbytes": 17432576,
718
+ "byteOffset": 8716288
719
+ },
720
+ {
721
+ "name": "model.layers.16.post_attention_layernorm.weight",
722
+ "shape": [
723
+ 896
724
+ ],
725
+ "dtype": "float16",
726
+ "format": "f32-to-bf16",
727
+ "nbytes": 1792,
728
+ "byteOffset": 26148864
729
+ },
730
+ {
731
+ "name": "model.layers.16.self_attn.c_attn.bias",
732
+ "shape": [
733
+ 1152
734
+ ],
735
+ "dtype": "float16",
736
+ "format": "f32-to-bf16",
737
+ "nbytes": 2304,
738
+ "byteOffset": 26150656
739
+ },
740
+ {
741
+ "name": "model.layers.16.self_attn.c_attn.weight",
742
+ "shape": [
743
+ 1152,
744
+ 896
745
+ ],
746
+ "dtype": "float16",
747
+ "format": "f32-to-bf16",
748
+ "nbytes": 2064384,
749
+ "byteOffset": 26152960
750
+ },
751
+ {
752
+ "name": "model.layers.16.self_attn.o_proj.weight",
753
+ "shape": [
754
+ 896,
755
+ 896
756
+ ],
757
+ "dtype": "float16",
758
+ "format": "f32-to-bf16",
759
+ "nbytes": 1605632,
760
+ "byteOffset": 28217344
761
+ },
762
+ {
763
+ "name": "model.layers.17.input_layernorm.weight",
764
+ "shape": [
765
+ 896
766
+ ],
767
+ "dtype": "float16",
768
+ "format": "f32-to-bf16",
769
+ "nbytes": 1792,
770
+ "byteOffset": 29822976
771
+ }
772
+ ],
773
+ "md5sum": "a800722636660cd9819c90c6a2ec1bad"
774
+ },
775
+ {
776
+ "dataPath": "params_shard_10.bin",
777
+ "format": "raw-shard",
778
+ "nbytes": 29824768,
779
+ "records": [
780
+ {
781
+ "name": "model.layers.17.mlp.down_proj.weight",
782
+ "shape": [
783
+ 896,
784
+ 4864
785
+ ],
786
+ "dtype": "float16",
787
+ "format": "f32-to-bf16",
788
+ "nbytes": 8716288,
789
+ "byteOffset": 0
790
+ },
791
+ {
792
+ "name": "model.layers.17.mlp.gate_up_proj.weight",
793
+ "shape": [
794
+ 9728,
795
+ 896
796
+ ],
797
+ "dtype": "float16",
798
+ "format": "f32-to-bf16",
799
+ "nbytes": 17432576,
800
+ "byteOffset": 8716288
801
+ },
802
+ {
803
+ "name": "model.layers.17.post_attention_layernorm.weight",
804
+ "shape": [
805
+ 896
806
+ ],
807
+ "dtype": "float16",
808
+ "format": "f32-to-bf16",
809
+ "nbytes": 1792,
810
+ "byteOffset": 26148864
811
+ },
812
+ {
813
+ "name": "model.layers.17.self_attn.c_attn.bias",
814
+ "shape": [
815
+ 1152
816
+ ],
817
+ "dtype": "float16",
818
+ "format": "f32-to-bf16",
819
+ "nbytes": 2304,
820
+ "byteOffset": 26150656
821
+ },
822
+ {
823
+ "name": "model.layers.17.self_attn.c_attn.weight",
824
+ "shape": [
825
+ 1152,
826
+ 896
827
+ ],
828
+ "dtype": "float16",
829
+ "format": "f32-to-bf16",
830
+ "nbytes": 2064384,
831
+ "byteOffset": 26152960
832
+ },
833
+ {
834
+ "name": "model.layers.17.self_attn.o_proj.weight",
835
+ "shape": [
836
+ 896,
837
+ 896
838
+ ],
839
+ "dtype": "float16",
840
+ "format": "f32-to-bf16",
841
+ "nbytes": 1605632,
842
+ "byteOffset": 28217344
843
+ },
844
+ {
845
+ "name": "model.layers.18.input_layernorm.weight",
846
+ "shape": [
847
+ 896
848
+ ],
849
+ "dtype": "float16",
850
+ "format": "f32-to-bf16",
851
+ "nbytes": 1792,
852
+ "byteOffset": 29822976
853
+ }
854
+ ],
855
+ "md5sum": "561af8229f6721c9fd16f4bfbdbe2a96"
856
+ },
857
+ {
858
+ "dataPath": "params_shard_11.bin",
859
+ "format": "raw-shard",
860
+ "nbytes": 29824768,
861
+ "records": [
862
+ {
863
+ "name": "model.layers.18.mlp.down_proj.weight",
864
+ "shape": [
865
+ 896,
866
+ 4864
867
+ ],
868
+ "dtype": "float16",
869
+ "format": "f32-to-bf16",
870
+ "nbytes": 8716288,
871
+ "byteOffset": 0
872
+ },
873
+ {
874
+ "name": "model.layers.18.mlp.gate_up_proj.weight",
875
+ "shape": [
876
+ 9728,
877
+ 896
878
+ ],
879
+ "dtype": "float16",
880
+ "format": "f32-to-bf16",
881
+ "nbytes": 17432576,
882
+ "byteOffset": 8716288
883
+ },
884
+ {
885
+ "name": "model.layers.18.post_attention_layernorm.weight",
886
+ "shape": [
887
+ 896
888
+ ],
889
+ "dtype": "float16",
890
+ "format": "f32-to-bf16",
891
+ "nbytes": 1792,
892
+ "byteOffset": 26148864
893
+ },
894
+ {
895
+ "name": "model.layers.18.self_attn.c_attn.bias",
896
+ "shape": [
897
+ 1152
898
+ ],
899
+ "dtype": "float16",
900
+ "format": "f32-to-bf16",
901
+ "nbytes": 2304,
902
+ "byteOffset": 26150656
903
+ },
904
+ {
905
+ "name": "model.layers.18.self_attn.c_attn.weight",
906
+ "shape": [
