Hugging Face's logo

nota-ai
/
cpt-lora_st-vicuna-v1.3-2.7b-ppl-q0f16-MLC

Model card Files Community
illian01 commited on
Commit
3d8edfe
•
1 Parent(s): ee20adb

Add weights and config

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. mlc-chat-config.json +77 -0
  2. ndarray-cache.json +1217 -0
  3. params_shard_0.bin +3 -0
  4. params_shard_1.bin +3 -0
  5. params_shard_10.bin +3 -0
  6. params_shard_11.bin +3 -0
  7. params_shard_12.bin +3 -0
  8. params_shard_13.bin +3 -0
  9. params_shard_14.bin +3 -0
  10. params_shard_15.bin +3 -0
  11. params_shard_16.bin +3 -0
  12. params_shard_17.bin +3 -0
  13. params_shard_18.bin +3 -0
  14. params_shard_19.bin +3 -0
  15. params_shard_2.bin +3 -0
  16. params_shard_20.bin +3 -0
  17. params_shard_21.bin +3 -0
  18. params_shard_22.bin +3 -0
  19. params_shard_23.bin +3 -0
  20. params_shard_24.bin +3 -0
  21. params_shard_25.bin +3 -0
  22. params_shard_26.bin +3 -0
  23. params_shard_27.bin +3 -0
  24. params_shard_28.bin +3 -0
  25. params_shard_29.bin +3 -0
  26. params_shard_3.bin +3 -0
  27. params_shard_30.bin +3 -0
  28. params_shard_31.bin +3 -0
  29. params_shard_32.bin +3 -0
  30. params_shard_33.bin +3 -0
  31. params_shard_34.bin +3 -0
  32. params_shard_35.bin +3 -0
  33. params_shard_36.bin +3 -0
  34. params_shard_37.bin +3 -0
  35. params_shard_38.bin +3 -0
  36. params_shard_39.bin +3 -0
  37. params_shard_4.bin +3 -0
  38. params_shard_40.bin +3 -0
  39. params_shard_41.bin +3 -0
  40. params_shard_42.bin +3 -0
  41. params_shard_43.bin +3 -0
  42. params_shard_44.bin +3 -0
  43. params_shard_45.bin +3 -0
  44. params_shard_46.bin +3 -0
  45. params_shard_47.bin +3 -0
  46. params_shard_48.bin +3 -0
  47. params_shard_49.bin +3 -0
  48. params_shard_5.bin +3 -0
  49. params_shard_50.bin +3 -0
  50. params_shard_6.bin +3 -0
mlc-chat-config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.1.0",
3
+ "model_type": "llama",
4
+ "quantization": "q0f16",
5
+ "model_config": {
6
+ "hidden_size": 4096,
7
+ "intermediate_size": 11008,
8
+ "num_attention_heads": 32,
9
+ "num_hidden_layers": 12,
10
+ "rms_norm_eps": 1e-06,
11
+ "vocab_size": 32000,
12
+ "position_embedding_base": 10000,
13
+ "context_window_size": 2048,
14
+ "prefill_chunk_size": 2048,
15
+ "num_key_value_heads": 32,
16
+ "head_dim": 128,
17
+ "tensor_parallel_shards": 1,
18
+ "max_batch_size": 80
19
+ },
20
+ "vocab_size": 32000,
21
+ "context_window_size": 2048,
22
+ "sliding_window_size": -1,
23
+ "prefill_chunk_size": 2048,
24
+ "attention_sink_size": -1,
25
+ "tensor_parallel_shards": 1,
26
+ "mean_gen_len": 128,
27
+ "max_gen_len": 512,
28
+ "shift_fill_factor": 0.3,
29
+ "temperature": 0.6,
30
+ "presence_penalty": 0.0,
31
+ "frequency_penalty": 0.0,
32
+ "repetition_penalty": 1.0,
33
+ "top_p": 0.9,
34
+ "tokenizer_files": [
35
+ "tokenizer.model",
36
+ "tokenizer_config.json",
37
+ "tokenizer.json"
38
+ ],
39
+ "tokenizer_info": {
40
+ "token_postproc_method": "byte_fallback",
41
+ "prepend_space_in_encode": true,
42
+ "strip_space_in_decode": true
43
+ },
44
+ "conv_template": {
45
+ "name": "st-llm",
46
+ "system_template": "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Instruction:\n{MessagePlaceholders.SYSTEM.value}</s>",
47
+ "system_message": "You are a helpful, respectful and honest assistant.",
48
+ "system_prefix_token_ids": null,
49
+ "add_role_after_system_message": true,
50
+ "roles": {
51
+ "user": "### Input:",
52
+ "assistant": "### Response:"
53
+ },
54
+ "role_templates": {
55
+ "user": "{user_message}",
56
+ "assistant": "{assistant_message}",
57
+ "tool": "{tool_message}"
58
+ },
59
+ "messages": [],
60
+ "seps": [
61
+ "</s>"
62
+ ],
63
+ "role_content_sep": "\n",
64
+ "role_empty_sep": "\n",
65
+ "stop_str": [
66
+ "</s>"
67
+ ],
68
+ "stop_token_ids": [
69
+ 2
70
+ ],
71
+ "function_string": "",
72
+ "use_function_calling": false
73
+ },
74
+ "pad_token_id": 0,
75
+ "bos_token_id": 1,
76
+ "eos_token_id": 2
77
+ }
ndarray-cache.json ADDED
@@ -0,0 +1,1217 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "ParamSize": 75,
4
+ "ParamBytes": 5381496832.0,
5
+ "BitsPerParam": 16.0
6
+ },
7
+ "records": [
8
+ {
9
+ "dataPath": "params_shard_0.bin",
10
+ "format": "raw-shard",
11
+ "nbytes": 262144000,
12
+ "records": [
13
+ {
14
+ "name": "model.embed_tokens.weight",
15
+ "shape": [
16
+ 32000,
17
+ 4096
18
+ ],
19
+ "dtype": "float16",
20
+ "format": "f32-to-bf16",
21
+ "nbytes": 262144000,
22
+ "byteOffset": 0
23
+ }
24
+ ],
25
+ "md5sum": "086fa5d85dd04f05e2a3a1fdf82b21ef"
26
+ },
27
+ {
28
+ "dataPath": "params_shard_1.bin",
29
+ "format": "raw-shard",
30
+ "nbytes": 100663296,
31
+ "records": [
32
+ {
33
+ "name": "model.layers.0.self_attn.qkv_proj.weight",
34
+ "shape": [
35
+ 12288,
36
+ 4096
37
+ ],
38
