Hugging Face's logo

nota-ai
/
cpt-lora_st-vicuna-v1.3-3.7b-ppl-q0f16-MLC

Model card Files Community
illian01 commited on
Commit
537f54e
•
1 Parent(s): c0de649

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 +1697 -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_51.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": 17,
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 +1,1697 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "ParamSize": 105,
4
+ "ParamBytes": 7405330432.0,
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": "cd25a0e6b4bc8161826fc5056e6cff2f"
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": "4cd4f63250b348906985186e5d19be22"
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": "318388d943058ca57632f381c2bbd592"
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": "a7070a67b57f475eeface96d35ad4e3b"
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": "5e2c18827553eb1655236ebb1d51b510"
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": "3c646522247ddd81debd288247a2820d"
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": "885a1d2ab386ec87801d642babd86c07"
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": "fd537fbddf068dee6c153e3c6ec3cbf2"
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": "95a9d95f44e81bac0ea7b7c6116f5dd5"
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": "53684986c85dd93648b9ec08b14c2871"
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": "5df83f4f22ffb36896a9e7b50446c193"
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": "95ce9e6a676a66f27b6a71908f1f4694"
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": "a3398381a5c22f6fb7808dd243e8e145"
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": "d70ec0e94f9dcb485f22e3fe983c7354"
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": "b24aadfe362b9d3a4042d7a7b4342e2a"
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": "12668a6f09d295d0a91b0e0e48a39ac7"
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": "e966aa20b847fb9aa4f2c0481846648f"
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": "424aee9252a40b7b497cf0344ecc6a90"
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": "18fb823cac1011607404fad78a050e46"
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": "0a721fe93e970c8f6f84797035764ec9"
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": "cbf0a0817e02f8af89103aac4adab678"
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": "8ae44a030d303f649bdfc7d9219b8aa9"
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": "93e7e277431f7c6793d9d8a207c22a14"
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": "c4a327895700afc715899fa627b8e26f"
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": "3a37b974d511de656f2382ba62133f86"
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": "41a73472bd0adf44146f00e1e910116b"
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": "566ce9aff08c9f355b70221f29d39c62"
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": "e1ef3ef8e7d98aebbc66c4d174670505"
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": "679a13b88ee766d85d7bc95b3890073c"
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": "14aea661a9eaeb4b5e1672bf9e206304"
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": "31a5604a557bcbb9853758dca780b626"
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": "5339293fe19e18daad8d479ffcb1a724"
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": "4031ad352eec0120a63b31e0354e2da7"
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": "a1236d981350f8db06e743c074b98502"
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": "6ac471aea5dd9fa92ce5f121f0f58617"