907
+ 1152,
908
+ 896
909
+ ],
910
+ "dtype": "float16",
911
+ "format": "f32-to-bf16",
912
+ "nbytes": 2064384,
913
+ "byteOffset": 26152960
914
+ },
915
+ {
916
+ "name": "model.layers.18.self_attn.o_proj.weight",
917
+ "shape": [
918
+ 896,
919
+ 896
920
+ ],
921
+ "dtype": "float16",
922
+ "format": "f32-to-bf16",
923
+ "nbytes": 1605632,
924
+ "byteOffset": 28217344
925
+ },
926
+ {
927
+ "name": "model.layers.19.input_layernorm.weight",
928
+ "shape": [
929
+ 896
930
+ ],
931
+ "dtype": "float16",
932
+ "format": "f32-to-bf16",
933
+ "nbytes": 1792,
934
+ "byteOffset": 29822976
935
+ }
936
+ ],
937
+ "md5sum": "10b83f14823650721c5941737a814795"
938
+ },
939
+ {
940
+ "dataPath": "params_shard_12.bin",
941
+ "format": "raw-shard",
942
+ "nbytes": 29824768,
943
+ "records": [
944
+ {
945
+ "name": "model.layers.19.mlp.down_proj.weight",
946
+ "shape": [
947
+ 896,
948
+ 4864
949
+ ],
950
+ "dtype": "float16",
951
+ "format": "f32-to-bf16",
952
+ "nbytes": 8716288,
953
+ "byteOffset": 0
954
+ },
955
+ {
956
+ "name": "model.layers.19.mlp.gate_up_proj.weight",
957
+ "shape": [
958
+ 9728,
959
+ 896
960
+ ],
961
+ "dtype": "float16",
962
+ "format": "f32-to-bf16",
963
+ "nbytes": 17432576,
964
+ "byteOffset": 8716288
965
+ },
966
+ {
967
+ "name": "model.layers.19.post_attention_layernorm.weight",
968
+ "shape": [
969
+ 896
970
+ ],
971
+ "dtype": "float16",
972
+ "format": "f32-to-bf16",
973
+ "nbytes": 1792,
974
+ "byteOffset": 26148864
975
+ },
976
+ {
977
+ "name": "model.layers.19.self_attn.c_attn.bias",
978
+ "shape": [
979
+ 1152
980
+ ],
981
+ "dtype": "float16",
982
+ "format": "f32-to-bf16",
983
+ "nbytes": 2304,
984
+ "byteOffset": 26150656
985
+ },
986
+ {
987
+ "name": "model.layers.19.self_attn.c_attn.weight",
988
+ "shape": [
989
+ 1152,
990
+ 896
991
+ ],
992
+ "dtype": "float16",
993
+ "format": "f32-to-bf16",
994
+ "nbytes": 2064384,
995
+ "byteOffset": 26152960
996
+ },
997
+ {
998
+ "name": "model.layers.19.self_attn.o_proj.weight",
999
+ "shape": [
1000
+ 896,
1001
+ 896
1002
+ ],
1003
+ "dtype": "float16",
1004
+ "format": "f32-to-bf16",
1005
+ "nbytes": 1605632,
1006
+ "byteOffset": 28217344
1007
+ },
1008
+ {
1009
+ "name": "model.layers.2.input_layernorm.weight",
1010
+ "shape": [
1011
+ 896
1012
+ ],
1013
+ "dtype": "float16",
1014
+ "format": "f32-to-bf16",
1015
+ "nbytes": 1792,
1016
+ "byteOffset": 29822976
1017
+ }
1018
+ ],
1019
+ "md5sum": "5ee494b14573733f13c47ff6d3d22242"
1020
+ },
1021
+ {
1022
+ "dataPath": "params_shard_13.bin",
1023
+ "format": "raw-shard",
1024
+ "nbytes": 29824768,
1025
+ "records": [
1026
+ {
1027
+ "name": "model.layers.2.mlp.down_proj.weight",
1028
+ "shape": [
1029
+ 896,
1030
+ 4864
1031
+ ],
1032
+ "dtype": "float16",
1033
+ "format": "f32-to-bf16",
1034
+ "nbytes": 8716288,
1035
+ "byteOffset": 0
1036
+ },
1037
+ {
1038
+ "name": "model.layers.2.mlp.gate_up_proj.weight",
1039
+ "shape": [
1040
+ 9728,
1041
+ 896
1042
+ ],
1043
+ "dtype": "float16",
1044
+ "format": "f32-to-bf16",
1045
+ "nbytes": 17432576,
1046
+ "byteOffset": 8716288
1047
+ },
1048
+ {
1049
+ "name": "model.layers.2.post_attention_layernorm.weight",
1050
+ "shape": [
1051
+ 896
1052
+ ],
1053
+ "dtype": "float16",
1054
+ "format": "f32-to-bf16",
1055
+ "nbytes": 1792,
1056
+ "byteOffset": 26148864
1057
+ },
1058
+ {
1059
+ "name": "model.layers.2.self_attn.c_attn.bias",
1060
+ "shape": [
1061
+ 1152
1062
+ ],
1063
+ "dtype": "float16",
1064
+ "format": "f32-to-bf16",
1065
+ "nbytes": 2304,
1066
+ "byteOffset": 26150656
1067
+ },
1068
+ {
1069
+ "name": "model.layers.2.self_attn.c_attn.weight",
1070
+ "shape": [
1071
+ 1152,
1072
+ 896
1073
+ ],
1074
+ "dtype": "float16",
1075
+ "format": "f32-to-bf16",
1076
+ "nbytes": 2064384,
1077
+ "byteOffset": 26152960
1078
+ },
1079
+ {
1080
+ "name": "model.layers.2.self_attn.o_proj.weight",
1081
+ "shape": [
1082
+ 896,
1083
+ 896
1084
+ ],
1085
+ "dtype": "float16",
1086
+ "format": "f32-to-bf16",
1087
+ "nbytes": 1605632,
1088
+ "byteOffset": 28217344
1089
+ },
1090
+ {
1091
+ "name": "model.layers.20.input_layernorm.weight",
1092
+ "shape": [
1093
+ 896
1094
+ ],