+ "dtype": "float16",
39
+ "format": "f32-to-bf16",
40
+ "nbytes": 100663296,
41
+ "byteOffset": 0
42
+ }
43
+ ],
44
+ "md5sum": "1fb8f6712b9e3c5b1aac6f4197633a91"
45
+ },
46
+ {
47
+ "dataPath": "params_shard_2.bin",
48
+ "format": "raw-shard",
49
+ "nbytes": 33554432,
50
+ "records": [
51
+ {
52
+ "name": "model.layers.0.self_attn.o_proj.weight",
53
+ "shape": [
54
+ 4096,
55
+ 4096
56
+ ],
57
+ "dtype": "float16",
58
+ "format": "f32-to-bf16",
59
+ "nbytes": 33554432,
60
+ "byteOffset": 0
61
+ }
62
+ ],
63
+ "md5sum": "5cc13d2d6a882827051d687930217539"
64
+ },
65
+ {
66
+ "dataPath": "params_shard_3.bin",
67
+ "format": "raw-shard",
68
+ "nbytes": 180355072,
69
+ "records": [
70
+ {
71
+ "name": "model.layers.0.mlp.gate_up_proj.weight",
72
+ "shape": [
73
+ 22016,
74
+ 4096
75
+ ],
76
+ "dtype": "float16",
77
+ "format": "f32-to-bf16",
78
+ "nbytes": 180355072,
79
+ "byteOffset": 0
80
+ }
81
+ ],
82
+ "md5sum": "65e4a62e1adf285476475f56bcb96548"
83
+ },
84
+ {
85
+ "dataPath": "params_shard_4.bin",
86
+ "format": "raw-shard",
87
+ "nbytes": 90177536,
88
+ "records": [
89
+ {
90
+ "name": "model.layers.0.mlp.down_proj.weight",
91
+ "shape": [
92
+ 4096,
93
+ 11008
94
+ ],
95
+ "dtype": "float16",
96
+ "format": "f32-to-bf16",
97
+ "nbytes": 90177536,
98
+ "byteOffset": 0
99
+ }
100
+ ],
101
+ "md5sum": "80c915c21aabb40eab4af32e71d27d6c"
102
+ },
103
+ {
104
+ "dataPath": "params_shard_5.bin",
105
+ "format": "raw-shard",
106
+ "nbytes": 100663296,
107
+ "records": [
108
+ {
109
+ "name": "model.layers.1.self_attn.qkv_proj.weight",
110
+ "shape": [
111
+ 12288,
112
+ 4096
113
+ ],
114
+ "dtype": "float16",
115
+ "format": "f32-to-bf16",
116
+ "nbytes": 100663296,
117
+ "byteOffset": 0
118
+ }
119
+ ],
120
+ "md5sum": "5196379bc71ec987f1c1e73907b95fe9"
121
+ },
122
+ {
123
+ "dataPath": "params_shard_6.bin",
124
+ "format": "raw-shard",
125
+ "nbytes": 33554432,
126
+ "records": [
127
+ {
128
+ "name": "model.layers.1.self_attn.o_proj.weight",
129
+ "shape": [
130
+ 4096,
131
+ 4096
132
+ ],
133
+ "dtype": "float16",
134
+ "format": "f32-to-bf16",
135
+ "nbytes": 33554432,
136
+ "byteOffset": 0
137
+ }
138
+ ],
139
+ "md5sum": "38a3f547d09b0716f44af82d87ed8faa"
140
+ },
141
+ {
142
+ "dataPath": "params_shard_7.bin",
143
+ "format": "raw-shard",
144
+ "nbytes": 180355072,
145
+ "records": [
146
+ {
147
+ "name": "model.layers.1.mlp.gate_up_proj.weight",
148
+ "shape": [
149
+ 22016,
150
+ 4096
151
+ ],
152
+ "dtype": "float16",
153
+ "format": "f32-to-bf16",
154
+ "nbytes": 180355072,
155
+ "byteOffset": 0
156
+ }
157
+ ],
158
+ "md5sum": "6adb5d274bd5b147e5541b4c5239250f"
159
+ },
160
+ {
161
+ "dataPath": "params_shard_8.bin",
162
+ "format": "raw-shard",
163
+ "nbytes": 90177536,
164
+ "records": [
165
+ {
166
+ "name": "model.layers.1.mlp.down_proj.weight",
167
+ "shape": [
168
+ 4096,
169
+ 11008
170
+ ],
171
+ "dtype": "float16",
172
+ "format": "f32-to-bf16",
173
+ "nbytes": 90177536,
174
+ "byteOffset": 0
175
+ }
176
+ ],
177
+ "md5sum": "266739798197328e16c5cc0844be7628"
178
+ },
179
+ {
180
+ "dataPath": "params_shard_9.bin",
181
+ "format": "raw-shard",
182
+ "nbytes": 100663296,
183
+ "records": [
184
+ {
185
+ "name": "model.layers.2.self_attn.qkv_proj.weight",
186
+ "shape": [
187
+ 12288,
188
+ 4096
189
+ ],
190
+ "dtype": "float16",
191
+ "format": "f32-to-bf16",
192
+ "nbytes": 100663296,
193
+ "byteOffset": 0
194
+ }
195
+ ],
196
+ "md5sum": "b302cb752360877786c085edefdbf8c0"
197
+ },
198
+ {
199
+ "dataPath": "params_shard_10.bin",
200
+ "format": "raw-shard",
201
+ "nbytes": 33554432,
202
+ "records": [
203
+ {
204
+ "name": "model.layers.2.self_attn.o_proj.weight",
205
+ "shape": [
206
+ 4096,
207
+ 4096
208
+ ],
209
+ "dtype": "float16",
210
+ "format": "f32-to-bf16",
211
+ "nbytes": 33554432,
212
+ "byteOffset": 0
213
+ }
214
+ ],
215
+ "md5sum": "6948d3c0609142725614d3934ffa9447"
216
+ },
217
+ {
218
+ "dataPath": "params_shard_11.bin",
219
+ "format": "raw-shard",
220
+ "nbytes": 180355072,
221
+ "records": [
222
+ {
223
+ "name": "model.layers.2.mlp.gate_up_proj.weight",
224
+ "shape": [
225
+ 22016,
226
+ 4096
227
+ ],
228
+ "dtype": "float16",
229
+ "format": "f32-to-bf16",
230
+ "nbytes": 180355072,
231
+ "byteOffset": 0
232
+ }
233
+ ],
234
+ "md5sum": "65b29fc7b558e0e1edfc7dec335349e3"
235
+ },
236
+ {
237
+ "dataPath": "params_shard_12.bin",
238
+ "format": "raw-shard",
239
+ "nbytes": 90177536,
240
+ "records": [
241
+ {
242
+ "name": "model.layers.2.mlp.down_proj.weight",
243
+ "shape": [
244
+ 4096,
245
+ 11008
246
+ ],
247
+ "dtype": "float16",
248
+ "format": "f32-to-bf16",
249
+ "nbytes": 90177536,
250
+ "byteOffset": 0
251
+ }
252
+ ],
253
+ "md5sum": "9f0b5472decd8005f13d62aa18f6a3f3"
254
+ },
255
+ {
256
+ "dataPath": "params_shard_13.bin",