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": "66729107c7d75122ca1f6fdf82e7cee4"
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": "05983e5e58c5e0d32ce86cc7e3f49ba1"
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": "147b5e8ad4fd080abf76fc9cdd9bd758"
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": "d52eb5ce1f04a8ebd49912d11a3507f4"
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": "fbd33ccc1834c93d9c5c3f32f2c4ce7c"
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": "4882a5ed28597fc11ce1593c52a53ad6"
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": "8f7a23394846c884152e60f47d10f170"
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": "3b334be246094198941316e21ad437a1"
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": "43958cb1181eb394053172ac1eafe139"
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": "9f6e1185ec0a3d4a0db0ad110fb55372"
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": "fd27954abcaa68b4b6607d87a820c4d0"
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": "892df7b48193aeb6f51f0553a94884c9"
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": "ca178abda39ca9c02fb16ec492541c4f"
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": "ad74166a2eaa93ff6395a5e8a6354c8f"
938
+ },
939
+ {
940
+ "dataPath": "params_shard_49.bin",
941
+ "format": "raw-shard",
942
+ "nbytes": 100663296,
943
+ "records": [
944
+ {
945
+ "name": "model.layers.12.self_attn.qkv_proj.weight",
946
+ "shape": [
947
+ 12288,
948
+ 4096
949
+ ],
950
+ "dtype": "float16",
951
+ "format": "f32-to-bf16",
952
+ "nbytes": 100663296,
953
+ "byteOffset": 0
954
+ }
955
+ ],
956
+ "md5sum": "b7397a0857e8de6657a855119a20d71d"
957
+ },
958
+ {
959
+ "dataPath": "params_shard_50.bin",
960
+ "format": "raw-shard",
961
+ "nbytes": 33554432,
962
+ "records": [
963
+ {
964
+ "name": "model.layers.12.self_attn.o_proj.weight",
965
+ "shape": [
966
+ 4096,
967
+ 4096
968
+ ],
969
+ "dtype": "float16",
970
+ "format": "f32-to-bf16",
971
+ "nbytes": 33554432,
972
+ "byteOffset": 0
973
+ }
974
+ ],
975
+ "md5sum": "71f419719ae8c138464ca91907c9d97b"
976
+ },
977
+ {
978
+ "dataPath": "params_shard_51.bin",
979
+ "format": "raw-shard",
980
+ "nbytes": 180355072,
981
+ "records": [
982
+ {
983
+ "name": "model.layers.12.mlp.gate_up_proj.weight",
984
+ "shape": [
985
+ 22016,
986
+ 4096
987
+ ],
988
+ "dtype": "float16",
989
+ "format": "f32-to-bf16",
990
+ "nbytes": 180355072,
991
+ "byteOffset": 0
992
+ }
993
+ ],
994
+ "md5sum": "ceb903e130b1008ff393efcb2f146128"
995
+ },
996
+ {
997
+ "dataPath": "params_shard_52.bin",
998
+ "format": "raw-shard",
999
+ "nbytes": 90177536,
1000
+ "records": [
1001
+ {
1002
+ "name": "model.layers.12.mlp.down_proj.weight",
1003
+ "shape": [
1004
+ 4096,
1005
+ 11008
1006
+ ],
1007
+ "dtype": "float16",
1008
+ "format": "f32-to-bf16",
1009
+ "nbytes": 90177536,
1010
+ "byteOffset": 0
1011
+ }
1012
+ ],
1013
+ "md5sum": "993fc79b4fdb810ec65ddf09d45e2716"
1014
+ },
1015
+ {
1016
+ "dataPath": "params_shard_53.bin",
1017
+ "format": "raw-shard",
1018
+ "nbytes": 100663296,
1019
+ "records": [
1020
+ {
1021
+ "name": "model.layers.13.self_attn.qkv_proj.weight",
1022
+ "shape": [
1023
+ 12288,
1024
+ 4096
1025
+ ],
1026
+ "dtype": "float16",
1027
+ "format": "f32-to-bf16",
1028
+ "nbytes": 100663296,
1029
+ "byteOffset": 0
1030
+ }
1031
+ ],
1032
+ "md5sum": "39253307df27775f7bcf926bada7497d"
1033
+ },
1034
+ {
1035
+ "dataPath": "params_shard_54.bin",
1036
+ "format": "raw-shard",
1037
+ "nbytes": 33554432,
1038
+ "records": [
1039
+ {
1040
+ "name": "model.layers.13.self_attn.o_proj.weight",
1041
+ "shape": [
1042
+ 4096,
1043
+ 4096
1044
+ ],
1045
+ "dtype": "float16",
1046