1095
+ "dtype": "float16",
1096
+ "format": "f32-to-bf16",
1097
+ "nbytes": 1792,
1098
+ "byteOffset": 29822976
1099
+ }
1100
+ ],
1101
+ "md5sum": "69d2cb1700a3a4d56e3722db3380bff2"
1102
+ },
1103
+ {
1104
+ "dataPath": "params_shard_14.bin",
1105
+ "format": "raw-shard",
1106
+ "nbytes": 29824768,
1107
+ "records": [
1108
+ {
1109
+ "name": "model.layers.20.mlp.down_proj.weight",
1110
+ "shape": [
1111
+ 896,
1112
+ 4864
1113
+ ],
1114
+ "dtype": "float16",
1115
+ "format": "f32-to-bf16",
1116
+ "nbytes": 8716288,
1117
+ "byteOffset": 0
1118
+ },
1119
+ {
1120
+ "name": "model.layers.20.mlp.gate_up_proj.weight",
1121
+ "shape": [
1122
+ 9728,
1123
+ 896
1124
+ ],
1125
+ "dtype": "float16",
1126
+ "format": "f32-to-bf16",
1127
+ "nbytes": 17432576,
1128
+ "byteOffset": 8716288
1129
+ },
1130
+ {
1131
+ "name": "model.layers.20.post_attention_layernorm.weight",
1132
+ "shape": [
1133
+ 896
1134
+ ],
1135
+ "dtype": "float16",
1136
+ "format": "f32-to-bf16",
1137
+ "nbytes": 1792,
1138
+ "byteOffset": 26148864
1139
+ },
1140
+ {
1141
+ "name": "model.layers.20.self_attn.c_attn.bias",
1142
+ "shape": [
1143
+ 1152
1144
+ ],
1145
+ "dtype": "float16",
1146
+ "format": "f32-to-bf16",
1147
+ "nbytes": 2304,
1148
+ "byteOffset": 26150656
1149
+ },
1150
+ {
1151
+ "name": "model.layers.20.self_attn.c_attn.weight",
1152
+ "shape": [
1153
+ 1152,
1154
+ 896
1155
+ ],
1156
+ "dtype": "float16",
1157
+ "format": "f32-to-bf16",
1158
+ "nbytes": 2064384,
1159
+ "byteOffset": 26152960
1160
+ },
1161
+ {
1162
+ "name": "model.layers.20.self_attn.o_proj.weight",
1163
+ "shape": [
1164
+ 896,
1165
+ 896
1166
+ ],
1167
+ "dtype": "float16",
1168
+ "format": "f32-to-bf16",
1169
+ "nbytes": 1605632,
1170
+ "byteOffset": 28217344
1171
+ },
1172
+ {
1173
+ "name": "model.layers.21.input_layernorm.weight",
1174
+ "shape": [
1175
+ 896
1176
+ ],
1177
+ "dtype": "float16",
1178
+ "format": "f32-to-bf16",
1179
+ "nbytes": 1792,
1180
+ "byteOffset": 29822976
1181
+ }
1182
+ ],
1183
+ "md5sum": "d9c2d36676d974f8ec6cdd67bacb136e"
1184
+ },
1185
+ {
1186
+ "dataPath": "params_shard_15.bin",
1187
+ "format": "raw-shard",
1188
+ "nbytes": 29824768,
1189
+ "records": [
1190
+ {
1191
+ "name": "model.layers.21.mlp.down_proj.weight",
1192
+ "shape": [
1193
+ 896,
1194
+ 4864
1195
+ ],
1196
+ "dtype": "float16",
1197
+ "format": "f32-to-bf16",
1198
+ "nbytes": 8716288,
1199
+ "byteOffset": 0
1200
+ },
1201
+ {
1202
+ "name": "model.layers.21.mlp.gate_up_proj.weight",
1203
+ "shape": [
1204
+ 9728,
1205
+ 896
1206
+ ],
1207
+ "dtype": "float16",
1208
+ "format": "f32-to-bf16",
1209
+ "nbytes": 17432576,
1210
+ "byteOffset": 8716288
1211
+ },
1212
+ {
1213
+ "name": "model.layers.21.post_attention_layernorm.weight",
1214
+ "shape": [
1215
+ 896
1216
+ ],
1217
+ "dtype": "float16",
1218
+ "format": "f32-to-bf16",
1219
+ "nbytes": 1792,
1220
+ "byteOffset": 26148864
1221
+ },
1222
+ {
1223
+ "name": "model.layers.21.self_attn.c_attn.bias",
1224
+ "shape": [
1225
+ 1152
1226
+ ],
1227
+ "dtype": "float16",
1228
+ "format": "f32-to-bf16",
1229
+ "nbytes": 2304,
1230
+ "byteOffset": 26150656
1231
+ },
1232
+ {
1233
+ "name": "model.layers.21.self_attn.c_attn.weight",
1234
+ "shape": [
1235
+ 1152,
1236
+ 896
1237
+ ],
1238
+ "dtype": "float16",
1239
+ "format": "f32-to-bf16",
1240
+ "nbytes": 2064384,
1241
+ "byteOffset": 26152960
1242
+ },
1243
+ {
1244
+ "name": "model.layers.21.self_attn.o_proj.weight",
1245
+ "shape": [
1246
+ 896,
1247
+ 896
1248
+ ],
1249
+ "dtype": "float16",
1250
+ "format": "f32-to-bf16",
1251
+ "nbytes": 1605632,
1252
+ "byteOffset": 28217344
1253
+ },
1254
+ {
1255
+ "name": "model.layers.22.input_layernorm.weight",
1256
+ "shape": [
1257
+ 896
1258
+ ],
1259
+ "dtype": "float16",
1260
+ "format": "f32-to-bf16",
1261
+ "nbytes": 1792,
1262
+ "byteOffset": 29822976
1263
+ }
1264
+ ],
1265
+ "md5sum": "c628deff33f36f21c9945aa36af0f699"
1266
+ },
1267
+ {
1268
+ "dataPath": "params_shard_16.bin",
1269
+ "format": "raw-shard",
1270
+ "nbytes": 29824768,
1271
+ "records": [
1272
+ {
1273
+ "name": "model.layers.22.mlp.down_proj.weight",
1274
+ "shape": [
1275