257
+ "format": "raw-shard",
258
+ "nbytes": 100663296,
259
+ "records": [
260
+ {
261
+ "name": "model.layers.3.self_attn.qkv_proj.weight",
262
+ "shape": [
263
+ 12288,
264
+ 4096
265
+ ],
266
+ "dtype": "float16",
267
+ "format": "f32-to-bf16",
268
+ "nbytes": 100663296,
269
+ "byteOffset": 0
270
+ }
271
+ ],
272
+ "md5sum": "557a66fcb9e9fe375a44a21bcad56a7f"
273
+ },
274
+ {
275
+ "dataPath": "params_shard_14.bin",
276
+ "format": "raw-shard",
277
+ "nbytes": 33554432,
278
+ "records": [
279
+ {
280
+ "name": "model.layers.3.self_attn.o_proj.weight",
281
+ "shape": [
282
+ 4096,
283
+ 4096
284
+ ],
285
+ "dtype": "float16",
286
+ "format": "f32-to-bf16",
287
+ "nbytes": 33554432,
288
+ "byteOffset": 0
289
+ }
290
+ ],
291
+ "md5sum": "89b95d1896cd4cbb05636c3f830a05c9"
292
+ },
293
+ {
294
+ "dataPath": "params_shard_15.bin",
295
+ "format": "raw-shard",
296
+ "nbytes": 180355072,
297
+ "records": [
298
+ {
299
+ "name": "model.layers.3.mlp.gate_up_proj.weight",
300
+ "shape": [
301
+ 22016,
302
+ 4096
303
+ ],
304
+ "dtype": "float16",
305
+ "format": "f32-to-bf16",
306
+ "nbytes": 180355072,
307
+ "byteOffset": 0
308
+ }
309
+ ],
310
+ "md5sum": "a49a98e21c05ac823be7bce4f0969894"
311
+ },
312
+ {
313
+ "dataPath": "params_shard_16.bin",
314
+ "format": "raw-shard",
315
+ "nbytes": 90177536,
316
+ "records": [
317
+ {
318
+ "name": "model.layers.3.mlp.down_proj.weight",
319
+ "shape": [
320
+ 4096,
321
+ 11008
322
+ ],
323
+ "dtype": "float16",
324
+ "format": "f32-to-bf16",
325
+ "nbytes": 90177536,
326
+ "byteOffset": 0
327
+ }
328
+ ],
329
+ "md5sum": "bfcebf50a21e96325053fb48f89970dc"
330
+ },
331
+ {
332
+ "dataPath": "params_shard_17.bin",
333
+ "format": "raw-shard",
334
+ "nbytes": 100663296,
335
+ "records": [
336
+ {
337
+ "name": "model.layers.4.self_attn.qkv_proj.weight",
338
+ "shape": [
339
+ 12288,
340
+ 4096
341
+ ],
342
+ "dtype": "float16",
343
+ "format": "f32-to-bf16",
344
+ "nbytes": 100663296,
345
+ "byteOffset": 0
346
+ }
347
+ ],
348
+ "md5sum": "e51ff8b8536ed897255433fd277fce65"
349
+ },
350
+ {
351
+ "dataPath": "params_shard_18.bin",
352
+ "format": "raw-shard",
353
+ "nbytes": 33554432,
354
+ "records": [
355
+ {
356
+ "name": "model.layers.4.self_attn.o_proj.weight",
357
+ "shape": [
358
+ 4096,
359
+ 4096
360
+ ],
361
+ "dtype": "float16",
362
+ "format": "f32-to-bf16",
363
+ "nbytes": 33554432,
364
+ "byteOffset": 0
365
+ }
366
+ ],
367
+ "md5sum": "7d9e4d2ec260092e5e764949aaa1ada7"
368
+ },
369
+ {
370
+ "dataPath": "params_shard_19.bin",
371
+ "format": "raw-shard",
372
+ "nbytes": 180355072,
373
+ "records": [
374
+ {
375
+ "name": "model.layers.4.mlp.gate_up_proj.weight",
376
+ "shape": [
377
+ 22016,
378
+ 4096
379
+ ],
380
+ "dtype": "float16",
381
+ "format": "f32-to-bf16",
382
+ "nbytes": 180355072,
383
+ "byteOffset": 0
384
+ }
385
+ ],
386
+ "md5sum": "fda793d517d205bad7d554c3b5973ea6"
387
+ },
388
+ {
389
+ "dataPath": "params_shard_20.bin",
390
+ "format": "raw-shard",
391
+ "nbytes": 90177536,
392
+ "records": [
393
+ {
394
+ "name": "model.layers.4.mlp.down_proj.weight",
395
+ "shape": [
396
+ 4096,
397
+ 11008
398
+ ],
399
+ "dtype": "float16",
400
+ "format": "f32-to-bf16",
401
+ "nbytes": 90177536,
402
+ "byteOffset": 0
403
+ }
404
+ ],
405
+ "md5sum": "5b5c3d5453b0dd1c0060681880085b69"
406
+ },
407
+ {
408
+ "dataPath": "params_shard_21.bin",
409
+ "format": "raw-shard",
410
+ "nbytes": 100663296,
411
+ "records": [
412
+ {
413
+ "name": "model.layers.5.self_attn.qkv_proj.weight",
414
+ "shape": [
415
+ 12288,
416
+ 4096
417
+ ],
418
+ "dtype": "float16",
419
+ "format": "f32-to-bf16",
420
+ "nbytes": 100663296,
421
+ "byteOffset": 0
422
+ }
423
+ ],
424
+ "md5sum": "9e7028cdcf3f8547097a349b6e0c51a4"
425
+ },
426
+ {
427
+ "dataPath": "params_shard_22.bin",
428
+ "format": "raw-shard",
429
+ "nbytes": 33554432,
430
+ "records": [
431
+ {
432
+ "name": "model.layers.5.self_attn.o_proj.weight",
433
+ "shape": [
434
+ 4096,
435
+ 4096
436
+ ],
437
+ "dtype": "float16",
438
+ "format": "f32-to-bf16",
439
+ "nbytes": 33554432,
440
+ "byteOffset": 0
441
+ }
442
+ ],
443
+ "md5sum": "5a8bb702543682e94db86cf538d930ae"
444
+ },
445
+ {
446
+ "dataPath": "params_shard_23.bin",
447
+ "format": "raw-shard",
448
+ "nbytes": 180355072,
449
+ "records": [
450
+ {
451
+ "name": "model.layers.5.mlp.gate_up_proj.weight",
452
+ "shape": [
453
+ 22016,
454
+ 4096
455
+ ],
456
+ "dtype": "float16",
457
+ "format": "f32-to-bf16",
458
+ "nbytes": 180355072,
459
+ "byteOffset": 0
460
+ }
461
+ ],
462
+ "md5sum": "30f79bf495fa30cd777c3e742604e596"
463
+ },
464
+ {
465
+ "dataPath": "params_shard_24.bin",
466
+ "format": "raw-shard",
467
+ "nbytes": 90177536,
468
+ "records": [
469
+ {
470
+ "name": "model.layers.5.mlp.down_proj.weight",
471
+ "shape": [