+ "format": "f32-to-bf16",
1047
+ "nbytes": 33554432,
1048
+ "byteOffset": 0
1049
+ }
1050
+ ],
1051
+ "md5sum": "ba542d70e312517be53f8183fe4dae81"
1052
+ },
1053
+ {
1054
+ "dataPath": "params_shard_55.bin",
1055
+ "format": "raw-shard",
1056
+ "nbytes": 180355072,
1057
+ "records": [
1058
+ {
1059
+ "name": "model.layers.13.mlp.gate_up_proj.weight",
1060
+ "shape": [
1061
+ 22016,
1062
+ 4096
1063
+ ],
1064
+ "dtype": "float16",
1065
+ "format": "f32-to-bf16",
1066
+ "nbytes": 180355072,
1067
+ "byteOffset": 0
1068
+ }
1069
+ ],
1070
+ "md5sum": "4cefbdbcd104420f62edcceb1b96057c"
1071
+ },
1072
+ {
1073
+ "dataPath": "params_shard_56.bin",
1074
+ "format": "raw-shard",
1075
+ "nbytes": 90177536,
1076
+ "records": [
1077
+ {
1078
+ "name": "model.layers.13.mlp.down_proj.weight",
1079
+ "shape": [
1080
+ 4096,
1081
+ 11008
1082
+ ],
1083
+ "dtype": "float16",
1084
+ "format": "f32-to-bf16",
1085
+ "nbytes": 90177536,
1086
+ "byteOffset": 0
1087
+ }
1088
+ ],
1089
+ "md5sum": "6e932be356dd90bf22e2693aee7ac2d2"
1090
+ },
1091
+ {
1092
+ "dataPath": "params_shard_57.bin",
1093
+ "format": "raw-shard",
1094
+ "nbytes": 100663296,
1095
+ "records": [
1096
+ {
1097
+ "name": "model.layers.14.self_attn.qkv_proj.weight",
1098
+ "shape": [
1099
+ 12288,
1100
+ 4096
1101
+ ],
1102
+ "dtype": "float16",
1103
+ "format": "f32-to-bf16",
1104
+ "nbytes": 100663296,
1105
+ "byteOffset": 0
1106
+ }
1107
+ ],
1108
+ "md5sum": "1e0e808d0064d94b1c5da59860e8db24"
1109
+ },
1110
+ {
1111
+ "dataPath": "params_shard_58.bin",
1112
+ "format": "raw-shard",
1113
+ "nbytes": 33554432,
1114
+ "records": [
1115
+ {
1116
+ "name": "model.layers.14.self_attn.o_proj.weight",
1117
+ "shape": [
1118
+ 4096,
1119
+ 4096
1120
+ ],
1121
+ "dtype": "float16",
1122
+ "format": "f32-to-bf16",
1123
+ "nbytes": 33554432,
1124
+ "byteOffset": 0
1125
+ }
1126
+ ],
1127
+ "md5sum": "466759ff2429658c910c37f5bc9d20f1"
1128
+ },
1129
+ {
1130
+ "dataPath": "params_shard_59.bin",
1131
+ "format": "raw-shard",
1132
+ "nbytes": 180355072,
1133
+ "records": [
1134
+ {
1135
+ "name": "model.layers.14.mlp.gate_up_proj.weight",
1136
+ "shape": [
1137
+ 22016,
1138
+ 4096
1139
+ ],
1140
+ "dtype": "float16",
1141
+ "format": "f32-to-bf16",
1142
+ "nbytes": 180355072,
1143
+ "byteOffset": 0
1144
+ }
1145
+ ],
1146
+ "md5sum": "88e97b46efae2a3da238d65fde1adb61"
1147
+ },
1148
+ {
1149
+ "dataPath": "params_shard_60.bin",
1150
+ "format": "raw-shard",
1151
+ "nbytes": 90177536,
1152
+ "records": [
1153
+ {
1154
+ "name": "model.layers.14.mlp.down_proj.weight",
1155
+ "shape": [
1156
+ 4096,
1157
+ 11008
1158
+ ],
1159
+ "dtype": "float16",
1160
+ "format": "f32-to-bf16",
1161
+ "nbytes": 90177536,
1162
+ "byteOffset": 0
1163
+ }
1164
+ ],
1165
+ "md5sum": "cca00bc36ca644e07adcc2a8f6a24114"
1166
+ },
1167
+ {
1168
+ "dataPath": "params_shard_61.bin",
1169
+ "format": "raw-shard",
1170
+ "nbytes": 100663296,
1171
+ "records": [
1172
+ {
1173
+ "name": "model.layers.15.self_attn.qkv_proj.weight",
1174
+ "shape": [
1175
+ 12288,
1176
+ 4096
1177
+ ],
1178
+ "dtype": "float16",
1179
+ "format": "f32-to-bf16",
1180
+ "nbytes": 100663296,
1181
+ "byteOffset": 0
1182
+ }
1183
+ ],
1184
+ "md5sum": "c9e3ded76bc30ad58eaeaa925d41aee9"
1185
+ },
1186
+ {
1187
+ "dataPath": "params_shard_62.bin",
1188
+ "format": "raw-shard",
1189
+ "nbytes": 33554432,
1190
+ "records": [
1191
+ {
1192
+ "name": "model.layers.15.self_attn.o_proj.weight",
1193
+ "shape": [
1194
+ 4096,
1195
+ 4096
1196
+ ],
1197
+ "dtype": "float16",
1198
+ "format": "f32-to-bf16",
1199
+ "nbytes": 33554432,
1200
+ "byteOffset": 0
1201
+ }
1202
+ ],
1203
+ "md5sum": "d49c550cd19e9f47e245fabe0f590ae7"
1204
+ },
1205
+ {
1206