+ 896,
1276
+ 4864
1277
+ ],
1278
+ "dtype": "float16",
1279
+ "format": "f32-to-bf16",
1280
+ "nbytes": 8716288,
1281
+ "byteOffset": 0
1282
+ },
1283
+ {
1284
+ "name": "model.layers.22.mlp.gate_up_proj.weight",
1285
+ "shape": [
1286
+ 9728,
1287
+ 896
1288
+ ],
1289
+ "dtype": "float16",
1290
+ "format": "f32-to-bf16",
1291
+ "nbytes": 17432576,
1292
+ "byteOffset": 8716288
1293
+ },
1294
+ {
1295
+ "name": "model.layers.22.post_attention_layernorm.weight",
1296
+ "shape": [
1297
+ 896
1298
+ ],
1299
+ "dtype": "float16",
1300
+ "format": "f32-to-bf16",
1301
+ "nbytes": 1792,
1302
+ "byteOffset": 26148864
1303
+ },
1304
+ {
1305
+ "name": "model.layers.22.self_attn.c_attn.bias",
1306
+ "shape": [
1307
+ 1152
1308
+ ],
1309
+ "dtype": "float16",
1310
+ "format": "f32-to-bf16",
1311
+ "nbytes": 2304,
1312
+ "byteOffset": 26150656
1313
+ },
1314
+ {
1315
+ "name": "model.layers.22.self_attn.c_attn.weight",
1316
+ "shape": [
1317
+ 1152,
1318
+ 896
1319
+ ],
1320
+ "dtype": "float16",
1321
+ "format": "f32-to-bf16",
1322
+ "nbytes": 2064384,
1323
+ "byteOffset": 26152960
1324
+ },
1325
+ {
1326
+ "name": "model.layers.22.self_attn.o_proj.weight",
1327
+ "shape": [
1328
+ 896,
1329
+ 896
1330
+ ],
1331
+ "dtype": "float16",
1332
+ "format": "f32-to-bf16",
1333
+ "nbytes": 1605632,
1334
+ "byteOffset": 28217344
1335
+ },
1336
+ {
1337
+ "name": "model.layers.23.input_layernorm.weight",
1338
+ "shape": [
1339
+ 896
1340
+ ],
1341
+ "dtype": "float16",
1342
+ "format": "f32-to-bf16",
1343
+ "nbytes": 1792,
1344
+ "byteOffset": 29822976
1345
+ }
1346
+ ],
1347
+ "md5sum": "68476d60f51c53fec003188a0bae8ee3"
1348
+ },
1349
+ {
1350
+ "dataPath": "params_shard_17.bin",
1351
+ "format": "raw-shard",
1352
+ "nbytes": 29824768,
1353
+ "records": [
1354
+ {
1355
+ "name": "model.layers.23.mlp.down_proj.weight",
1356
+ "shape": [
1357
+ 896,
1358
+ 4864
1359
+ ],
1360
+ "dtype": "float16",
1361
+ "format": "f32-to-bf16",
1362
+ "nbytes": 8716288,
1363
+ "byteOffset": 0
1364
+ },
1365
+ {
1366
+ "name": "model.layers.23.mlp.gate_up_proj.weight",
1367
+ "shape": [
1368
+ 9728,
1369
+ 896
1370
+ ],
1371
+ "dtype": "float16",
1372
+ "format": "f32-to-bf16",
1373
+ "nbytes": 17432576,
1374
+ "byteOffset": 8716288
1375
+ },
1376
+ {
1377
+ "name": "model.layers.23.post_attention_layernorm.weight",
1378
+ "shape": [
1379
+ 896
1380
+ ],
1381
+ "dtype": "float16",
1382
+ "format": "f32-to-bf16",
1383
+ "nbytes": 1792,
1384
+ "byteOffset": 26148864
1385
+ },
1386
+ {
1387
+ "name": "model.layers.23.self_attn.c_attn.bias",
1388
+ "shape": [
1389
+ 1152
1390
+ ],
1391
+ "dtype": "float16",
1392
+ "format": "f32-to-bf16",
1393
+ "nbytes": 2304,
1394
+ "byteOffset": 26150656
1395
+ },
1396
+ {
1397
+ "name": "model.layers.23.self_attn.c_attn.weight",
1398
+ "shape": [
1399
+ 1152,
1400
+ 896
1401
+ ],
1402
+ "dtype": "float16",
1403
+ "format": "f32-to-bf16",
1404
+ "nbytes": 2064384,
1405
+ "byteOffset": 26152960
1406
+ },
1407
+ {
1408
+ "name": "model.layers.23.self_attn.o_proj.weight",
1409
+ "shape": [
1410
+ 896,
1411
+ 896
1412
+ ],
1413
+ "dtype": "float16",
1414
+ "format": "f32-to-bf16",
1415
+ "nbytes": 1605632,
1416
+ "byteOffset": 28217344
1417
+ },
1418
+ {
1419
+ "name": "model.layers.3.input_layernorm.weight",
1420
+ "shape": [
1421
+ 896
1422
+ ],
1423
+ "dtype": "float16",
1424
+ "format": "f32-to-bf16",
1425
+ "nbytes": 1792,
1426
+ "byteOffset": 29822976
1427
+ }
1428
+ ],
1429
+ "md5sum": "df7593f2d9cfc7fdc887c46a2fee65e9"
1430
+ },
1431
+ {
1432
+ "dataPath": "params_shard_18.bin",
1433
+ "format": "raw-shard",
1434
+ "nbytes": 29824768,
1435
+ "records": [
1436
+ {
1437
+ "name": "model.layers.3.mlp.down_proj.weight",
1438
+ "shape": [
1439
+ 896,
1440
+ 4864
1441
+ ],
1442
+ "dtype": "float16",
1443
+ "format": "f32-to-bf16",
1444
+ "nbytes": 8716288,
1445
+ "byteOffset": 0
1446
+ },
1447
+ {
1448
+ "name": "model.layers.3.mlp.gate_up_proj.weight",
1449
+ "shape": [
1450
+ 9728,
1451
+ 896
1452
+ ],
1453
+ "dtype": "float16",
1454
+ "format": "f32-to-bf16",
1455
+ "nbytes": 17432576,
1456
+ "byteOffset": 8716288
1457
+ },
1458
+ {
1459