472
+ 4096,
473
+ 11008
474
+ ],
475
+ "dtype": "float16",
476
+ "format": "f32-to-bf16",
477
+ "nbytes": 90177536,
478
+ "byteOffset": 0
479
+ }
480
+ ],
481
+ "md5sum": "d21d42220557f8a0ad2a8cfa8812b4fa"
482
+ },
483
+ {
484
+ "dataPath": "params_shard_25.bin",
485
+ "format": "raw-shard",
486
+ "nbytes": 100663296,
487
+ "records": [
488
+ {
489
+ "name": "model.layers.6.self_attn.qkv_proj.weight",
490
+ "shape": [
491
+ 12288,
492
+ 4096
493
+ ],
494
+ "dtype": "float16",
495
+ "format": "f32-to-bf16",
496
+ "nbytes": 100663296,
497
+ "byteOffset": 0
498
+ }
499
+ ],
500
+ "md5sum": "c4610d5e1dda17930388d781883eeb0f"
501
+ },
502
+ {
503
+ "dataPath": "params_shard_26.bin",
504
+ "format": "raw-shard",
505
+ "nbytes": 33554432,
506
+ "records": [
507
+ {
508
+ "name": "model.layers.6.self_attn.o_proj.weight",
509
+ "shape": [
510
+ 4096,
511
+ 4096
512
+ ],
513
+ "dtype": "float16",
514
+ "format": "f32-to-bf16",
515
+ "nbytes": 33554432,
516
+ "byteOffset": 0
517
+ }
518
+ ],
519
+ "md5sum": "fd9a05c5be5ebeb72908834197971507"
520
+ },
521
+ {
522
+ "dataPath": "params_shard_27.bin",
523
+ "format": "raw-shard",
524
+ "nbytes": 180355072,
525
+ "records": [
526
+ {
527
+ "name": "model.layers.6.mlp.gate_up_proj.weight",
528
+ "shape": [
529
+ 22016,
530
+ 4096
531
+ ],
532
+ "dtype": "float16",
533
+ "format": "f32-to-bf16",
534
+ "nbytes": 180355072,
535
+ "byteOffset": 0
536
+ }
537
+ ],
538
+ "md5sum": "da52a84f42bc870cb2d61ba0f64199fe"
539
+ },
540
+ {
541
+ "dataPath": "params_shard_28.bin",
542
+ "format": "raw-shard",
543
+ "nbytes": 90177536,
544
+ "records": [
545
+ {
546
+ "name": "model.layers.6.mlp.down_proj.weight",
547
+ "shape": [
548
+ 4096,
549
+ 11008
550
+ ],
551
+ "dtype": "float16",
552
+ "format": "f32-to-bf16",
553
+ "nbytes": 90177536,
554
+ "byteOffset": 0
555
+ }
556
+ ],
557
+ "md5sum": "41ace8cfdb431b869c364b181669adb8"
558
+ },
559
+ {
560
+ "dataPath": "params_shard_29.bin",
561
+ "format": "raw-shard",
562
+ "nbytes": 100663296,
563
+ "records": [
564
+ {
565
+ "name": "model.layers.7.self_attn.qkv_proj.weight",
566
+ "shape": [
567
+ 12288,
568
+ 4096
569
+ ],
570
+ "dtype": "float16",
571
+ "format": "f32-to-bf16",
572
+ "nbytes": 100663296,
573
+ "byteOffset": 0
574
+ }
575
+ ],
576
+ "md5sum": "24efd39c1d43d8f1629efd9ffe94879a"
577
+ },
578
+ {
579
+ "dataPath": "params_shard_30.bin",
580
+ "format": "raw-shard",
581
+ "nbytes": 33554432,
582
+ "records": [
583
+ {
584
+ "name": "model.layers.7.self_attn.o_proj.weight",
585
+ "shape": [
586
+ 4096,
587
+ 4096
588
+ ],
589
+ "dtype": "float16",
590
+ "format": "f32-to-bf16",
591
+ "nbytes": 33554432,
592
+ "byteOffset": 0
593
+ }
594
+ ],
595
+ "md5sum": "5cc9d55e6e95aed53923e19204f298d8"
596
+ },
597
+ {
598
+ "dataPath": "params_shard_31.bin",
599
+ "format": "raw-shard",
600
+ "nbytes": 180355072,
601
+ "records": [
602
+ {
603
+ "name": "model.layers.7.mlp.gate_up_proj.weight",
604
+ "shape": [
605
+ 22016,
606
+ 4096
607
+ ],
608
+ "dtype": "float16",
609
+ "format": "f32-to-bf16",
610
+ "nbytes": 180355072,
611
+ "byteOffset": 0
612
+ }
613
+ ],
614
+ "md5sum": "a2cd26d3539402368b331f982f63a4e0"
615
+ },
616
+ {
617
+ "dataPath": "params_shard_32.bin",
618
+ "format": "raw-shard",
619
+ "nbytes": 90177536,
620
+ "records": [
621
+ {
622
+ "name": "model.layers.7.mlp.down_proj.weight",
623
+ "shape": [
624
+ 4096,
625
+ 11008
626
+ ],
627
+ "dtype": "float16",
628
+ "format": "f32-to-bf16",
629
+ "nbytes": 90177536,
630
+ "byteOffset": 0
631
+ }
632
+ ],
633
+ "md5sum": "409cccf8165554b0f38be84d133d24fe"
634
+ },
635
+ {
636
+ "dataPath": "params_shard_33.bin",
637
+ "format": "raw-shard",
638
+ "nbytes": 100663296,
639
+ "records": [
640
+ {
641
+ "name": "model.layers.8.self_attn.qkv_proj.weight",
642
+ "shape": [
643
+ 12288,
644
+ 4096
645
+ ],
646
+ "dtype": "float16",
647
+ "format": "f32-to-bf16",
648
+ "nbytes": 100663296,
649
+ "byteOffset": 0
650
+ }
651
+ ],
652
+ "md5sum": "8210986609e4c327c1871dbb1dda7ef8"
653
+ },
654
+ {
655
+ "dataPath": "params_shard_34.bin",
656
+ "format": "raw-shard",
657
+ "nbytes": 33554432,
658
+ "records": [
659
+ {
660
+ "name": "model.layers.8.self_attn.o_proj.weight",
661
+ "shape": [
662
+ 4096,
663
+ 4096
664
+ ],
665
+ "dtype": "float16",
666
+ "format": "f32-to-bf16",
667
+ "nbytes": 33554432,
668
+ "byteOffset": 0
669
+ }
670
+ ],
671
+ "md5sum": "2784c684870ebdd4e1c318c6a2415be8"
672
+ },
673
+ {
674
+ "dataPath": "params_shard_35.bin",
675
+ "format": "raw-shard",
676
+ "nbytes": 180355072,
677
+ "records": [
678
+ {
679
+ "name": "model.layers.8.mlp.gate_up_proj.weight",
680
+ "shape": [
681
+ 22016,
682
+ 4096
683
+ ],
684
+ "dtype": "float16",
685
+ "format": "f32-to-bf16",
686
+ "nbytes": 180355072,
687
+ "byteOffset": 0
688