+ "dataPath": "params_shard_63.bin",
1207
+ "format": "raw-shard",
1208
+ "nbytes": 180355072,
1209
+ "records": [
1210
+ {
1211
+ "name": "model.layers.15.mlp.gate_up_proj.weight",
1212
+ "shape": [
1213
+ 22016,
1214
+ 4096
1215
+ ],
1216
+ "dtype": "float16",
1217
+ "format": "f32-to-bf16",
1218
+ "nbytes": 180355072,
1219
+ "byteOffset": 0
1220
+ }
1221
+ ],
1222
+ "md5sum": "fc552dee542f6ebb7ed590a74cb18681"
1223
+ },
1224
+ {
1225
+ "dataPath": "params_shard_64.bin",
1226
+ "format": "raw-shard",
1227
+ "nbytes": 90177536,
1228
+ "records": [
1229
+ {
1230
+ "name": "model.layers.15.mlp.down_proj.weight",
1231
+ "shape": [
1232
+ 4096,
1233
+ 11008
1234
+ ],
1235
+ "dtype": "float16",
1236
+ "format": "f32-to-bf16",
1237
+ "nbytes": 90177536,
1238
+ "byteOffset": 0
1239
+ }
1240
+ ],
1241
+ "md5sum": "bb873eb18ba5651993626f73d913e5e1"
1242
+ },
1243
+ {
1244
+ "dataPath": "params_shard_65.bin",
1245
+ "format": "raw-shard",
1246
+ "nbytes": 100663296,
1247
+ "records": [
1248
+ {
1249
+ "name": "model.layers.16.self_attn.qkv_proj.weight",
1250
+ "shape": [
1251
+ 12288,
1252
+ 4096
1253
+ ],
1254
+ "dtype": "float16",
1255
+ "format": "f32-to-bf16",
1256
+ "nbytes": 100663296,
1257
+ "byteOffset": 0
1258
+ }
1259
+ ],
1260
+ "md5sum": "67f33745c9844f82f59d64f60e9a78aa"
1261
+ },
1262
+ {
1263
+ "dataPath": "params_shard_66.bin",
1264
+ "format": "raw-shard",
1265
+ "nbytes": 33554432,
1266
+ "records": [
1267
+ {
1268
+ "name": "model.layers.16.self_attn.o_proj.weight",
1269
+ "shape": [
1270
+ 4096,
1271
+ 4096
1272
+ ],
1273
+ "dtype": "float16",
1274
+ "format": "f32-to-bf16",
1275
+ "nbytes": 33554432,
1276
+ "byteOffset": 0
1277
+ }
1278
+ ],
1279
+ "md5sum": "e16bf94b5970adde5a727c8e3c9d60de"
1280
+ },
1281
+ {
1282
+ "dataPath": "params_shard_67.bin",
1283
+ "format": "raw-shard",
1284
+ "nbytes": 180355072,
1285
+ "records": [
1286
+ {
1287
+ "name": "model.layers.16.mlp.gate_up_proj.weight",
1288
+ "shape": [
1289
+ 22016,
1290
+ 4096
1291
+ ],
1292
+ "dtype": "float16",
1293
+ "format": "f32-to-bf16",
1294
+ "nbytes": 180355072,
1295
+ "byteOffset": 0
1296
+ }
1297
+ ],
1298
+ "md5sum": "c1ffa40ea7bdf607bcb9322924cd7637"
1299
+ },
1300
+ {
1301
+ "dataPath": "params_shard_68.bin",
1302
+ "format": "raw-shard",
1303
+ "nbytes": 90177536,
1304
+ "records": [
1305
+ {
1306
+ "name": "model.layers.16.mlp.down_proj.weight",
1307
+ "shape": [
1308
+ 4096,
1309
+ 11008
1310
+ ],
1311
+ "dtype": "float16",
1312
+ "format": "f32-to-bf16",
1313
+ "nbytes": 90177536,
1314
+ "byteOffset": 0
1315
+ }
1316
+ ],
1317
+ "md5sum": "350720761de687e2e5b266c15be1be12"
1318
+ },
1319
+ {
1320
+ "dataPath": "params_shard_69.bin",
1321
+ "format": "raw-shard",
1322
+ "nbytes": 262144000,
1323
+ "records": [
1324
+ {
1325
+ "name": "lm_head.weight",
1326
+ "shape": [
1327
+ 32000,
1328
+ 4096
1329
+ ],
1330
+ "dtype": "float16",
1331
+ "format": "f32-to-bf16",
1332
+ "nbytes": 262144000,
1333
+ "byteOffset": 0
1334
+ }
1335
+ ],
1336
+ "md5sum": "c4453fd8afd0e9397475a1626c5b5940"
1337
+ },
1338
+ {
1339
+ "dataPath": "params_shard_70.bin",
1340
+ "format": "raw-shard",
1341
+ "nbytes": 286720,
1342
+ "records": [
1343
+ {
1344
+ "name": "model.layers.0.input_layernorm.weight",
1345
+ "shape": [
1346
+ 4096
1347
+ ],
1348
+ "dtype": "float16",
1349
+ "format": "f32-to-bf16",
1350
+ "nbytes": 8192,
1351
+ "byteOffset": 0
1352
+ },
1353
+ {
1354
+ "name": "model.layers.0.post_attention_layernorm.weight",
1355
+ "shape": [
1356
+ 4096
1357
+ ],
1358
+ "dtype": "float16",
1359
+ "format": "f32-to-bf16",
1360
+ "nbytes": 8192,
1361
+ "byteOffset": 8192
1362
+ },
1363
+ {
1364
+ "name": "model.layers.1.input_layernorm.weight",
1365
+ "shape": [
1366
+ 4096
1367