+ "name": "model.layers.3.post_attention_layernorm.weight",
1460
+ "shape": [
1461
+ 896
1462
+ ],
1463
+ "dtype": "float16",
1464
+ "format": "f32-to-bf16",
1465
+ "nbytes": 1792,
1466
+ "byteOffset": 26148864
1467
+ },
1468
+ {
1469
+ "name": "model.layers.3.self_attn.c_attn.bias",
1470
+ "shape": [
1471
+ 1152
1472
+ ],
1473
+ "dtype": "float16",
1474
+ "format": "f32-to-bf16",
1475
+ "nbytes": 2304,
1476
+ "byteOffset": 26150656
1477
+ },
1478
+ {
1479
+ "name": "model.layers.3.self_attn.c_attn.weight",
1480
+ "shape": [
1481
+ 1152,
1482
+ 896
1483
+ ],
1484
+ "dtype": "float16",
1485
+ "format": "f32-to-bf16",
1486
+ "nbytes": 2064384,
1487
+ "byteOffset": 26152960
1488
+ },
1489
+ {
1490
+ "name": "model.layers.3.self_attn.o_proj.weight",
1491
+ "shape": [
1492
+ 896,
1493
+ 896
1494
+ ],
1495
+ "dtype": "float16",
1496
+ "format": "f32-to-bf16",
1497
+ "nbytes": 1605632,
1498
+ "byteOffset": 28217344
1499
+ },
1500
+ {
1501
+ "name": "model.layers.4.input_layernorm.weight",
1502
+ "shape": [
1503
+ 896
1504
+ ],
1505
+ "dtype": "float16",
1506
+ "format": "f32-to-bf16",
1507
+ "nbytes": 1792,
1508
+ "byteOffset": 29822976
1509
+ }
1510
+ ],
1511
+ "md5sum": "706df355d9a7994a83c46f474eee6c58"
1512
+ },
1513
+ {
1514
+ "dataPath": "params_shard_19.bin",
1515
+ "format": "raw-shard",
1516
+ "nbytes": 29824768,
1517
+ "records": [
1518
+ {
1519
+ "name": "model.layers.4.mlp.down_proj.weight",
1520
+ "shape": [
1521
+ 896,
1522
+ 4864
1523
+ ],
1524
+ "dtype": "float16",
1525
+ "format": "f32-to-bf16",
1526
+ "nbytes": 8716288,
1527
+ "byteOffset": 0
1528
+ },
1529
+ {
1530
+ "name": "model.layers.4.mlp.gate_up_proj.weight",
1531
+ "shape": [
1532
+ 9728,
1533
+ 896
1534
+ ],
1535
+ "dtype": "float16",
1536
+ "format": "f32-to-bf16",
1537
+ "nbytes": 17432576,
1538
+ "byteOffset": 8716288
1539
+ },
1540
+ {
1541
+ "name": "model.layers.4.post_attention_layernorm.weight",
1542
+ "shape": [
1543
+ 896
1544
+ ],
1545
+ "dtype": "float16",
1546
+ "format": "f32-to-bf16",
1547
+ "nbytes": 1792,
1548
+ "byteOffset": 26148864
1549
+ },
1550
+ {
1551
+ "name": "model.layers.4.self_attn.c_attn.bias",
1552
+ "shape": [
1553
+ 1152
1554
+ ],
1555
+ "dtype": "float16",
1556
+ "format": "f32-to-bf16",
1557
+ "nbytes": 2304,
1558
+ "byteOffset": 26150656
1559
+ },
1560
+ {
1561
+ "name": "model.layers.4.self_attn.c_attn.weight",
1562
+ "shape": [
1563
+ 1152,
1564
+ 896
1565
+ ],
1566
+ "dtype": "float16",
1567
+ "format": "f32-to-bf16",
1568
+ "nbytes": 2064384,
1569
+ "byteOffset": 26152960
1570
+ },
1571
+ {
1572
+ "name": "model.layers.4.self_attn.o_proj.weight",
1573
+ "shape": [
1574
+ 896,
1575
+ 896
1576
+ ],
1577
+ "dtype": "float16",
1578
+ "format": "f32-to-bf16",
1579
+ "nbytes": 1605632,
1580
+ "byteOffset": 28217344
1581
+ },
1582
+ {
1583
+ "name": "model.layers.5.input_layernorm.weight",
1584
+ "shape": [
1585
+ 896
1586
+ ],
1587
+ "dtype": "float16",
1588
+ "format": "f32-to-bf16",
1589
+ "nbytes": 1792,
1590
+ "byteOffset": 29822976
1591
+ }
1592
+ ],
1593
+ "md5sum": "7c36e162780e0fdc0a6a9b9e96f046bc"
1594
+ },
1595
+ {
1596
+ "dataPath": "params_shard_20.bin",
1597
+ "format": "raw-shard",
1598
+ "nbytes": 29824768,
1599
+ "records": [
1600
+ {
1601
+ "name": "model.layers.5.mlp.down_proj.weight",
1602
+ "shape": [
1603
+ 896,
1604
+ 4864
1605
+ ],
1606
+ "dtype": "float16",
1607
+ "format": "f32-to-bf16",
1608
+ "nbytes": 8716288,
1609
+ "byteOffset": 0
1610
+ },
1611
+ {
1612
+ "name": "model.layers.5.mlp.gate_up_proj.weight",
1613
+ "shape": [
1614
+ 9728,
1615
+ 896
1616
+ ],
1617
+ "dtype": "float16",
1618
+ "format": "f32-to-bf16",
1619
+ "nbytes": 17432576,
1620
+ "byteOffset": 8716288
1621
+ },
1622
+ {
1623
+ "name": "model.layers.5.post_attention_layernorm.weight",
1624
+ "shape": [
1625
+ 896
1626
+ ],
1627
+ "dtype": "float16",
1628
+ "format": "f32-to-bf16",
1629
+ "nbytes": 1792,
1630
+ "byteOffset": 26148864
1631
+ },
1632
+ {
1633
+ "name": "model.layers.5.self_attn.c_attn.bias",
1634
+ "shape": [
1635
+ 1152
1636
+ ],
1637
+ "dtype": "float16",
1638
+ "format": "f32-to-bf16",
1639
+ "nbytes": 2304,
1640
+ "byteOffset": 26150656