+ }
689
+ ],
690
+ "md5sum": "45bbb2e8d8dc3431cfb6bf98be3faf09"
691
+ },
692
+ {
693
+ "dataPath": "params_shard_36.bin",
694
+ "format": "raw-shard",
695
+ "nbytes": 90177536,
696
+ "records": [
697
+ {
698
+ "name": "model.layers.8.mlp.down_proj.weight",
699
+ "shape": [
700
+ 4096,
701
+ 11008
702
+ ],
703
+ "dtype": "float16",
704
+ "format": "f32-to-bf16",
705
+ "nbytes": 90177536,
706
+ "byteOffset": 0
707
+ }
708
+ ],
709
+ "md5sum": "d848155e6d826ca74b4864984a18ba85"
710
+ },
711
+ {
712
+ "dataPath": "params_shard_37.bin",
713
+ "format": "raw-shard",
714
+ "nbytes": 100663296,
715
+ "records": [
716
+ {
717
+ "name": "model.layers.9.self_attn.qkv_proj.weight",
718
+ "shape": [
719
+ 12288,
720
+ 4096
721
+ ],
722
+ "dtype": "float16",
723
+ "format": "f32-to-bf16",
724
+ "nbytes": 100663296,
725
+ "byteOffset": 0
726
+ }
727
+ ],
728
+ "md5sum": "126d24134e500c39ce503b29719ec1fb"
729
+ },
730
+ {
731
+ "dataPath": "params_shard_38.bin",
732
+ "format": "raw-shard",
733
+ "nbytes": 33554432,
734
+ "records": [
735
+ {
736
+ "name": "model.layers.9.self_attn.o_proj.weight",
737
+ "shape": [
738
+ 4096,
739
+ 4096
740
+ ],
741
+ "dtype": "float16",
742
+ "format": "f32-to-bf16",
743
+ "nbytes": 33554432,
744
+ "byteOffset": 0
745
+ }
746
+ ],
747
+ "md5sum": "7df707dc20613f043ed2ee4a62e39497"
748
+ },
749
+ {
750
+ "dataPath": "params_shard_39.bin",
751
+ "format": "raw-shard",
752
+ "nbytes": 180355072,
753
+ "records": [
754
+ {
755
+ "name": "model.layers.9.mlp.gate_up_proj.weight",
756
+ "shape": [
757
+ 22016,
758
+ 4096
759
+ ],
760
+ "dtype": "float16",
761
+ "format": "f32-to-bf16",
762
+ "nbytes": 180355072,
763
+ "byteOffset": 0
764
+ }
765
+ ],
766
+ "md5sum": "5c3cd837b1f24c04205fa1ab324abe83"
767
+ },
768
+ {
769
+ "dataPath": "params_shard_40.bin",
770
+ "format": "raw-shard",
771
+ "nbytes": 90177536,
772
+ "records": [
773
+ {
774
+ "name": "model.layers.9.mlp.down_proj.weight",
775
+ "shape": [
776
+ 4096,
777
+ 11008
778
+ ],
779
+ "dtype": "float16",
780
+ "format": "f32-to-bf16",
781
+ "nbytes": 90177536,
782
+ "byteOffset": 0
783
+ }
784
+ ],
785
+ "md5sum": "e9467a549dd25774fa294e4366a13b18"
786
+ },
787
+ {
788
+ "dataPath": "params_shard_41.bin",
789
+ "format": "raw-shard",
790
+ "nbytes": 100663296,
791
+ "records": [
792
+ {
793
+ "name": "model.layers.10.self_attn.qkv_proj.weight",
794
+ "shape": [
795
+ 12288,
796
+ 4096
797
+ ],
798
+ "dtype": "float16",
799
+ "format": "f32-to-bf16",
800
+ "nbytes": 100663296,
801
+ "byteOffset": 0
802
+ }
803
+ ],
804
+ "md5sum": "94d9f19b1d011d30a15417b876b7b322"
805
+ },
806
+ {
807
+ "dataPath": "params_shard_42.bin",
808
+ "format": "raw-shard",
809
+ "nbytes": 33554432,
810
+ "records": [
811
+ {
812
+ "name": "model.layers.10.self_attn.o_proj.weight",
813
+ "shape": [
814
+ 4096,
815
+ 4096
816
+ ],
817
+ "dtype": "float16",
818
+ "format": "f32-to-bf16",
819
+ "nbytes": 33554432,
820
+ "byteOffset": 0
821
+ }
822
+ ],
823
+ "md5sum": "a986376cdc1c267d3a7e0fc6e0d7cb11"
824
+ },
825
+ {
826
+ "dataPath": "params_shard_43.bin",
827
+ "format": "raw-shard",
828
+ "nbytes": 180355072,
829
+ "records": [
830
+ {
831
+ "name": "model.layers.10.mlp.gate_up_proj.weight",
832
+ "shape": [
833
+ 22016,
834
+ 4096
835
+ ],
836
+ "dtype": "float16",
837
+ "format": "f32-to-bf16",
838
+ "nbytes": 180355072,
839
+ "byteOffset": 0
840
+ }
841
+ ],
842
+ "md5sum": "866f411eff8777b6778c4c13601ebf26"
843
+ },
844
+ {
845
+ "dataPath": "params_shard_44.bin",
846
+ "format": "raw-shard",
847
+ "nbytes": 90177536,
848
+ "records": [
849
+ {
850
+ "name": "model.layers.10.mlp.down_proj.weight",
851
+ "shape": [
852
+ 4096,
853
+ 11008
854
+ ],
855
+ "dtype": "float16",
856
+ "format": "f32-to-bf16",
857
+ "nbytes": 90177536,
858
+ "byteOffset": 0
859
+ }
860
+ ],
861
+ "md5sum": "137bd49a811d6e5b9960610dfe0302bd"
862
+ },
863
+ {
864
+ "dataPath": "params_shard_45.bin",
865
+ "format": "raw-shard",
866
+ "nbytes": 100663296,
867
+ "records": [
868
+ {
869
+ "name": "model.layers.11.self_attn.qkv_proj.weight",
870
+ "shape": [
871
+ 12288,
872
+ 4096
873
+ ],
874
+ "dtype": "float16",
875
+ "format": "f32-to-bf16",
876
+ "nbytes": 100663296,
877
+ "byteOffset": 0
878
+ }
879
+ ],
880
+ "md5sum": "7e4fc322a3eb63f0320f76904addf7c8"
881
+ },
882
+ {
883
+ "dataPath": "params_shard_46.bin",
884
+ "format": "raw-shard",
885
+ "nbytes": 33554432,
886
+ "records": [
887
+ {
888
+ "name": "model.layers.11.self_attn.o_proj.weight",
889
+ "shape": [
890
+ 4096,
891
+ 4096
892
+ ],
893
+ "dtype": "float16",
894
+ "format": "f32-to-bf16",
895
+ "nbytes": 33554432,
896
+ "byteOffset": 0
897
+ }
898
+ ],
899
+ "md5sum": "d37cc200922ed73aeeff3c089bf42920"
900
+ },
901
+ {
902
+ "dataPath": "params_shard_47.bin",
903
+ "format": "raw-shard",