+ ],
1368
+ "dtype": "float16",
1369
+ "format": "f32-to-bf16",
1370
+ "nbytes": 8192,
1371
+ "byteOffset": 16384
1372
+ },
1373
+ {
1374
+ "name": "model.layers.1.post_attention_layernorm.weight",
1375
+ "shape": [
1376
+ 4096
1377
+ ],
1378
+ "dtype": "float16",
1379
+ "format": "f32-to-bf16",
1380
+ "nbytes": 8192,
1381
+ "byteOffset": 24576
1382
+ },
1383
+ {
1384
+ "name": "model.layers.2.input_layernorm.weight",
1385
+ "shape": [
1386
+ 4096
1387
+ ],
1388
+ "dtype": "float16",
1389
+ "format": "f32-to-bf16",
1390
+ "nbytes": 8192,
1391
+ "byteOffset": 32768
1392
+ },
1393
+ {
1394
+ "name": "model.layers.2.post_attention_layernorm.weight",
1395
+ "shape": [
1396
+ 4096
1397
+ ],
1398
+ "dtype": "float16",
1399
+ "format": "f32-to-bf16",
1400
+ "nbytes": 8192,
1401
+ "byteOffset": 40960
1402
+ },
1403
+ {
1404
+ "name": "model.layers.3.input_layernorm.weight",
1405
+ "shape": [
1406
+ 4096
1407
+ ],
1408
+ "dtype": "float16",
1409
+ "format": "f32-to-bf16",
1410
+ "nbytes": 8192,
1411
+ "byteOffset": 49152
1412
+ },
1413
+ {
1414
+ "name": "model.layers.3.post_attention_layernorm.weight",
1415
+ "shape": [
1416
+ 4096
1417
+ ],
1418
+ "dtype": "float16",
1419
+ "format": "f32-to-bf16",
1420
+ "nbytes": 8192,
1421
+ "byteOffset": 57344
1422
+ },
1423
+ {
1424
+ "name": "model.layers.4.input_layernorm.weight",
1425
+ "shape": [
1426
+ 4096
1427
+ ],
1428
+ "dtype": "float16",
1429
+ "format": "f32-to-bf16",
1430
+ "nbytes": 8192,
1431
+ "byteOffset": 65536
1432
+ },
1433
+ {
1434
+ "name": "model.layers.4.post_attention_layernorm.weight",
1435
+ "shape": [
1436
+ 4096
1437
+ ],
1438
+ "dtype": "float16",
1439
+ "format": "f32-to-bf16",
1440
+ "nbytes": 8192,
1441
+ "byteOffset": 73728
1442
+ },
1443
+ {
1444
+ "name": "model.layers.5.input_layernorm.weight",
1445
+ "shape": [
1446
+ 4096
1447
+ ],
1448
+ "dtype": "float16",
1449
+ "format": "f32-to-bf16",
1450
+ "nbytes": 8192,
1451
+ "byteOffset": 81920
1452
+ },
1453
+ {
1454
+ "name": "model.layers.5.post_attention_layernorm.weight",
1455
+ "shape": [
1456
+ 4096
1457
+ ],
1458
+ "dtype": "float16",
1459
+ "format": "f32-to-bf16",
1460
+ "nbytes": 8192,
1461
+ "byteOffset": 90112
1462
+ },
1463
+ {
1464
+ "name": "model.layers.6.input_layernorm.weight",
1465
+ "shape": [
1466
+ 4096
1467
+ ],
1468
+ "dtype": "float16",
1469
+ "format": "f32-to-bf16",
1470
+ "nbytes": 8192,
1471
+ "byteOffset": 98304
1472
+ },
1473
+ {
1474
+ "name": "model.layers.6.post_attention_layernorm.weight",
1475
+ "shape": [
1476
+ 4096
1477
+ ],
1478
+ "dtype": "float16",
1479
+ "format": "f32-to-bf16",
1480
+ "nbytes": 8192,
1481
+ "byteOffset": 106496
1482
+ },
1483
+ {
1484
+ "name": "model.layers.7.input_layernorm.weight",
1485
+ "shape": [
1486
+ 4096
1487
+ ],
1488
+ "dtype": "float16",
1489
+ "format": "f32-to-bf16",
1490
+ "nbytes": 8192,
1491
+ "byteOffset": 114688
1492
+ },
1493
+ {
1494
+ "name": "model.layers.7.post_attention_layernorm.weight",
1495
+ "shape": [
1496
+ 4096
1497
+ ],
1498
+ "dtype": "float16",
1499
+ "format": "f32-to-bf16",
1500
+ "nbytes": 8192,
1501
+ "byteOffset": 122880
1502
+ },
1503
+ {
1504
+ "name": "model.layers.8.input_layernorm.weight",
1505
+ "shape": [
1506
+ 4096
1507
+ ],
1508
+ "dtype": "float16",
1509
+ "format": "f32-to-bf16",
1510
+ "nbytes": 8192,
1511
+ "byteOffset": 131072
1512
+ },
1513
+ {
1514
+ "name": "model.layers.8.post_attention_layernorm.weight",
1515
+ "shape": [
1516
+ 4096
1517
+ ],
1518
+ "dtype": "float16",
1519
+ "format": "f32-to-bf16",
1520
+ "nbytes": 8192,
1521
+ "byteOffset": 139264
1522
+ },
1523
+ {
1524
+ "name": "model.layers.9.input_layernorm.weight",
1525
+ "shape": [
1526
+ 4096
1527
+ ],
1528
+ "dtype": "float16",
1529