1641
+ },
1642
+ {
1643
+ "name": "model.layers.5.self_attn.c_attn.weight",
1644
+ "shape": [
1645
+ 1152,
1646
+ 896
1647
+ ],
1648
+ "dtype": "float16",
1649
+ "format": "f32-to-bf16",
1650
+ "nbytes": 2064384,
1651
+ "byteOffset": 26152960
1652
+ },
1653
+ {
1654
+ "name": "model.layers.5.self_attn.o_proj.weight",
1655
+ "shape": [
1656
+ 896,
1657
+ 896
1658
+ ],
1659
+ "dtype": "float16",
1660
+ "format": "f32-to-bf16",
1661
+ "nbytes": 1605632,
1662
+ "byteOffset": 28217344
1663
+ },
1664
+ {
1665
+ "name": "model.layers.6.input_layernorm.weight",
1666
+ "shape": [
1667
+ 896
1668
+ ],
1669
+ "dtype": "float16",
1670
+ "format": "f32-to-bf16",
1671
+ "nbytes": 1792,
1672
+ "byteOffset": 29822976
1673
+ }
1674
+ ],
1675
+ "md5sum": "1e6fbc4dc336e8b61a046012e748bf24"
1676
+ },
1677
+ {
1678
+ "dataPath": "params_shard_21.bin",
1679
+ "format": "raw-shard",
1680
+ "nbytes": 29824768,
1681
+ "records": [
1682
+ {
1683
+ "name": "model.layers.6.mlp.down_proj.weight",
1684
+ "shape": [
1685
+ 896,
1686
+ 4864
1687
+ ],
1688
+ "dtype": "float16",
1689
+ "format": "f32-to-bf16",
1690
+ "nbytes": 8716288,
1691
+ "byteOffset": 0
1692
+ },
1693
+ {
1694
+ "name": "model.layers.6.mlp.gate_up_proj.weight",
1695
+ "shape": [
1696
+ 9728,
1697
+ 896
1698
+ ],
1699
+ "dtype": "float16",
1700
+ "format": "f32-to-bf16",
1701
+ "nbytes": 17432576,
1702
+ "byteOffset": 8716288
1703
+ },
1704
+ {
1705
+ "name": "model.layers.6.post_attention_layernorm.weight",
1706
+ "shape": [
1707
+ 896
1708
+ ],
1709
+ "dtype": "float16",
1710
+ "format": "f32-to-bf16",
1711
+ "nbytes": 1792,
1712
+ "byteOffset": 26148864
1713
+ },
1714
+ {
1715
+ "name": "model.layers.6.self_attn.c_attn.bias",
1716
+ "shape": [
1717
+ 1152
1718
+ ],
1719
+ "dtype": "float16",
1720
+ "format": "f32-to-bf16",
1721
+ "nbytes": 2304,
1722
+ "byteOffset": 26150656
1723
+ },
1724
+ {
1725
+ "name": "model.layers.6.self_attn.c_attn.weight",
1726
+ "shape": [
1727
+ 1152,
1728
+ 896
1729
+ ],
1730
+ "dtype": "float16",
1731
+ "format": "f32-to-bf16",
1732
+ "nbytes": 2064384,
1733
+ "byteOffset": 26152960
1734
+ },
1735
+ {
1736
+ "name": "model.layers.6.self_attn.o_proj.weight",
1737
+ "shape": [
1738
+ 896,
1739
+ 896
1740
+ ],
1741
+ "dtype": "float16",
1742
+ "format": "f32-to-bf16",
1743
+ "nbytes": 1605632,
1744
+ "byteOffset": 28217344
1745
+ },
1746
+ {
1747
+ "name": "model.layers.7.input_layernorm.weight",
1748
+ "shape": [
1749
+ 896
1750
+ ],
1751
+ "dtype": "float16",
1752
+ "format": "f32-to-bf16",
1753
+ "nbytes": 1792,
1754
+ "byteOffset": 29822976
1755
+ }
1756
+ ],
1757
+ "md5sum": "ce22bf370a3ac8ba1094ae6182ccbf70"
1758
+ },
1759
+ {
1760
+ "dataPath": "params_shard_22.bin",
1761
+ "format": "raw-shard",
1762
+ "nbytes": 29824768,
1763
+ "records": [
1764
+ {
1765
+ "name": "model.layers.7.mlp.down_proj.weight",
1766
+ "shape": [
1767
+ 896,
1768
+ 4864
1769
+ ],
1770
+ "dtype": "float16",
1771
+ "format": "f32-to-bf16",
1772
+ "nbytes": 8716288,
1773
+ "byteOffset": 0
1774
+ },
1775
+ {
1776
+ "name": "model.layers.7.mlp.gate_up_proj.weight",
1777
+ "shape": [
1778
+ 9728,
1779
+ 896
1780
+ ],
1781
+ "dtype": "float16",
1782
+ "format": "f32-to-bf16",
1783
+ "nbytes": 17432576,
1784
+ "byteOffset": 8716288
1785
+ },
1786
+ {
1787
+ "name": "model.layers.7.post_attention_layernorm.weight",
1788
+ "shape": [
1789
+ 896
1790
+ ],
1791
+ "dtype": "float16",
1792
+ "format": "f32-to-bf16",
1793
+ "nbytes": 1792,
1794
+ "byteOffset": 26148864
1795
+ },
1796
+ {
1797
+ "name": "model.layers.7.self_attn.c_attn.bias",
1798
+ "shape": [
1799
+ 1152
1800
+ ],
1801
+ "dtype": "float16",
1802
+ "format": "f32-to-bf16",
1803
+ "nbytes": 2304,
1804
+ "byteOffset": 26150656
1805
+ },
1806
+ {
1807
+ "name": "model.layers.7.self_attn.c_attn.weight",
1808
+ "shape": [
1809
+ 1152,
1810
+ 896
1811
+ ],
1812
+ "dtype": "float16",
1813
+ "format": "f32-to-bf16",
1814
+ "nbytes": 2064384,
1815
+ "byteOffset": 26152960
1816
+ },
1817
+ {
1818
+ "name": "model.layers.7.self_attn.o_proj.weight",
1819
+ "shape": [
1820
+ 896,
1821
+ 896
1822
+ ],
1823
+ "dtype": "float16",
1824
+ "format": "f32-to-bf16",