904
+ "nbytes": 180355072,
905
+ "records": [
906
+ {
907
+ "name": "model.layers.11.mlp.gate_up_proj.weight",
908
+ "shape": [
909
+ 22016,
910
+ 4096
911
+ ],
912
+ "dtype": "float16",
913
+ "format": "f32-to-bf16",
914
+ "nbytes": 180355072,
915
+ "byteOffset": 0
916
+ }
917
+ ],
918
+ "md5sum": "42f241b74b0f766606e75671611c0850"
919
+ },
920
+ {
921
+ "dataPath": "params_shard_48.bin",
922
+ "format": "raw-shard",
923
+ "nbytes": 90177536,
924
+ "records": [
925
+ {
926
+ "name": "model.layers.11.mlp.down_proj.weight",
927
+ "shape": [
928
+ 4096,
929
+ 11008
930
+ ],
931
+ "dtype": "float16",
932
+ "format": "f32-to-bf16",
933
+ "nbytes": 90177536,
934
+ "byteOffset": 0
935
+ }
936
+ ],
937
+ "md5sum": "201da8c6f10c599bbb68f235ab4a0d3f"
938
+ },
939
+ {
940
+ "dataPath": "params_shard_49.bin",
941
+ "format": "raw-shard",
942
+ "nbytes": 262144000,
943
+ "records": [
944
+ {
945
+ "name": "lm_head.weight",
946
+ "shape": [
947
+ 32000,
948
+ 4096
949
+ ],
950
+ "dtype": "float16",
951
+ "format": "f32-to-bf16",
952
+ "nbytes": 262144000,
953
+ "byteOffset": 0
954
+ }
955
+ ],
956
+ "md5sum": "834a7e63f2db90051eb9bd4ba139125f"
957
+ },
958
+ {
959
+ "dataPath": "params_shard_50.bin",
960
+ "format": "raw-shard",
961
+ "nbytes": 204800,
962
+ "records": [
963
+ {
964
+ "name": "model.layers.0.input_layernorm.weight",
965
+ "shape": [
966
+ 4096
967
+ ],
968
+ "dtype": "float16",
969
+ "format": "f32-to-bf16",
970
+ "nbytes": 8192,
971
+ "byteOffset": 0
972
+ },
973
+ {
974
+ "name": "model.layers.0.post_attention_layernorm.weight",
975
+ "shape": [
976
+ 4096
977
+ ],
978
+ "dtype": "float16",
979
+ "format": "f32-to-bf16",
980
+ "nbytes": 8192,
981
+ "byteOffset": 8192
982
+ },
983
+ {
984
+ "name": "model.layers.1.input_layernorm.weight",
985
+ "shape": [
986
+ 4096
987
+ ],
988
+ "dtype": "float16",
989
+ "format": "f32-to-bf16",
990
+ "nbytes": 8192,
991
+ "byteOffset": 16384
992
+ },
993
+ {
994
+ "name": "model.layers.1.post_attention_layernorm.weight",
995
+ "shape": [
996
+ 4096
997
+ ],
998
+ "dtype": "float16",
999
+ "format": "f32-to-bf16",
1000
+ "nbytes": 8192,
1001
+ "byteOffset": 24576
1002
+ },
1003
+ {
1004
+ "name": "model.layers.2.input_layernorm.weight",
1005
+ "shape": [
1006
+ 4096
1007
+ ],
1008
+ "dtype": "float16",
1009
+ "format": "f32-to-bf16",
1010
+ "nbytes": 8192,
1011
+ "byteOffset": 32768
1012
+ },
1013
+ {
1014
+ "name": "model.layers.2.post_attention_layernorm.weight",
1015
+ "shape": [
1016
+ 4096
1017
+ ],
1018
+ "dtype": "float16",
1019
+ "format": "f32-to-bf16",
1020
+ "nbytes": 8192,
1021
+ "byteOffset": 40960
1022
+ },
1023
+ {
1024
+ "name": "model.layers.3.input_layernorm.weight",
1025
+ "shape": [
1026
+ 4096
1027
+ ],
1028
+ "dtype": "float16",
1029
+ "format": "f32-to-bf16",
1030
+ "nbytes": 8192,
1031
+ "byteOffset": 49152
1032
+ },
1033
+ {
1034
+ "name": "model.layers.3.post_attention_layernorm.weight",
1035
+ "shape": [
1036
+ 4096
1037
+ ],
1038
+ "dtype": "float16",
1039
+ "format": "f32-to-bf16",
1040
+ "nbytes": 8192,
1041
+ "byteOffset": 57344
1042
+ },
1043
+ {
1044
+ "name": "model.layers.4.input_layernorm.weight",
1045
+ "shape": [
1046
+ 4096
1047
+ ],
1048
+ "dtype": "float16",
1049
+ "format": "f32-to-bf16",
1050
+ "nbytes": 8192,
1051
+ "byteOffset": 65536
1052
+ },
1053
+ {
1054
+ "name": "model.layers.4.post_attention_layernorm.weight",
1055
+ "shape": [
1056
+ 4096
1057
+ ],
1058
+ "dtype": "float16",
1059
+ "format": "f32-to-bf16",
1060
+ "nbytes": 8192,
1061
+ "byteOffset": 73728
1062
+ },
1063
+ {
1064
+ "name": "model.layers.5.input_layernorm.weight",
1065
+ "shape": [
1066
+ 4096
1067
+ ],
1068
+ "dtype": "float16",
1069
+ "format": "f32-to-bf16",
1070
+ "nbytes": 8192,
1071
+ "byteOffset": 81920
1072
+ },
1073
+ {
1074
+ "name": "model.layers.5.post_attention_layernorm.weight",
1075
+ "shape": [
1076
+ 4096
1077
+ ],
1078
+ "dtype": "float16",
1079
+ "format": "f32-to-bf16",
1080
+ "nbytes": 8192,
1081
+ "byteOffset": 90112
1082
+ },
1083
+ {
1084
+ "name": "model.layers.6.input_layernorm.weight",
1085
+ "shape": [
1086
+ 4096
1087
+ ],
1088
+ "dtype": "float16",
1089
+ "format": "f32-to-bf16",
1090
+ "nbytes": 8192,
1091
+ "byteOffset": 98304
1092
+ },
1093
+ {
1094
+ "name": "model.layers.6.post_attention_layernorm.weight",
1095
+ "shape": [
1096
+ 4096
1097
+ ],
1098
+ "dtype": "float16",
1099
+ "format": "f32-to-bf16",
1100
+ "nbytes": 8192,
1101
+ "byteOffset": 106496
1102
+ },
1103
+ {
1104
+ "name": "model.layers.7.input_layernorm.weight",
1105
+ "shape": [
1106
+ 4096
1107
+ ],
1108
+ "dtype": "float16",
1109
+ "format": "f32-to-bf16",
1110
+ "nbytes": 8192,
1111
+ "byteOffset": 114688
1112
+ },
1113
+ {
1114
+ "name": "model.layers.7.post_attention_layernorm.weight",
1115
+ "shape": [
1116
+ 4096