+ "format": "f32-to-bf16",
1530
+ "nbytes": 8192,
1531
+ "byteOffset": 147456
1532
+ },
1533
+ {
1534
+ "name": "model.layers.9.post_attention_layernorm.weight",
1535
+ "shape": [
1536
+ 4096
1537
+ ],
1538
+ "dtype": "float16",
1539
+ "format": "f32-to-bf16",
1540
+ "nbytes": 8192,
1541
+ "byteOffset": 155648
1542
+ },
1543
+ {
1544
+ "name": "model.layers.10.input_layernorm.weight",
1545
+ "shape": [
1546
+ 4096
1547
+ ],
1548
+ "dtype": "float16",
1549
+ "format": "f32-to-bf16",
1550
+ "nbytes": 8192,
1551
+ "byteOffset": 163840
1552
+ },
1553
+ {
1554
+ "name": "model.layers.10.post_attention_layernorm.weight",
1555
+ "shape": [
1556
+ 4096
1557
+ ],
1558
+ "dtype": "float16",
1559
+ "format": "f32-to-bf16",
1560
+ "nbytes": 8192,
1561
+ "byteOffset": 172032
1562
+ },
1563
+ {
1564
+ "name": "model.layers.11.input_layernorm.weight",
1565
+ "shape": [
1566
+ 4096
1567
+ ],
1568
+ "dtype": "float16",
1569
+ "format": "f32-to-bf16",
1570
+ "nbytes": 8192,
1571
+ "byteOffset": 180224
1572
+ },
1573
+ {
1574
+ "name": "model.layers.11.post_attention_layernorm.weight",
1575
+ "shape": [
1576
+ 4096
1577
+ ],
1578
+ "dtype": "float16",
1579
+ "format": "f32-to-bf16",
1580
+ "nbytes": 8192,
1581
+ "byteOffset": 188416
1582
+ },
1583
+ {
1584
+ "name": "model.layers.12.input_layernorm.weight",
1585
+ "shape": [
1586
+ 4096
1587
+ ],
1588
+ "dtype": "float16",
1589
+ "format": "f32-to-bf16",
1590
+ "nbytes": 8192,
1591
+ "byteOffset": 196608
1592
+ },
1593
+ {
1594
+ "name": "model.layers.12.post_attention_layernorm.weight",
1595
+ "shape": [
1596
+ 4096
1597
+ ],
1598
+ "dtype": "float16",
1599
+ "format": "f32-to-bf16",
1600
+ "nbytes": 8192,
1601
+ "byteOffset": 204800
1602
+ },
1603
+ {
1604
+ "name": "model.layers.13.input_layernorm.weight",
1605
+ "shape": [
1606
+ 4096
1607
+ ],
1608
+ "dtype": "float16",
1609
+ "format": "f32-to-bf16",
1610
+ "nbytes": 8192,
1611
+ "byteOffset": 212992
1612
+ },
1613
+ {
1614
+ "name": "model.layers.13.post_attention_layernorm.weight",
1615
+ "shape": [
1616
+ 4096
1617
+ ],
1618
+ "dtype": "float16",
1619
+ "format": "f32-to-bf16",
1620
+ "nbytes": 8192,
1621
+ "byteOffset": 221184
1622
+ },
1623
+ {
1624
+ "name": "model.layers.14.input_layernorm.weight",
1625
+ "shape": [
1626
+ 4096
1627
+ ],
1628
+ "dtype": "float16",
1629
+ "format": "f32-to-bf16",
1630
+ "nbytes": 8192,
1631
+ "byteOffset": 229376
1632
+ },
1633
+ {
1634
+ "name": "model.layers.14.post_attention_layernorm.weight",
1635
+ "shape": [
1636
+ 4096
1637
+ ],
1638
+ "dtype": "float16",
1639
+ "format": "f32-to-bf16",
1640
+ "nbytes": 8192,
1641
+ "byteOffset": 237568
1642
+ },
1643
+ {
1644
+ "name": "model.layers.15.input_layernorm.weight",
1645
+ "shape": [
1646
+ 4096
1647
+ ],
1648
+ "dtype": "float16",
1649
+ "format": "f32-to-bf16",
1650
+ "nbytes": 8192,
1651
+ "byteOffset": 245760
1652
+ },
1653
+ {
1654
+ "name": "model.layers.15.post_attention_layernorm.weight",
1655
+ "shape": [
1656
+ 4096
1657
+ ],
1658
+ "dtype": "float16",
1659
+ "format": "f32-to-bf16",
1660
+ "nbytes": 8192,
1661
+ "byteOffset": 253952
1662
+ },
1663
+ {
1664
+ "name": "model.layers.16.input_layernorm.weight",
1665
+ "shape": [
1666
+ 4096
1667
+ ],
1668
+ "dtype": "float16",
1669
+ "format": "f32-to-bf16",
1670
+ "nbytes": 8192,
1671
+ "byteOffset": 262144
1672
+ },
1673
+ {
1674
+ "name": "model.layers.16.post_attention_layernorm.weight",
1675
+ "shape": [
1676
+ 4096
1677
+ ],
1678
+ "dtype": "float16",
1679
+ "format": "f32-to-bf16",
1680
+ "nbytes": 8192,
1681
+ "byteOffset": 270336
1682
+ },
1683
+ {
1684
+ "name": "model.norm.weight",
1685
+ "shape": [
1686
+ 4096
1687
+ ],
1688
+ "dtype": "float16",
1689
+ "format": "f32-to-bf16",
1690