1825
+ "nbytes": 1605632,
1826
+ "byteOffset": 28217344
1827
+ },
1828
+ {
1829
+ "name": "model.layers.8.input_layernorm.weight",
1830
+ "shape": [
1831
+ 896
1832
+ ],
1833
+ "dtype": "float16",
1834
+ "format": "f32-to-bf16",
1835
+ "nbytes": 1792,
1836
+ "byteOffset": 29822976
1837
+ }
1838
+ ],
1839
+ "md5sum": "0bcd63a0a9528474d6a658ea2ca51791"
1840
+ },
1841
+ {
1842
+ "dataPath": "params_shard_23.bin",
1843
+ "format": "raw-shard",
1844
+ "nbytes": 29824768,
1845
+ "records": [
1846
+ {
1847
+ "name": "model.layers.8.mlp.down_proj.weight",
1848
+ "shape": [
1849
+ 896,
1850
+ 4864
1851
+ ],
1852
+ "dtype": "float16",
1853
+ "format": "f32-to-bf16",
1854
+ "nbytes": 8716288,
1855
+ "byteOffset": 0
1856
+ },
1857
+ {
1858
+ "name": "model.layers.8.mlp.gate_up_proj.weight",
1859
+ "shape": [
1860
+ 9728,
1861
+ 896
1862
+ ],
1863
+ "dtype": "float16",
1864
+ "format": "f32-to-bf16",
1865
+ "nbytes": 17432576,
1866
+ "byteOffset": 8716288
1867
+ },
1868
+ {
1869
+ "name": "model.layers.8.post_attention_layernorm.weight",
1870
+ "shape": [
1871
+ 896
1872
+ ],
1873
+ "dtype": "float16",
1874
+ "format": "f32-to-bf16",
1875
+ "nbytes": 1792,
1876
+ "byteOffset": 26148864
1877
+ },
1878
+ {
1879
+ "name": "model.layers.8.self_attn.c_attn.bias",
1880
+ "shape": [
1881
+ 1152
1882
+ ],
1883
+ "dtype": "float16",
1884
+ "format": "f32-to-bf16",
1885
+ "nbytes": 2304,
1886
+ "byteOffset": 26150656
1887
+ },
1888
+ {
1889
+ "name": "model.layers.8.self_attn.c_attn.weight",
1890
+ "shape": [
1891
+ 1152,
1892
+ 896
1893
+ ],
1894
+ "dtype": "float16",
1895
+ "format": "f32-to-bf16",
1896
+ "nbytes": 2064384,
1897
+ "byteOffset": 26152960
1898
+ },
1899
+ {
1900
+ "name": "model.layers.8.self_attn.o_proj.weight",
1901
+ "shape": [
1902
+ 896,
1903
+ 896
1904
+ ],
1905
+ "dtype": "float16",
1906
+ "format": "f32-to-bf16",
1907
+ "nbytes": 1605632,
1908
+ "byteOffset": 28217344
1909
+ },
1910
+ {
1911
+ "name": "model.layers.9.input_layernorm.weight",
1912
+ "shape": [
1913
+ 896
1914
+ ],
1915
+ "dtype": "float16",
1916
+ "format": "f32-to-bf16",
1917
+ "nbytes": 1792,
1918
+ "byteOffset": 29822976
1919
+ }
1920
+ ],
1921
+ "md5sum": "942964c7522bbfe279b32d0a32715ab2"
1922
+ },
1923
+ {
1924
+ "dataPath": "params_shard_24.bin",
1925
+ "format": "raw-shard",
1926
+ "nbytes": 29824768,
1927
+ "records": [
1928
+ {
1929
+ "name": "model.layers.9.mlp.down_proj.weight",
1930
+ "shape": [
1931
+ 896,
1932
+ 4864
1933
+ ],
1934
+ "dtype": "float16",
1935
+ "format": "f32-to-bf16",
1936
+ "nbytes": 8716288,
1937
+ "byteOffset": 0
1938
+ },
1939
+ {
1940
+ "name": "model.layers.9.mlp.gate_up_proj.weight",
1941
+ "shape": [
1942
+ 9728,
1943
+ 896
1944
+ ],
1945
+ "dtype": "float16",
1946
+ "format": "f32-to-bf16",
1947
+ "nbytes": 17432576,
1948
+ "byteOffset": 8716288
1949
+ },
1950
+ {
1951
+ "name": "model.layers.9.post_attention_layernorm.weight",
1952
+ "shape": [
1953
+ 896
1954
+ ],
1955
+ "dtype": "float16",
1956
+ "format": "f32-to-bf16",
1957
+ "nbytes": 1792,
1958
+ "byteOffset": 26148864
1959
+ },
1960
+ {
1961
+ "name": "model.layers.9.self_attn.c_attn.bias",
1962
+ "shape": [
1963
+ 1152
1964
+ ],
1965
+ "dtype": "float16",
1966
+ "format": "f32-to-bf16",
1967
+ "nbytes": 2304,
1968
+ "byteOffset": 26150656
1969
+ },
1970
+ {
1971
+ "name": "model.layers.9.self_attn.c_attn.weight",
1972
+ "shape": [
1973
+ 1152,
1974
+ 896
1975
+ ],
1976
+ "dtype": "float16",
1977
+ "format": "f32-to-bf16",
1978
+ "nbytes": 2064384,
1979
+ "byteOffset": 26152960
1980
+ },
1981
+ {
1982
+ "name": "model.layers.9.self_attn.o_proj.weight",
1983
+ "shape": [
1984
+ 896,
1985
+ 896
1986
+ ],
1987
+ "dtype": "float16",
1988
+ "format": "f32-to-bf16",
1989
+ "nbytes": 1605632,
1990
+ "byteOffset": 28217344
1991
+ },
1992
+ {
1993
+ "name": "model.norm.weight",
1994
+ "shape": [
1995
+ 896
1996
+ ],
1997
+ "dtype": "float16",
1998
+ "format": "f32-to-bf16",
1999
+ "nbytes": 1792,
2000
+ "byteOffset": 29822976
2001
+ }
2002
+ ],
2003
+ "md5sum": "106f860dac3f9d6186f6cfcc61be8722"
2004
+ }
2005
+ ]
2006
+ }