1117
+ ],
1118
+ "dtype": "float16",
1119
+ "format": "f32-to-bf16",
1120
+ "nbytes": 8192,
1121
+ "byteOffset": 122880
1122
+ },
1123
+ {
1124
+ "name": "model.layers.8.input_layernorm.weight",
1125
+ "shape": [
1126
+ 4096
1127
+ ],
1128
+ "dtype": "float16",
1129
+ "format": "f32-to-bf16",
1130
+ "nbytes": 8192,
1131
+ "byteOffset": 131072
1132
+ },
1133
+ {
1134
+ "name": "model.layers.8.post_attention_layernorm.weight",
1135
+ "shape": [
1136
+ 4096
1137
+ ],
1138
+ "dtype": "float16",
1139
+ "format": "f32-to-bf16",
1140
+ "nbytes": 8192,
1141
+ "byteOffset": 139264
1142
+ },
1143
+ {
1144
+ "name": "model.layers.9.input_layernorm.weight",
1145
+ "shape": [
1146
+ 4096
1147
+ ],
1148
+ "dtype": "float16",
1149
+ "format": "f32-to-bf16",
1150
+ "nbytes": 8192,
1151
+ "byteOffset": 147456
1152
+ },
1153
+ {
1154
+ "name": "model.layers.9.post_attention_layernorm.weight",
1155
+ "shape": [
1156
+ 4096
1157
+ ],
1158
+ "dtype": "float16",
1159
+ "format": "f32-to-bf16",
1160
+ "nbytes": 8192,
1161
+ "byteOffset": 155648
1162
+ },
1163
+ {
1164
+ "name": "model.layers.10.input_layernorm.weight",
1165
+ "shape": [
1166
+ 4096
1167
+ ],
1168
+ "dtype": "float16",
1169
+ "format": "f32-to-bf16",
1170
+ "nbytes": 8192,
1171
+ "byteOffset": 163840
1172
+ },
1173
+ {
1174
+ "name": "model.layers.10.post_attention_layernorm.weight",
1175
+ "shape": [
1176
+ 4096
1177
+ ],
1178
+ "dtype": "float16",
1179
+ "format": "f32-to-bf16",
1180
+ "nbytes": 8192,
1181
+ "byteOffset": 172032
1182
+ },
1183
+ {
1184
+ "name": "model.layers.11.input_layernorm.weight",
1185
+ "shape": [
1186
+ 4096
1187
+ ],
1188
+ "dtype": "float16",
1189
+ "format": "f32-to-bf16",
1190
+ "nbytes": 8192,
1191
+ "byteOffset": 180224
1192
+ },
1193
+ {
1194
+ "name": "model.layers.11.post_attention_layernorm.weight",
1195
+ "shape": [
1196
+ 4096
1197
+ ],
1198
+ "dtype": "float16",
1199
+ "format": "f32-to-bf16",
1200
+ "nbytes": 8192,
1201
+ "byteOffset": 188416
1202
+ },
1203
+ {
1204
+ "name": "model.norm.weight",
1205
+ "shape": [
1206
+ 4096
1207
+ ],
1208
+ "dtype": "float16",
1209
+ "format": "f32-to-bf16",
1210
+ "nbytes": 8192,
1211
+ "byteOffset": 196608
1212
+ }
1213
+ ],
1214
+ "md5sum": "d8bee1a66409c293cf0b2fe932342db8"
1215
+ }
1216
+ ]
1217
+ }
params_shard_0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d6fd5f267ae629461d7cb08b725ba42829ecc534756b34c55da791bd54f6017
3
+ size 262144000
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:810bd1b71cc74af9922f171e0ae7cec0ed7678c79d882d65a9690fcb16970388
3
+ size 100663296
params_shard_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:996cc73d466d2b33db630f92e0bf6d4f4c6ac770e89f1f086751a48d5435b44b
3
+ size 33554432
params_shard_11.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9b12770849a84904b46fcaa79c9501cb92399e43d5ac75ec5502d1951860306
3
+ size 180355072
params_shard_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86a0fad849e47f4ec2d557c45267a0c31141d2b886a66999543c74a34cdb9573
3
+ size 90177536
params_shard_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b86bd0267850bb62bb1935ea1609141a9a508e507a446ae68e64fd172281549
3
+ size 100663296
params_shard_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b38353bba58aefabde52d3ed33822162cbfb371aed8a501a8a9f6c7d45a4b109
3
+ size 33554432
params_shard_15.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce8ba8d7a459ca3da42fa2c136fdf72a9b8a9af429ac12cbed79078413dde921
3
+ size 180355072
params_shard_16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdcee0073eff219abc55bf57510c1b52e7ac99c4b710a056eeed989e1bb4cf97
3
+ size 90177536
params_shard_17.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:528516091ab8a006455a833d253d2a5c6c83b7ac1ad404c06b0ac209f5073302
3
+ size 100663296
params_shard_18.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:422eb592444ac040543035051b55d59e9a5feea89b7377401865c31655fb3b17
3
+ size 33554432
params_shard_19.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e02881bc4ed9b81c1def9e4afbec9c9b129ea7b0a099d0bd2561b600b45f743
3
+ size 180355072
params_shard_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6b7fb21a08301d2e1aa00c1f888add5407fb609bfaf525c5a6053c17c642864
3
+ size 33554432
params_shard_20.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c48dbe688e3f2ca3f1b0acba267173464cd2dc9e339f68d6061f63ffa97a4732
3
+ size 90177536
params_shard_21.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50e094bad155bffde04f2fabd1cda9b557746f87413ba3f4c5c8895934673a42
3
+ size 100663296
params_shard_22.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d32bd7b3af144beab78f66ca813de3288c43ad527f183ade80429e321c02ed20
3
+ size 33554432
params_shard_23.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21808438be7de583c8bcdf737a98f22ef4224e4f37763306b4432ea0bc2e08bc
3
+ size 180355072
params_shard_24.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e8b0d116b758dbb0a2f0f71ca6e8f8a9d3a0e056c943af6d432ed204833192a
3
+ size 90177536
params_shard_25.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9f5294cba51f7f8f2a3a195da19f54bd8d30581117a5818ae0c4fb0a681e5c7
3
+ size 100663296
params_shard_26.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2189ced8655cae117528c0dafa49f2cdaa6f58169ddc7a699b08b6b73d77558d
3
+ size 33554432
params_shard_27.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96fa18d8a9e96c4d2808bfa86a845b86b2fc1017e929e35cba7b2b63cf546811
3
+ size 180355072
params_shard_28.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:531b8abc2436de9d27c4ad4d5e5ec97a856bf8ceee15df1e593614c036aaace3
3
+ size 90177536
params_shard_29.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:271aae515bf1f6a964e4385408118fa4639bd5c2db8fcf034034317eb6701f2d
3
+ size 100663296
params_shard_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c49adb25990862d93dae4f6eb88b27a00ed2695300dea0edee6590f07a88724
3
+ size 180355072
params_shard_30.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76a91125131f9434e6232118777659a5f2fee982ee35e14ca08e01e722107b11
3
+ size 33554432
params_shard_31.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62f24a43135046536e4b32fa1667fc889f044de0ebd832cc0554be8919ef353c
3
+ size 180355072
params_shard_32.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e93b23be9526bf385adfec4772e7bdbc026586fb3a2ca6cb6fcc79747b11716
3
+ size 90177536
params_shard_33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c41851eaa0c683f1dd98f72969fcc3e371f4fda3c5a1dcb1908e00296ecc65a2
3
+ size 100663296
params_shard_34.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:746b9e6c6bf89bcd98a3ed6f243c207e6b4823d8129da3d90077add11f332828
3
+ size 33554432
params_shard_35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33f730941c9cd50b590c88e30d0cde4b191982e7c9d45d08ac48a06cc7511b8d
3
+ size 180355072
params_shard_36.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0355e73270ea506230edb0797b3ab615e47debae12cfd5282f4b2d6a979448b1
3
+ size 90177536
params_shard_37.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caed3f940899824e5b02cd393b929dce8f7038cc2434cd32bd5fad32ecdeab5d
3
+ size 100663296
params_shard_38.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0473729421b1372a12b7eb3bc06885e1eecf8817f85ea65c50a281d396b810a5
3
+ size 33554432
params_shard_39.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faccd439ec5dfdbbf07787eab35e7fef8606f74a764c7a5ad0af8e3820db1c40
3
+ size 180355072
params_shard_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67d425dd401ff0557c8e4286f331375c1905044b6b83cd1beabdc00abf710c54
3
+ size 90177536
params_shard_40.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7112e833b036114346113d56da50c7079f1595f25ac632c7c7c95b5f4298dfed
3
+ size 90177536
params_shard_41.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c11a10d8990b3b434c6a505176f63dba5f2de54db9082c7f0a7783ea6a7fcc9f
3
+ size 100663296
params_shard_42.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6224d15e9bfe11dccc6d825b6c78a91bd26a01cf8406400875c283080556739
3
+ size 33554432
params_shard_43.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adc5abeb247bf79a8ada19f27d2dd9164794dcd53e2a2dbf55830f3cbc32f707
3
+ size 180355072
params_shard_44.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18a5f15243c1ab00dfa433f6b2b6f32800e73bce21a3e229b48e9e5066371fce
3
+ size 90177536
params_shard_45.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77edfc8ea6523a160a9c70e7270b4166c934706b89edf7525f66530b74b75790
3
+ size 100663296
params_shard_46.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c284666849e8a11d25903d4acaace90b752d2c4ae0877e9ca7813e835f0ef1a5
3
+ size 33554432
params_shard_47.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8702121d91aa1076da683811094e83f47c68114de79f67cadbc13c70104c3506
3
+ size 180355072
params_shard_48.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25d89abe2a7e6361dc79cd2588abd8dbae133a6c2b8fdc546fa857b616f393f1
3
+ size 90177536
params_shard_49.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01dd2e6c2f1ab555fbdac546d4b8ad8ea34ef3c255344b0f80ad7383a6dea243
3
+ size 262144000
params_shard_5.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60456e4da2fa02c78947a403c931981372202db1b77333ea8e120846dac9cf09
3
+ size 100663296
params_shard_50.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26eed189298a94424ee4cbcad3a1d7f8846c88cea7b0564288e7a84272ae5d30
3
+ size 204800
params_shard_6.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e75160246cd91607a913bba75d904d13456dff326c86eb45aab78cac0229d4
3
+ size 33554432