+ "nbytes": 8192,
1691
+ "byteOffset": 278528
1692
+ }
1693
+ ],
1694
+ "md5sum": "e774a2d70024de12f2a25b167b4e89b7"
1695
+ }
1696
+ ]
1697
+ }
params_shard_0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b43ba363dfd85f10fc6cbf21b3d370159bc48e3255d0f170f0c11c5e0782d5e
3
+ size 262144000
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffbfc282ffde9948ceec3dfa2be776494fd2f71e4799430b2e2708457f13898c
3
+ size 100663296
params_shard_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e58892a41ec6bdcac98a311da84a10a025f788526d72da9b43a58725b6520d41
3
+ size 33554432
params_shard_11.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20644a96eaa4443fa70136fcbad155f8d7e73ff8c8c6966069e0bc9ab6c4af31
3
+ size 180355072
params_shard_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dcea8d76f205ef1eb13bf2ac95b12e16f0cdb5a5ffaa6957f237b796ba270c8
3
+ size 90177536
params_shard_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae627e76a29acd9a04c27aef268911e63b74ca917ca59c4155de0ed1555a44ca
3
+ size 100663296
params_shard_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f79e8b1796f3b40cf75edc98f416c2b2c31e46afd68fdadb2623da9aee1ddcf
3
+ size 33554432
params_shard_15.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2b1635d38017e614a52528e042c5dcdbcbf0b53c8ebb49c6aafa0f85776b84a
3
+ size 180355072
params_shard_16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b6f1e650f6f2475848b4754bc9a85d3319111bc512e271862a5ab5e3406957d
3
+ size 90177536
params_shard_17.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26d932f22ccfd0718c90263bf58ed97cd267401615c147e60ffe13a2d1098b9c
3
+ size 100663296
params_shard_18.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89c4fc8592d8014efd8f017aaf28bae95e23c200d37dac1883531adf8794d366
3
+ size 33554432
params_shard_19.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1802740f9c3250156eabe749d0e4d610d41b603a56e3c396fa7e653facff0db9
3
+ size 180355072
params_shard_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e270b90d1886976382af40fd436cf0c293500c1f4cfcca715eacd76f040aad6
3
+ size 33554432
params_shard_20.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5e4242b1464c6efabb3415d8790efd7c40a0bdcb10733052b819706b43e211f
3
+ size 90177536
params_shard_21.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8ab181ba257e24902bf7ca1d4ea463f5596fdc34d8836274170c240af055040
3
+ size 100663296
params_shard_22.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc948d8373605acd49ee059b0b4912eede71a10ab47ada47976c373c188cd7a6
3
+ size 33554432
params_shard_23.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d159f1368073292e70b1bd62692d3e25833a809e21e461ba9031ced0b1ab4852
3
+ size 180355072
params_shard_24.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2ad7cd212721d9f5b1519596502617e24328078076db5de342bd93b6fa0c187
3
+ size 90177536
params_shard_25.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f988fd431a846c5ef8a5d0ce43c3e220ef5cf00abbe4e599227fc940c037e7ff
3
+ size 100663296
params_shard_26.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da8c07bf89ceb8dd276d297125b2044b4b504972217df65b85d22a246e790ff8
3
+ size 33554432
params_shard_27.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bd5f489825591a07eb2a791d3c10b3a30caea7b1d5f39c7437ba6c745712ec3
3
+ size 180355072
params_shard_28.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55669c5ae6187b0597e260d2e1677291efd39f7a93b379ed22d8da674e54a4db
3
+ size 90177536
params_shard_29.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06f76144618b6477b2720478cdec07367d76cb15e2e5e56801378f9cab66b958
3
+ size 100663296
params_shard_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2837b0f5a42e38d80ad1ac1d993c09733ba525cf02951d424c30e7916aa76fbb
3
+ size 180355072
params_shard_30.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81fcae903ee2543d9524cd1400fa87bef194757a0f51b1f9367c2cb0381d5df8
3
+ size 33554432
params_shard_31.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ea372beae8d1946dcf95dcb85bb256db7c51eee1674b645408935dd0eec22d3
3
+ size 180355072
params_shard_32.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00091e291b7f6d92dce8179ebc84f0e740b0686179ae109e529ed913df035b13
3
+ size 90177536
params_shard_33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4f78a286d1fa9a8a1982987943b7ad36e35f69d82457e4f1f6906bb1f96e242
3
+ size 100663296
params_shard_34.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cff2d61cabd439dd6b58bdba8d2409a3c5550e303a67e6c0ceaf041e045c5b2
3
+ size 33554432
params_shard_35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d794396f8dafdad4b94b19bf08656675476acac390e755b555de99705497bb0
3
+ size 180355072
params_shard_36.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85a88ded2efa3a702a6d91ad32aaf658a70ba30aef6b91648db3e05c6efa7c72
3
+ size 90177536
params_shard_37.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:266ffc97b0fcef1768a12698370eb5d73f94f15b7dc66a30e75a464e121d90d7
3
+ size 100663296
params_shard_38.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b6cce2a2b006152e8c332ecddad8d403db2029e5e9a9008255670a9c2091751
3
+ size 33554432
params_shard_39.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb34f8a7e8a1127d9afe9862605f3040bfeec3e4e2bf6aab129a0e7da846c4a5
3
+ size 180355072
params_shard_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7b297371731c8272dfc009cf8f0737661494081e1a85bbd0934fcabdf7502d3
3
+ size 90177536
params_shard_40.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f1c070dd54416925079c546f2cb1546a7c72634c8037d6ea08052f5e0b5d97a
3
+ size 90177536
params_shard_41.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35366407c038bcbb570ea5997c1da658eb39a1b93c32fe0579cae22e8c921e17
3
+ size 100663296
params_shard_42.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22fa70ac1de0fe89b4b29075341c7e688373a6d5cb7ae32bb21acaf1a311e1c7
3
+ size 33554432
params_shard_43.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c324e1a2c84ec10e11f43aed2ff6e2509fe834ea398aa0f4e6c009e4a5eb2489
3
+ size 180355072
params_shard_44.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a47c6e90e0f9fa18b2400dd0fc71780ba82811208592ac16e723d8cc8482b0d
3
+ size 90177536
params_shard_45.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2444cc1bf0aa55eac7713973d24e928087c61cbc66216b0e2a0fd23e23a06e78
3
+ size 100663296
params_shard_46.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:135acaed3036237c4998674325f01b6e6c5e38267a15ea6164b8da2fb9e6bec9
3
+ size 33554432
params_shard_47.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3c438bec60eefae6b42f14248f62dde0dde56f1543d9cbba74fd3730ebe683a
3
+ size 180355072
params_shard_48.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6d83e4e8b6aeb72b3727118b454a0afbad60dae2e0286b6bce63c4ca51864eb
3
+ size 90177536
params_shard_49.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f30bbf2d7ebe5e5b5f9aea8b73518ef5339f6300c75ebc71a93d7ad894e735b
3
+ size 100663296
params_shard_5.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ef467f5c4c4d37ae28df8e56f2f332296535af4a132e02894bb86a381d26fa9
3
+ size 100663296
params_shard_50.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb8b98fd0aacd873706ccbd6b23810362212f2f5c3f93cd2d3c84e0f65a21671
3
+ size 33554432
params_shard_51.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46f6e76bb1afd464ab49c6f5ad1879e4b82fe1b005c5f249eaae4aedd8fe8584
3
+ size 180355072