params_shard_0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22883b3c9ca0903d43b43afb61fa11160a59188a850ad35c3ba176aa434a2b10
3
+ size 272269312
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa682f4ae05b527d16c9fe9358e69ba4b75696ed82d64694549ede70eb1d9ce9
3
+ size 29826560
params_shard_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd681244b976777fce4af4164cc63a23a47710ba70f82e2b045d1f486addb4f2
3
+ size 29824768
params_shard_11.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2cf0d8d3dd54eb84b691eeb650712ab557b0ce20943004d6cd3cabb7d8b53ed
3
+ size 29824768
params_shard_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5b639868df90bebedae6e1a79f9f28e4e6691b6c9b067d7e88b99258fc9a547
3
+ size 29824768
params_shard_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06c2effdcdd2f963f5287e1578f56f29a640c39ae260f76b4130c3ad517a6205
3
+ size 29824768
params_shard_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37906eb2fb3440eabd8a072a604dd5d1074e82d49991460b52b9086f399c2440
3
+ size 29824768
params_shard_15.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fd2938816ba1978e569f8f213d756403a77dba5034a6fed870e9399e1632294
3
+ size 29824768
params_shard_16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d8fe50ded250f30d44fb8f995776c85ef55f5bcc45202a4eedbe6affda3d463
3
+ size 29824768
params_shard_17.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5282ece5730941fe0209921830b0b5d885c91684a717b96f6e6ed07f9f277806
3
+ size 29824768
params_shard_18.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16e6d2eae350b00cdf198caf6dd077485682e59d2c8bc2b96a6050bf9d157ded
3
+ size 29824768
params_shard_19.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cfe877cc73cf0d22f5ebf04a6430d0471e5f79c159c467874182510a13d24ac
3
+ size 29824768
params_shard_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc8d7a596eeee4f7c873d14bfd633c8049cfb118a6e37a779eb9ec3e1ff43e9d
3
+ size 29824768
params_shard_20.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93d33f22ca671c591c2eecfb1ab389c0490e32d93ec945d12ffa4fe729c87181
3
+ size 29824768
params_shard_21.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:611abe05e92a8109810a8b9c21baf8d4a2064adc17168f763a41d73825e3e840
3
+ size 29824768
params_shard_22.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca33d153488d794364333a1a9a24863a86597f47b5d60a30ab3c4e1f1bb71f61
3
+ size 29824768
params_shard_23.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6baaa4e6c3626bf24026a5443844f81b0eaf483dd5e5541b2c3a426ecefa472c
3
+ size 29824768
params_shard_24.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4140d470f0659dc589fc33945199d3fe104275ad326827539d1b4ec9e7e88d79
3
+ size 29824768
params_shard_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea2ac5c71d2a9c37a3aa46f536b5f7b313b70c9e69f4eaf03b9758089cad77e9
3
+ size 29824768
params_shard_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d059428a5bacaf51ef3132521a9c52efa58ea9f5f9c77be293ac25b0be5cfe38
3
+ size 29824768
params_shard_5.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d0b59e8d5ef552ec04739e8cb04de909209445ba9757b202a2121183b01535d
3
+ size 29824768
params_shard_6.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bbaea512edd30f71bacfe07315f603419151eff39c6d9c0b77978131474dc9b
3
+ size 29824768
params_shard_7.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:674af4218b7a5263f5e61f9b628e25307c889ef3abed4eb63e894a05592fb130
3
+ size 29824768
params_shard_8.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57bf519e5d4bda3fe12630a035bf9d9f3eefcee67a63e22e07ebbe45733021e7
3
+ size 29824768
params_shard_9.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:718bf9c6ea21740f7976551cc4883f513c0c8718346ac691873821d23500552e
3
+ size 29824768
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": ["<|im_start|>", "<|im_end|>"],
30
+ "bos_token": null,
31
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "<|im_end|>",
34
+ "errors": "replace",
35
+ "model_max_length": 32768,
36
+ "pad_token": "<|endoftext|>",
37
+ "split_special_tokens": false,
38
+ "tokenizer_class": "Qwen2Tokenizer",
39
+ "unk_token": null
40
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff