Hugging Face's logo

kechengcode
/
llama-4b-alpaca_dataset-15layers-mlc

Model card Files Community
kechengcode commited on
Commit
d0af3d4
·
verified ·
1 Parent(s): df3a383

Upload folder using huggingface_hub

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 +90 -0
  2. ndarray-cache.json +1505 -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 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.1.0",
3
+ "model_type": "llama",
4
+ "quantization": "q0f16",
5
+ "model_config": {
6
+ "hidden_size": 4096,
7
+ "intermediate_size": 14336,
8
+ "num_attention_heads": 32,
9
+ "num_hidden_layers": 15,
10
+ "rms_norm_eps": 1e-05,
11
+ "vocab_size": 128256,
12
+ "tie_word_embeddings": false,
13
+ "position_embedding_base": 500000.0,
14
+ "rope_scaling": {
15
+ "factor": 8.0,
16
+ "high_freq_factor": 4.0,
17
+ "low_freq_factor": 1.0,
18
+ "original_max_position_embeddings": 8192,
19
+ "rope_type": "llama3"
20
+ },
21
+ "context_window_size": 2048,
22
+ "prefill_chunk_size": 2048,
23
+ "num_key_value_heads": 8,
24
+ "head_dim": 128,
25
+ "tensor_parallel_shards": 1,
26
+ "pipeline_parallel_stages": 1,
27
+ "max_batch_size": 1
28
+ },
29
+ "vocab_size": 128256,
30
+ "context_window_size": 2048,
31
+ "sliding_window_size": -1,
32
+ "prefill_chunk_size": 2048,
33
+ "attention_sink_size": -1,
34
+ "tensor_parallel_shards": 1,
35
+ "pipeline_parallel_stages": 1,
36
+ "temperature": 0.6,
37
+ "presence_penalty": 0.0,
38
+ "frequency_penalty": 0.0,
39
+ "repetition_penalty": 1.0,
40
+ "top_p": 0.9,
41
+ "tokenizer_files": [
42
+ "tokenizer.json",
43
+ "tokenizer_config.json"
44
+ ],
45
+ "tokenizer_info": {
46
+ "token_postproc_method": "byte_level",
47
+ "prepend_space_in_encode": false,
48
+ "strip_space_in_decode": false
49
+ },
50
+ "conv_template": {
51
+ "name": "llama-3_1",
52
+ "system_template": "<|start_header_id|>system<|end_header_id|>\n\n{system_message}<|eot_id|>",
53
+ "system_message": "You are a helpful, respectful and honest assistant.",
54
+ "system_prefix_token_ids": [
55
+ 128000
56
+ ],
57
+ "add_role_after_system_message": true,
58
+ "roles": {
59
+ "user": "<|start_header_id|>user",
60
+ "assistant": "<|start_header_id|>assistant",
61
+ "tool": "<|start_header_id|>ipython"
62
+ },
63
+ "role_templates": {
64
+ "user": "{user_message}",
65
+ "assistant": "{assistant_message}",
66
+ "tool": "{tool_message}"
67
+ },
68
+ "messages": [],
69
+ "seps": [
70
+ "<|eot_id|>"
71
+ ],
72
+ "role_content_sep": "<|end_header_id|>\n\n",
73
+ "role_empty_sep": "<|end_header_id|>\n\n",
74
+ "stop_str": [],
75
+ "stop_token_ids": [
76
+ 128001,
77
+ 128008,
78
+ 128009
79
+ ],
80
+ "function_string": "",
81
+ "use_function_calling": false
82
+ },
83
+ "pad_token_id": 0,
84
+ "bos_token_id": 128000,
85
+ "eos_token_id": [
86
+ 128001,
87
+ 128008,
88
+ 128009
89
+ ]
90
+ }
ndarray-cache.json ADDED
@@ -0,0 +1,1505 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "ParamSize": 93,
4
+ "ParamBytes": 8644714496.0,
5
+ "BitsPerParam": 16.0
6
+ },
7
+ "records": [
8
+ {
9
+ "dataPath": "params_shard_0.bin",
10
+ "format": "raw-shard",
11
+ "nbytes": 1050673152,
12
+ "records": [
13
+ {
14
+ "name": "lm_head.weight",
15
+ "shape": [
16
+ 128256,
17
+ 4096
18
+ ],
19
+ "dtype": "float16",
20
+ "format": "f32-to-bf16",
21
+ "nbytes": 1050673152,
22
+ "byteOffset": 0
23
+ }
24
+ ],
25
+ "md5sum": "86011fc8d6d280ac1805509c0d17de66"
26
+ },
27
+ {
28
+ "dataPath": "params_shard_1.bin",
29
+ "format": "raw-shard",
30
+ "nbytes": 117440512,
31
+ "records": [
32
+ {
33
+ "name": "model.layers.10.mlp.down_proj.weight",
34
+ "shape": [
35
+ 4096,
36
+ 14336
37
+ ],
38
+ "dtype": "float16",
39
+ "format": "f32-to-bf16",
40
+ "nbytes": 117440512,
41
+ "byteOffset": 0
42
+ }
43
+ ],
44
+ "md5sum": "f79bfb3233473b999f28c56331ad915a"
45
+ },
46
+ {
47
+ "dataPath": "params_shard_2.bin",
48
+ "format": "raw-shard",
49
+ "nbytes": 234881024,
50
+ "records": [
51
+ {
52
+ "name": "model.layers.10.mlp.gate_up_proj.weight",
53
+ "shape": [
54
+ 28672,
55
+ 4096
56
+ ],
57
+ "dtype": "float16",
58
+ "format": "f32-to-bf16",
59
+ "nbytes": 234881024,
60
+ "byteOffset": 0
61
+ }
62
+ ],
63
+ "md5sum": "f14ca0af5959e02f152e3ad93b013084"
64
+ },
65
+ {
66
+ "dataPath": "params_shard_3.bin",
67
+ "format": "raw-shard",
68
+ "nbytes": 50331648,
69
+ "records": [
70
+ {
71
+ "name": "model.layers.10.self_attn.qkv_proj.weight",
72
+ "shape": [
73
+ 6144,
74
+ 4096
75
+ ],
76
+ "dtype": "float16",
77
+ "format": "f32-to-bf16",
78
+ "nbytes": 50331648,
79
+ "byteOffset": 0
80
+ }
81
+ ],
82
+ "md5sum": "0236ca78b420fc9eaa6088d81d668dd7"
83
+ },
84
+ {
85
+ "dataPath": "params_shard_4.bin",
86
+ "format": "raw-shard",
87
+ "nbytes": 33554432,
88
+ "records": [
89
+ {
90
+ "name": "model.layers.10.self_attn.o_proj.weight",
91
+ "shape": [
92
+ 4096,
93
+ 4096
94
+ ],
95
+ "dtype": "float16",
96
+ "format": "f32-to-bf16",
97
+ "nbytes": 33554432,
98
+ "byteOffset": 0
99
+ }
100
+ ],
101
+ "md5sum": "ea73f3ffeaba1745ad83655deadeca04"
102
+ },
103
+ {
104
+ "dataPath": "params_shard_5.bin",
105
+ "format": "raw-shard",
106
+ "nbytes": 117440512,
107
+ "records": [
108
+ {
109
+ "name": "model.layers.11.mlp.down_proj.weight",
110
+ "shape": [
111
+ 4096,
112
+ 14336
113
+ ],
114
+ "dtype": "float16",
115
+ "format": "f32-to-bf16",
116
+ "nbytes": 117440512,
117
+ "byteOffset": 0
118
+ }
119
+ ],
120
+ "md5sum": "1047dd811d238cbbe095dc92f50bfe18"
121
+ },
122
+ {
123
+ "dataPath": "params_shard_6.bin",
124
+ "format": "raw-shard",
125
+ "nbytes": 234881024,
126
+ "records": [
127
+ {
128
+ "name": "model.layers.11.mlp.gate_up_proj.weight",
129
+ "shape": [
130
+ 28672,
131
+ 4096
132
+ ],
133
+ "dtype": "float16",
134
+ "format": "f32-to-bf16",
135
+ "nbytes": 234881024,
136
+ "byteOffset": 0
137
+ }
138
+ ],
139
+ "md5sum": "9c0c5239b3f651fa98e265a4560aadb4"
140
+ },
141
+ {
142
+ "dataPath": "params_shard_7.bin",
143
+ "format": "raw-shard",
144
+ "nbytes": 50331648,
145
+ "records": [
146
+ {
147
+ "name": "model.layers.11.self_attn.qkv_proj.weight",
148
+ "shape": [
149
+ 6144,
150
+ 4096
151
+ ],
152
+ "dtype": "float16",
153
+ "format": "f32-to-bf16",
154
+ "nbytes": 50331648,
155
+ "byteOffset": 0
156
+ }
157
+ ],
158
+ "md5sum": "ff88bdc45a8af96bd461074b11af25a0"
159
+ },
160
+ {
161
+ "dataPath": "params_shard_8.bin",
162
+ "format": "raw-shard",
163
+ "nbytes": 33554432,
164
+ "records": [
165
+ {
166
+ "name": "model.layers.11.self_attn.o_proj.weight",
167
+ "shape": [
168
+ 4096,
169
+ 4096
170
+ ],
171
+ "dtype": "float16",
172
+ "format": "f32-to-bf16",
173
+ "nbytes": 33554432,
174
+ "byteOffset": 0
175
+ }
176
+ ],
177
+ "md5sum": "36545c44019aff7f7a1c048a750db858"
178
+ },
179
+ {
180
+ "dataPath": "params_shard_9.bin",
181
+ "format": "raw-shard",
182
+ "nbytes": 117440512,
183
+ "records": [
184
+ {
185
+ "name": "model.layers.12.mlp.down_proj.weight",
186
+ "shape": [
187
+ 4096,
188
+ 14336
189
+ ],
190
+ "dtype": "float16",
191
+ "format": "f32-to-bf16",
192
+ "nbytes": 117440512,
193
+ "byteOffset": 0
194
+ }
195
+ ],
196
+ "md5sum": "770522c2bd329cadfefc95b46b5f61c2"
197
+ },
198
+ {
199
+ "dataPath": "params_shard_10.bin",
200
+ "format": "raw-shard",
201
+ "nbytes": 234881024,
202
+ "records": [
203
+ {
204
+ "name": "model.layers.12.mlp.gate_up_proj.weight",
205
+ "shape": [
206
+ 28672,
207
+ 4096
208
+ ],
209
+ "dtype": "float16",
210
+ "format": "f32-to-bf16",
211
+ "nbytes": 234881024,
212
+ "byteOffset": 0
213
+ }
214
+ ],
215
+ "md5sum": "e14c1084fe3161a3cb638b9558ff44c0"
216
+ },
217
+ {
218
+ "dataPath": "params_shard_11.bin",
219
+ "format": "raw-shard",
220
+ "nbytes": 50331648,
221
+ "records": [
222
+ {
223
+ "name": "model.layers.12.self_attn.qkv_proj.weight",
224
+ "shape": [
225
+ 6144,
226
+ 4096
227
+ ],
228
+ "dtype": "float16",
229
+ "format": "f32-to-bf16",
230
+ "nbytes": 50331648,
231
+ "byteOffset": 0
232
+ }
233
+ ],
234
+ "md5sum": "15205d46f0832355f97abbf70d25392b"
235
+ },
236
+ {
237
+ "dataPath": "params_shard_12.bin",
238
+ "format": "raw-shard",
239
+ "nbytes": 33554432,
240
+ "records": [
241
+ {
242
+ "name": "model.layers.12.self_attn.o_proj.weight",
243
+ "shape": [
244
+ 4096,
245
+ 4096
246
+ ],
247
+ "dtype": "float16",
248
+ "format": "f32-to-bf16",
249
+ "nbytes": 33554432,
250
+ "byteOffset": 0
251
+ }
252
+ ],
253
+ "md5sum": "64c792ec9093b90ea524e7ca9d66e88c"
254
+ },
255
+ {
256
+ "dataPath": "params_shard_13.bin",
257
+ "format": "raw-shard",
258
+ "nbytes": 117440512,
259
+ "records": [
260
+ {
261
+ "name": "model.layers.13.mlp.down_proj.weight",
262
+ "shape": [
263
+ 4096,
264
+ 14336
265
+ ],
266
+ "dtype": "float16",
267
+ "format": "f32-to-bf16",
268
+ "nbytes": 117440512,
269
+ "byteOffset": 0
270
+ }
271
+ ],
272
+ "md5sum": "224583992660fbe33f5b1edc7679f26a"
273
+ },
274
+ {
275
+ "dataPath": "params_shard_14.bin",
276
+ "format": "raw-shard",
277
+ "nbytes": 234881024,
278
+ "records": [
279
+ {
280
+ "name": "model.layers.13.mlp.gate_up_proj.weight",
281
+ "shape": [
282
+ 28672,
283
+ 4096
284
+ ],
285
+ "dtype": "float16",
286
+ "format": "f32-to-bf16",
287
+ "nbytes": 234881024,
288
+ "byteOffset": 0
289
+ }
290
+ ],
291
+ "md5sum": "b5005524be8f65a7ea75d26f91266c3c"
292
+ },
293
+ {
294
+ "dataPath": "params_shard_15.bin",
295
+ "format": "raw-shard",
296
+ "nbytes": 50331648,
297
+ "records": [
298
+ {
299
+ "name": "model.layers.13.self_attn.qkv_proj.weight",
300
+ "shape": [
301
+ 6144,
302
+ 4096
303
+ ],
304
+ "dtype": "float16",
305
+ "format": "f32-to-bf16",
306
+ "nbytes": 50331648,
307
+ "byteOffset": 0
308
+ }
309
+ ],
310
+ "md5sum": "8ebc9dceb176f3a4a0fa48a864282915"
311
+ },
312
+ {
313
+ "dataPath": "params_shard_16.bin",
314
+ "format": "raw-shard",
315
+ "nbytes": 33554432,
316
+ "records": [
317
+ {
318
+ "name": "model.layers.13.self_attn.o_proj.weight",
319
+ "shape": [
320
+ 4096,
321
+ 4096
322
+ ],
323
+ "dtype": "float16",
324
+ "format": "f32-to-bf16",
325
+ "nbytes": 33554432,
326
+ "byteOffset": 0
327
+ }
328
+ ],
329
+ "md5sum": "e5b5397835c2cfa9a988d2c3242a4214"
330
+ },
331
+ {
332
+ "dataPath": "params_shard_17.bin",
333
+ "format": "raw-shard",
334
+ "nbytes": 117440512,
335
+ "records": [
336
+ {
337
+ "name": "model.layers.14.mlp.down_proj.weight",
338
+ "shape": [
339
+ 4096,
340
+ 14336
341
+ ],
342
+ "dtype": "float16",
343
+ "format": "f32-to-bf16",
344
+ "nbytes": 117440512,
345
+ "byteOffset": 0
346
+ }
347
+ ],
348
+ "md5sum": "57929e3c93c19bdb6d41142202b5d606"
349
+ },
350
+ {
351
+ "dataPath": "params_shard_18.bin",
352
+ "format": "raw-shard",
353
+ "nbytes": 234881024,
354
+ "records": [
355
+ {
356
+ "name": "model.layers.14.mlp.gate_up_proj.weight",
357
+ "shape": [
358
+ 28672,
359
+ 4096
360
+ ],
361
+ "dtype": "float16",
362
+ "format": "f32-to-bf16",
363
+ "nbytes": 234881024,
364
+ "byteOffset": 0
365
+ }
366
+ ],
367
+ "md5sum": "4139f840b840b41bfb374955fbdc85f8"
368
+ },
369
+ {
370
+ "dataPath": "params_shard_19.bin",
371
+ "format": "raw-shard",
372
+ "nbytes": 50331648,
373
+ "records": [
374
+ {
375
+ "name": "model.layers.14.self_attn.qkv_proj.weight",
376
+ "shape": [
377
+ 6144,
378
+ 4096
379
+ ],
380
+ "dtype": "float16",
381
+ "format": "f32-to-bf16",
382
+ "nbytes": 50331648,
383
+ "byteOffset": 0
384
+ }
385
+ ],
386
+ "md5sum": "a96c3f05d23eb6c1ac882faebea4bc16"
387
+ },
388
+ {
389
+ "dataPath": "params_shard_20.bin",
390
+ "format": "raw-shard",
391
+ "nbytes": 33554432,
392
+ "records": [
393
+ {
394
+ "name": "model.layers.14.self_attn.o_proj.weight",
395
+ "shape": [
396
+ 4096,
397
+ 4096
398
+ ],
399
+ "dtype": "float16",
400
+ "format": "f32-to-bf16",
401
+ "nbytes": 33554432,
402
+ "byteOffset": 0
403
+ }
404
+ ],
405
+ "md5sum": "d64f181bfabb1aaae45d36bf6a541644"
406
+ },
407
+ {
408
+ "dataPath": "params_shard_21.bin",
409
+ "format": "raw-shard",
410
+ "nbytes": 117440512,
411
+ "records": [
412
+ {
413
+ "name": "model.layers.9.mlp.down_proj.weight",
414
+ "shape": [
415
+ 4096,
416
+ 14336
417
+ ],
418
+ "dtype": "float16",
419
+ "format": "f32-to-bf16",
420
+ "nbytes": 117440512,
421
+ "byteOffset": 0
422
+ }
423
+ ],
424
+ "md5sum": "9199dd4c779a1b9ae9ddccc5e7a3ec41"
425
+ },
426
+ {
427
+ "dataPath": "params_shard_22.bin",
428
+ "format": "raw-shard",
429
+ "nbytes": 234881024,
430
+ "records": [
431
+ {
432
+ "name": "model.layers.9.mlp.gate_up_proj.weight",
433
+ "shape": [
434
+ 28672,
435
+ 4096
436
+ ],
437
+ "dtype": "float16",
438
+ "format": "f32-to-bf16",
439
+ "nbytes": 234881024,
440
+ "byteOffset": 0
441
+ }
442
+ ],
443
+ "md5sum": "e200800802d314abfcf32056ebf0a79f"
444
+ },
445
+ {
446
+ "dataPath": "params_shard_23.bin",
447
+ "format": "raw-shard",
448
+ "nbytes": 50331648,
449
+ "records": [
450
+ {
451
+ "name": "model.layers.9.self_attn.qkv_proj.weight",
452
+ "shape": [
453
+ 6144,
454
+ 4096
455
+ ],
456
+ "dtype": "float16",
457
+ "format": "f32-to-bf16",
458
+ "nbytes": 50331648,
459
+ "byteOffset": 0
460
+ }
461
+ ],
462
+ "md5sum": "0dad768991391b52751313c54773674c"
463
+ },
464
+ {
465
+ "dataPath": "params_shard_24.bin",
466
+ "format": "raw-shard",
467
+ "nbytes": 33554432,
468
+ "records": [
469
+ {
470
+ "name": "model.layers.9.self_attn.o_proj.weight",
471
+ "shape": [
472
+ 4096,
473
+ 4096
474
+ ],
475
+ "dtype": "float16",
476
+ "format": "f32-to-bf16",
477
+ "nbytes": 33554432,
478
+ "byteOffset": 0
479
+ }
480
+ ],
481
+ "md5sum": "0dcdae9b06e2c7a52045b8608f6d9a52"
482
+ },
483
+ {
484
+ "dataPath": "params_shard_25.bin",
485
+ "format": "raw-shard",
486
+ "nbytes": 1050673152,
487
+ "records": [
488
+ {
489
+ "name": "model.embed_tokens.weight",
490
+ "shape": [
491
+ 128256,
492
+ 4096
493
+ ],
494
+ "dtype": "float16",
495
+ "format": "f32-to-bf16",
496
+ "nbytes": 1050673152,
497
+ "byteOffset": 0
498
+ }
499
+ ],
500
+ "md5sum": "6928f563b4a8b16250f0effe48d9bcf5"
501
+ },
502
+ {
503
+ "dataPath": "params_shard_26.bin",
504
+ "format": "raw-shard",
505
+ "nbytes": 117440512,
506
+ "records": [
507
+ {
508
+ "name": "model.layers.0.mlp.down_proj.weight",
509
+ "shape": [
510
+ 4096,
511
+ 14336
512
+ ],
513
+ "dtype": "float16",
514
+ "format": "f32-to-bf16",
515
+ "nbytes": 117440512,
516
+ "byteOffset": 0
517
+ }
518
+ ],
519
+ "md5sum": "942ed4a2a7a7b4f48bd685e2f5e07bc3"
520
+ },
521
+ {
522
+ "dataPath": "params_shard_27.bin",
523
+ "format": "raw-shard",
524
+ "nbytes": 234881024,
525
+ "records": [
526
+ {
527
+ "name": "model.layers.0.mlp.gate_up_proj.weight",
528
+ "shape": [
529
+ 28672,
530
+ 4096
531
+ ],
532
+ "dtype": "float16",
533
+ "format": "f32-to-bf16",
534
+ "nbytes": 234881024,
535
+ "byteOffset": 0
536
+ }
537
+ ],
538
+ "md5sum": "7121ed254b5c3edd8d121312dadbd784"
539
+ },
540
+ {
541
+ "dataPath": "params_shard_28.bin",
542
+ "format": "raw-shard",
543
+ "nbytes": 50331648,
544
+ "records": [
545
+ {
546
+ "name": "model.layers.0.self_attn.qkv_proj.weight",
547
+ "shape": [
548
+ 6144,
549
+ 4096
550
+ ],
551
+ "dtype": "float16",
552
+ "format": "f32-to-bf16",
553
+ "nbytes": 50331648,
554
+ "byteOffset": 0
555
+ }
556
+ ],
557
+ "md5sum": "2305a6f45b854305933aa42520b84edd"
558
+ },
559
+ {
560
+ "dataPath": "params_shard_29.bin",
561
+ "format": "raw-shard",
562
+ "nbytes": 33554432,
563
+ "records": [
564
+ {
565
+ "name": "model.layers.0.self_attn.o_proj.weight",
566
+ "shape": [
567
+ 4096,
568
+ 4096
569
+ ],
570
+ "dtype": "float16",
571
+ "format": "f32-to-bf16",
572
+ "nbytes": 33554432,
573
+ "byteOffset": 0
574
+ }
575
+ ],
576
+ "md5sum": "f4d6700c18d5fbd61e230b6e69df0b33"
577
+ },
578
+ {
579
+ "dataPath": "params_shard_30.bin",
580
+ "format": "raw-shard",
581
+ "nbytes": 117440512,
582
+ "records": [
583
+ {
584
+ "name": "model.layers.1.mlp.down_proj.weight",
585
+ "shape": [
586
+ 4096,
587
+ 14336
588
+ ],
589
+ "dtype": "float16",
590
+ "format": "f32-to-bf16",
591
+ "nbytes": 117440512,
592
+ "byteOffset": 0
593
+ }
594
+ ],
595
+ "md5sum": "6a0a90436e42dfa3d4b3c6099988aa24"
596
+ },
597
+ {
598
+ "dataPath": "params_shard_31.bin",
599
+ "format": "raw-shard",
600
+ "nbytes": 234881024,
601
+ "records": [
602
+ {
603
+ "name": "model.layers.1.mlp.gate_up_proj.weight",
604
+ "shape": [
605
+ 28672,
606
+ 4096
607
+ ],
608
+ "dtype": "float16",
609
+ "format": "f32-to-bf16",
610
+ "nbytes": 234881024,
611
+ "byteOffset": 0
612
+ }
613
+ ],
614
+ "md5sum": "63d70cf82f6012b86e235038033468c3"
615
+ },
616
+ {
617
+ "dataPath": "params_shard_32.bin",
618
+ "format": "raw-shard",
619
+ "nbytes": 50331648,
620
+ "records": [
621
+ {
622
+ "name": "model.layers.1.self_attn.qkv_proj.weight",
623
+ "shape": [
624
+ 6144,
625
+ 4096
626
+ ],
627
+ "dtype": "float16",
628
+ "format": "f32-to-bf16",
629
+ "nbytes": 50331648,
630
+ "byteOffset": 0
631
+ }
632
+ ],
633
+ "md5sum": "2bf3af3b5bb6026ef2fb915419a0770e"
634
+ },
635
+ {
636
+ "dataPath": "params_shard_33.bin",
637
+ "format": "raw-shard",
638
+ "nbytes": 33554432,
639
+ "records": [
640
+ {
641
+ "name": "model.layers.1.self_attn.o_proj.weight",
642
+ "shape": [
643
+ 4096,
644
+ 4096
645
+ ],
646
+ "dtype": "float16",
647
+ "format": "f32-to-bf16",
648
+ "nbytes": 33554432,
649
+ "byteOffset": 0
650
+ }
651
+ ],
652
+ "md5sum": "e23dab75bbfda9e4bcd58b816f37db0c"
653
+ },
654
+ {
655
+ "dataPath": "params_shard_34.bin",
656
+ "format": "raw-shard",
657
+ "nbytes": 117440512,
658
+ "records": [
659
+ {
660
+ "name": "model.layers.2.mlp.down_proj.weight",
661
+ "shape": [
662
+ 4096,
663
+ 14336
664
+ ],
665
+ "dtype": "float16",
666
+ "format": "f32-to-bf16",
667
+ "nbytes": 117440512,
668
+ "byteOffset": 0
669
+ }
670
+ ],
671
+ "md5sum": "80aa51d9c09bed1e30b4e3b152413705"
672
+ },
673
+ {
674
+ "dataPath": "params_shard_35.bin",
675
+ "format": "raw-shard",
676
+ "nbytes": 234881024,
677
+ "records": [
678
+ {
679
+ "name": "model.layers.2.mlp.gate_up_proj.weight",
680
+ "shape": [
681
+ 28672,
682
+ 4096
683
+ ],
684
+ "dtype": "float16",
685
+ "format": "f32-to-bf16",
686
+ "nbytes": 234881024,
687
+ "byteOffset": 0
688
+ }
689
+ ],
690
+ "md5sum": "aa15b431ed384bbf2f6ad78c5396a53e"
691
+ },
692
+ {
693
+ "dataPath": "params_shard_36.bin",
694
+ "format": "raw-shard",
695
+ "nbytes": 50331648,
696
+ "records": [
697
+ {
698
+ "name": "model.layers.2.self_attn.qkv_proj.weight",
699
+ "shape": [
700
+ 6144,
701
+ 4096
702
+ ],
703
+ "dtype": "float16",
704
+ "format": "f32-to-bf16",
705
+ "nbytes": 50331648,
706
+ "byteOffset": 0
707
+ }
708
+ ],
709
+ "md5sum": "e6d758eb8db2210fd4b6f8b1b86d8ab2"
710
+ },
711
+ {
712
+ "dataPath": "params_shard_37.bin",
713
+ "format": "raw-shard",
714
+ "nbytes": 33554432,
715
+ "records": [
716
+ {
717
+ "name": "model.layers.2.self_attn.o_proj.weight",
718
+ "shape": [
719
+ 4096,
720
+ 4096
721
+ ],
722
+ "dtype": "float16",
723
+ "format": "f32-to-bf16",
724
+ "nbytes": 33554432,
725
+ "byteOffset": 0
726
+ }
727
+ ],
728
+ "md5sum": "9a442fd3fcc4ab1b41c398a19bf69577"
729
+ },
730
+ {
731
+ "dataPath": "params_shard_38.bin",
732
+ "format": "raw-shard",
733
+ "nbytes": 117440512,
734
+ "records": [
735
+ {
736
+ "name": "model.layers.3.mlp.down_proj.weight",
737
+ "shape": [
738
+ 4096,
739
+ 14336
740
+ ],
741
+ "dtype": "float16",
742
+ "format": "f32-to-bf16",
743
+ "nbytes": 117440512,
744
+ "byteOffset": 0
745
+ }
746
+ ],
747
+ "md5sum": "92fec42fe1bd462bc06483eabb12b85b"
748
+ },
749
+ {
750
+ "dataPath": "params_shard_39.bin",
751
+ "format": "raw-shard",
752
+ "nbytes": 234881024,
753
+ "records": [
754
+ {
755
+ "name": "model.layers.3.mlp.gate_up_proj.weight",
756
+ "shape": [
757
+ 28672,
758
+ 4096
759
+ ],
760
+ "dtype": "float16",
761
+ "format": "f32-to-bf16",
762
+ "nbytes": 234881024,
763
+ "byteOffset": 0
764
+ }
765
+ ],
766
+ "md5sum": "59df764364a1d675dc1a2b6e7c0bbaf2"
767
+ },
768
+ {
769
+ "dataPath": "params_shard_40.bin",
770
+ "format": "raw-shard",
771
+ "nbytes": 50331648,
772
+ "records": [
773
+ {
774
+ "name": "model.layers.3.self_attn.qkv_proj.weight",
775
+ "shape": [
776
+ 6144,
777
+ 4096
778
+ ],
779
+ "dtype": "float16",
780
+ "format": "f32-to-bf16",
781
+ "nbytes": 50331648,
782
+ "byteOffset": 0
783
+ }
784
+ ],
785
+ "md5sum": "5e9efa89d002489a38b90418a6920208"
786
+ },
787
+ {
788
+ "dataPath": "params_shard_41.bin",
789
+ "format": "raw-shard",
790
+ "nbytes": 33554432,
791
+ "records": [
792
+ {
793
+ "name": "model.layers.3.self_attn.o_proj.weight",
794
+ "shape": [
795
+ 4096,
796
+ 4096
797
+ ],
798
+ "dtype": "float16",
799
+ "format": "f32-to-bf16",
800
+ "nbytes": 33554432,
801
+ "byteOffset": 0
802
+ }
803
+ ],
804
+ "md5sum": "e5f5e67cce4fb2d1282498f5174fc61b"
805
+ },
806
+ {
807
+ "dataPath": "params_shard_42.bin",
808
+ "format": "raw-shard",
809
+ "nbytes": 117440512,
810
+ "records": [
811
+ {
812
+ "name": "model.layers.4.mlp.down_proj.weight",
813
+ "shape": [
814
+ 4096,
815
+ 14336
816
+ ],
817
+ "dtype": "float16",
818
+ "format": "f32-to-bf16",
819
+ "nbytes": 117440512,
820
+ "byteOffset": 0
821
+ }
822
+ ],
823
+ "md5sum": "a3f91f10d5f1ca43e4abc087f1054d04"
824
+ },
825
+ {
826
+ "dataPath": "params_shard_43.bin",
827
+ "format": "raw-shard",
828
+ "nbytes": 234881024,
829
+ "records": [
830
+ {
831
+ "name": "model.layers.4.mlp.gate_up_proj.weight",
832
+ "shape": [
833
+ 28672,
834
+ 4096
835
+ ],
836
+ "dtype": "float16",
837
+ "format": "f32-to-bf16",
838
+ "nbytes": 234881024,
839
+ "byteOffset": 0
840
+ }
841
+ ],
842
+ "md5sum": "af92b196f341133d04147e81caaa0c9a"
843
+ },
844
+ {
845
+ "dataPath": "params_shard_44.bin",
846
+ "format": "raw-shard",
847
+ "nbytes": 50331648,
848
+ "records": [
849
+ {
850
+ "name": "model.layers.4.self_attn.qkv_proj.weight",
851
+ "shape": [
852
+ 6144,
853
+ 4096
854
+ ],
855
+ "dtype": "float16",
856
+ "format": "f32-to-bf16",
857
+ "nbytes": 50331648,
858
+ "byteOffset": 0
859
+ }
860
+ ],
861
+ "md5sum": "3dc3873f71c2b702784c155544e03a5f"
862
+ },
863
+ {
864
+ "dataPath": "params_shard_45.bin",
865
+ "format": "raw-shard",
866
+ "nbytes": 33554432,
867
+ "records": [
868
+ {
869
+ "name": "model.layers.4.self_attn.o_proj.weight",
870
+ "shape": [
871
+ 4096,
872
+ 4096
873
+ ],
874
+ "dtype": "float16",
875
+ "format": "f32-to-bf16",
876
+ "nbytes": 33554432,
877
+ "byteOffset": 0
878
+ }
879
+ ],
880
+ "md5sum": "365b3f92bce3f1e82f92dfae0e40735e"
881
+ },
882
+ {
883
+ "dataPath": "params_shard_46.bin",
884
+ "format": "raw-shard",
885
+ "nbytes": 117440512,
886
+ "records": [
887
+ {
888
+ "name": "model.layers.5.mlp.down_proj.weight",
889
+ "shape": [
890
+ 4096,
891
+ 14336
892
+ ],
893
+ "dtype": "float16",
894
+ "format": "f32-to-bf16",
895
+ "nbytes": 117440512,
896
+ "byteOffset": 0
897
+ }
898
+ ],
899
+ "md5sum": "f362eec3a598f037131faa09906b5ac3"
900
+ },
901
+ {
902
+ "dataPath": "params_shard_47.bin",
903
+ "format": "raw-shard",
904
+ "nbytes": 234881024,
905
+ "records": [
906
+ {
907
+ "name": "model.layers.5.mlp.gate_up_proj.weight",
908
+ "shape": [
909
+ 28672,
910
+ 4096
911
+ ],
912
+ "dtype": "float16",
913
+ "format": "f32-to-bf16",
914
+ "nbytes": 234881024,
915
+ "byteOffset": 0
916
+ }
917
+ ],
918
+ "md5sum": "a3d5d386f47253c86f8a55b7aa0e758d"
919
+ },
920
+ {
921
+ "dataPath": "params_shard_48.bin",
922
+ "format": "raw-shard",
923
+ "nbytes": 50331648,
924
+ "records": [
925
+ {
926
+ "name": "model.layers.5.self_attn.qkv_proj.weight",
927
+ "shape": [
928
+ 6144,
929
+ 4096
930
+ ],
931
+ "dtype": "float16",
932
+ "format": "f32-to-bf16",
933
+ "nbytes": 50331648,
934
+ "byteOffset": 0
935
+ }
936
+ ],
937
+ "md5sum": "deaf1b90e0be86a02b0cf9e8a14ec7a5"
938
+ },
939
+ {
940
+ "dataPath": "params_shard_49.bin",
941
+ "format": "raw-shard",
942
+ "nbytes": 33554432,
943
+ "records": [
944
+ {
945
+ "name": "model.layers.5.self_attn.o_proj.weight",
946
+ "shape": [
947
+ 4096,
948
+ 4096
949
+ ],
950
+ "dtype": "float16",
951
+ "format": "f32-to-bf16",
952
+ "nbytes": 33554432,
953
+ "byteOffset": 0
954
+ }
955
+ ],
956
+ "md5sum": "5f48b1ac5a7344db855b7d478a851c7e"
957
+ },
958
+ {
959
+ "dataPath": "params_shard_50.bin",
960
+ "format": "raw-shard",
961
+ "nbytes": 117440512,
962
+ "records": [
963
+ {
964
+ "name": "model.layers.6.mlp.down_proj.weight",
965
+ "shape": [
966
+ 4096,
967
+ 14336
968
+ ],
969
+ "dtype": "float16",
970
+ "format": "f32-to-bf16",
971
+ "nbytes": 117440512,
972
+ "byteOffset": 0
973
+ }
974
+ ],
975
+ "md5sum": "8fc8d07de6f753c6ccb515934686b7f3"
976
+ },
977
+ {
978
+ "dataPath": "params_shard_51.bin",
979
+ "format": "raw-shard",
980
+ "nbytes": 234881024,
981
+ "records": [
982
+ {
983
+ "name": "model.layers.6.mlp.gate_up_proj.weight",
984
+ "shape": [
985
+ 28672,
986
+ 4096
987
+ ],
988
+ "dtype": "float16",
989
+ "format": "f32-to-bf16",
990
+ "nbytes": 234881024,
991
+ "byteOffset": 0
992
+ }
993
+ ],
994
+ "md5sum": "9e3f00e6ad7d4d249d46a8d9efd043a0"
995
+ },
996
+ {
997
+ "dataPath": "params_shard_52.bin",
998
+ "format": "raw-shard",
999
+ "nbytes": 50331648,
1000
+ "records": [
1001
+ {
1002
+ "name": "model.layers.6.self_attn.qkv_proj.weight",
1003
+ "shape": [
1004
+ 6144,
1005
+ 4096
1006
+ ],
1007
+ "dtype": "float16",
1008
+ "format": "f32-to-bf16",
1009
+ "nbytes": 50331648,
1010
+ "byteOffset": 0
1011
+ }
1012
+ ],
1013
+ "md5sum": "68bbb0eccc4cd3e3296daf6e511295d0"
1014
+ },
1015
+ {
1016
+ "dataPath": "params_shard_53.bin",
1017
+ "format": "raw-shard",
1018
+ "nbytes": 33554432,
1019
+ "records": [
1020
+ {
1021
+ "name": "model.layers.6.self_attn.o_proj.weight",
1022
+ "shape": [
1023
+ 4096,
1024
+ 4096
1025
+ ],
1026
+ "dtype": "float16",
1027
+ "format": "f32-to-bf16",
1028
+ "nbytes": 33554432,
1029
+ "byteOffset": 0
1030
+ }
1031
+ ],
1032
+ "md5sum": "8e336da34882ebdfc6d845816feef2b7"
1033
+ },
1034
+ {
1035
+ "dataPath": "params_shard_54.bin",
1036
+ "format": "raw-shard",
1037
+ "nbytes": 117440512,
1038
+ "records": [
1039
+ {
1040
+ "name": "model.layers.7.mlp.down_proj.weight",
1041
+ "shape": [
1042
+ 4096,
1043
+ 14336
1044
+ ],
1045
+ "dtype": "float16",
1046
+ "format": "f32-to-bf16",
1047
+ "nbytes": 117440512,
1048
+ "byteOffset": 0
1049
+ }
1050
+ ],
1051
+ "md5sum": "e0f3e1e8f296b175e21ae538089913a4"
1052
+ },
1053
+ {
1054
+ "dataPath": "params_shard_55.bin",
1055
+ "format": "raw-shard",
1056
+ "nbytes": 234881024,
1057
+ "records": [
1058
+ {
1059
+ "name": "model.layers.7.mlp.gate_up_proj.weight",
1060
+ "shape": [
1061
+ 28672,
1062
+ 4096
1063
+ ],
1064
+ "dtype": "float16",
1065
+ "format": "f32-to-bf16",
1066
+ "nbytes": 234881024,
1067
+ "byteOffset": 0
1068
+ }
1069
+ ],
1070
+ "md5sum": "56f9506158811691a794a0aaca552b08"
1071
+ },
1072
+ {
1073
+ "dataPath": "params_shard_56.bin",
1074
+ "format": "raw-shard",
1075
+ "nbytes": 50331648,
1076
+ "records": [
1077
+ {
1078
+ "name": "model.layers.7.self_attn.qkv_proj.weight",
1079
+ "shape": [
1080
+ 6144,
1081
+ 4096
1082
+ ],
1083
+ "dtype": "float16",
1084
+ "format": "f32-to-bf16",
1085
+ "nbytes": 50331648,
1086
+ "byteOffset": 0
1087
+ }
1088
+ ],
1089
+ "md5sum": "71f017181d1b305c213746e770d7bd80"
1090
+ },
1091
+ {
1092
+ "dataPath": "params_shard_57.bin",
1093
+ "format": "raw-shard",
1094
+ "nbytes": 33554432,
1095
+ "records": [
1096
+ {
1097
+ "name": "model.layers.7.self_attn.o_proj.weight",
1098
+ "shape": [
1099
+ 4096,
1100
+ 4096
1101
+ ],
1102
+ "dtype": "float16",
1103
+ "format": "f32-to-bf16",
1104
+ "nbytes": 33554432,
1105
+ "byteOffset": 0
1106
+ }
1107
+ ],
1108
+ "md5sum": "6bb4aa2445219780517787cb1fc79275"
1109
+ },
1110
+ {
1111
+ "dataPath": "params_shard_58.bin",
1112
+ "format": "raw-shard",
1113
+ "nbytes": 117440512,
1114
+ "records": [
1115
+ {
1116
+ "name": "model.layers.8.mlp.down_proj.weight",
1117
+ "shape": [
1118
+ 4096,
1119
+ 14336
1120
+ ],
1121
+ "dtype": "float16",
1122
+ "format": "f32-to-bf16",
1123
+ "nbytes": 117440512,
1124
+ "byteOffset": 0
1125
+ }
1126
+ ],
1127
+ "md5sum": "6408db051aaf584f12097843039a9642"
1128
+ },
1129
+ {
1130
+ "dataPath": "params_shard_59.bin",
1131
+ "format": "raw-shard",
1132
+ "nbytes": 234881024,
1133
+ "records": [
1134
+ {
1135
+ "name": "model.layers.8.mlp.gate_up_proj.weight",
1136
+ "shape": [
1137
+ 28672,
1138
+ 4096
1139
+ ],
1140
+ "dtype": "float16",
1141
+ "format": "f32-to-bf16",
1142
+ "nbytes": 234881024,
1143
+ "byteOffset": 0
1144
+ }
1145
+ ],
1146
+ "md5sum": "7367c444cb98789129325929efe691f8"
1147
+ },
1148
+ {
1149
+ "dataPath": "params_shard_60.bin",
1150
+ "format": "raw-shard",
1151
+ "nbytes": 50331648,
1152
+ "records": [
1153
+ {
1154
+ "name": "model.layers.8.self_attn.qkv_proj.weight",
1155
+ "shape": [
1156
+ 6144,
1157
+ 4096
1158
+ ],
1159
+ "dtype": "float16",
1160
+ "format": "f32-to-bf16",
1161
+ "nbytes": 50331648,
1162
+ "byteOffset": 0
1163
+ }
1164
+ ],
1165
+ "md5sum": "acaaa89aa3b04ca49164fd8545ab9369"
1166
+ },
1167
+ {
1168
+ "dataPath": "params_shard_61.bin",
1169
+ "format": "raw-shard",
1170
+ "nbytes": 33554432,
1171
+ "records": [
1172
+ {
1173
+ "name": "model.layers.8.self_attn.o_proj.weight",
1174
+ "shape": [
1175
+ 4096,
1176
+ 4096
1177
+ ],
1178
+ "dtype": "float16",
1179
+ "format": "f32-to-bf16",
1180
+ "nbytes": 33554432,
1181
+ "byteOffset": 0
1182
+ }
1183
+ ],
1184
+ "md5sum": "24a709ec7c3313ab9c57bb0d1f02043a"
1185
+ },
1186
+ {
1187
+ "dataPath": "params_shard_62.bin",
1188
+ "format": "raw-shard",
1189
+ "nbytes": 253952,
1190
+ "records": [
1191
+ {
1192
+ "name": "model.layers.10.input_layernorm.weight",
1193
+ "shape": [
1194
+ 4096
1195
+ ],
1196
+ "dtype": "float16",
1197
+ "format": "f32-to-bf16",
1198
+ "nbytes": 8192,
1199
+ "byteOffset": 0
1200
+ },
1201
+ {
1202
+ "name": "model.layers.10.post_attention_layernorm.weight",
1203
+ "shape": [
1204
+ 4096
1205
+ ],
1206
+ "dtype": "float16",
1207
+ "format": "f32-to-bf16",
1208
+ "nbytes": 8192,
1209
+ "byteOffset": 8192
1210
+ },
1211
+ {
1212
+ "name": "model.layers.11.input_layernorm.weight",
1213
+ "shape": [
1214
+ 4096
1215
+ ],
1216
+ "dtype": "float16",
1217
+ "format": "f32-to-bf16",
1218
+ "nbytes": 8192,
1219
+ "byteOffset": 16384
1220
+ },
1221
+ {
1222
+ "name": "model.layers.11.post_attention_layernorm.weight",
1223
+ "shape": [
1224
+ 4096
1225
+ ],
1226
+ "dtype": "float16",
1227
+ "format": "f32-to-bf16",
1228
+ "nbytes": 8192,
1229
+ "byteOffset": 24576
1230
+ },
1231
+ {
1232
+ "name": "model.layers.12.input_layernorm.weight",
1233
+ "shape": [
1234
+ 4096
1235
+ ],
1236
+ "dtype": "float16",
1237
+ "format": "f32-to-bf16",
1238
+ "nbytes": 8192,
1239
+ "byteOffset": 32768
1240
+ },
1241
+ {
1242
+ "name": "model.layers.12.post_attention_layernorm.weight",
1243
+ "shape": [
1244
+ 4096
1245
+ ],
1246
+ "dtype": "float16",
1247
+ "format": "f32-to-bf16",
1248
+ "nbytes": 8192,
1249
+ "byteOffset": 40960
1250
+ },
1251
+ {
1252
+ "name": "model.layers.13.input_layernorm.weight",
1253
+ "shape": [
1254
+ 4096
1255
+ ],
1256
+ "dtype": "float16",
1257
+ "format": "f32-to-bf16",
1258
+ "nbytes": 8192,
1259
+ "byteOffset": 49152
1260
+ },
1261
+ {
1262
+ "name": "model.layers.13.post_attention_layernorm.weight",
1263
+ "shape": [
1264
+ 4096
1265
+ ],
1266
+ "dtype": "float16",
1267
+ "format": "f32-to-bf16",
1268
+ "nbytes": 8192,
1269
+ "byteOffset": 57344
1270
+ },
1271
+ {
1272
+ "name": "model.layers.14.input_layernorm.weight",
1273
+ "shape": [
1274
+ 4096
1275
+ ],
1276
+ "dtype": "float16",
1277
+ "format": "f32-to-bf16",
1278
+ "nbytes": 8192,
1279
+ "byteOffset": 65536
1280
+ },
1281
+ {
1282
+ "name": "model.layers.14.post_attention_layernorm.weight",
1283
+ "shape": [
1284
+ 4096
1285
+ ],
1286
+ "dtype": "float16",
1287
+ "format": "f32-to-bf16",
1288
+ "nbytes": 8192,
1289
+ "byteOffset": 73728
1290
+ },
1291
+ {
1292
+ "name": "model.layers.9.input_layernorm.weight",
1293
+ "shape": [
1294
+ 4096
1295
+ ],
1296
+ "dtype": "float16",
1297
+ "format": "f32-to-bf16",
1298
+ "nbytes": 8192,
1299
+ "byteOffset": 81920
1300
+ },
1301
+ {
1302
+ "name": "model.layers.9.post_attention_layernorm.weight",
1303
+ "shape": [
1304
+ 4096
1305
+ ],
1306
+ "dtype": "float16",
1307
+ "format": "f32-to-bf16",
1308
+ "nbytes": 8192,
1309
+ "byteOffset": 90112
1310
+ },
1311
+ {
1312
+ "name": "model.norm.weight",
1313
+ "shape": [
1314
+ 4096
1315
+ ],
1316
+ "dtype": "float16",
1317
+ "format": "f32-to-bf16",
1318
+ "nbytes": 8192,
1319
+ "byteOffset": 98304
1320
+ },
1321
+ {
1322
+ "name": "model.layers.0.input_layernorm.weight",
1323
+ "shape": [
1324
+ 4096
1325
+ ],
1326
+ "dtype": "float16",
1327
+ "format": "f32-to-bf16",
1328
+ "nbytes": 8192,
1329
+ "byteOffset": 106496
1330
+ },
1331
+ {
1332
+ "name": "model.layers.0.post_attention_layernorm.weight",
1333
+ "shape": [
1334
+ 4096
1335
+ ],
1336
+ "dtype": "float16",
1337
+ "format": "f32-to-bf16",
1338
+ "nbytes": 8192,
1339
+ "byteOffset": 114688
1340
+ },
1341
+ {
1342
+ "name": "model.layers.1.input_layernorm.weight",
1343
+ "shape": [
1344
+ 4096
1345
+ ],
1346
+ "dtype": "float16",
1347
+ "format": "f32-to-bf16",
1348
+ "nbytes": 8192,
1349
+ "byteOffset": 122880
1350
+ },
1351
+ {
1352
+ "name": "model.layers.1.post_attention_layernorm.weight",
1353
+ "shape": [
1354
+ 4096
1355
+ ],
1356
+ "dtype": "float16",
1357
+ "format": "f32-to-bf16",
1358
+ "nbytes": 8192,
1359
+ "byteOffset": 131072
1360
+ },
1361
+ {
1362
+ "name": "model.layers.2.input_layernorm.weight",
1363
+ "shape": [
1364
+ 4096
1365
+ ],
1366
+ "dtype": "float16",
1367
+ "format": "f32-to-bf16",
1368
+ "nbytes": 8192,
1369
+ "byteOffset": 139264
1370
+ },
1371
+ {
1372
+ "name": "model.layers.2.post_attention_layernorm.weight",
1373
+ "shape": [
1374
+ 4096
1375
+ ],
1376
+ "dtype": "float16",
1377
+ "format": "f32-to-bf16",
1378
+ "nbytes": 8192,
1379
+ "byteOffset": 147456
1380
+ },
1381
+ {
1382
+ "name": "model.layers.3.input_layernorm.weight",
1383
+ "shape": [
1384
+ 4096
1385
+ ],
1386
+ "dtype": "float16",
1387
+ "format": "f32-to-bf16",
1388
+ "nbytes": 8192,
1389
+ "byteOffset": 155648
1390
+ },
1391
+ {
1392
+ "name": "model.layers.3.post_attention_layernorm.weight",
1393
+ "shape": [
1394
+ 4096
1395
+ ],
1396
+ "dtype": "float16",
1397
+ "format": "f32-to-bf16",
1398
+ "nbytes": 8192,
1399
+ "byteOffset": 163840
1400
+ },
1401
+ {
1402
+ "name": "model.layers.4.input_layernorm.weight",
1403
+ "shape": [
1404
+ 4096
1405
+ ],
1406
+ "dtype": "float16",
1407
+ "format": "f32-to-bf16",
1408
+ "nbytes": 8192,
1409
+ "byteOffset": 172032
1410
+ },
1411
+ {
1412
+ "name": "model.layers.4.post_attention_layernorm.weight",
1413
+ "shape": [
1414
+ 4096
1415
+ ],
1416
+ "dtype": "float16",
1417
+ "format": "f32-to-bf16",
1418
+ "nbytes": 8192,
1419
+ "byteOffset": 180224
1420
+ },
1421
+ {
1422
+ "name": "model.layers.5.input_layernorm.weight",
1423
+ "shape": [
1424
+ 4096
1425
+ ],
1426
+ "dtype": "float16",
1427
+ "format": "f32-to-bf16",
1428
+ "nbytes": 8192,
1429
+ "byteOffset": 188416
1430
+ },
1431
+ {
1432
+ "name": "model.layers.5.post_attention_layernorm.weight",
1433
+ "shape": [
1434
+ 4096
1435
+ ],
1436
+ "dtype": "float16",
1437
+ "format": "f32-to-bf16",
1438
+ "nbytes": 8192,
1439
+ "byteOffset": 196608
1440
+ },
1441
+ {
1442
+ "name": "model.layers.6.input_layernorm.weight",
1443
+ "shape": [
1444
+ 4096
1445
+ ],
1446
+ "dtype": "float16",
1447
+ "format": "f32-to-bf16",
1448
+ "nbytes": 8192,
1449
+ "byteOffset": 204800
1450
+ },
1451
+ {
1452
+ "name": "model.layers.6.post_attention_layernorm.weight",
1453
+ "shape": [
1454
+ 4096
1455
+ ],
1456
+ "dtype": "float16",
1457
+ "format": "f32-to-bf16",
1458
+ "nbytes": 8192,
1459
+ "byteOffset": 212992
1460
+ },
1461
+ {
1462
+ "name": "model.layers.7.input_layernorm.weight",
1463
+ "shape": [
1464
+ 4096
1465
+ ],
1466
+ "dtype": "float16",
1467
+ "format": "f32-to-bf16",
1468
+ "nbytes": 8192,
1469
+ "byteOffset": 221184
1470
+ },
1471
+ {
1472
+ "name": "model.layers.7.post_attention_layernorm.weight",
1473
+ "shape": [
1474
+ 4096
1475
+ ],
1476
+ "dtype": "float16",
1477
+ "format": "f32-to-bf16",
1478
+ "nbytes": 8192,
1479
+ "byteOffset": 229376
1480
+ },
1481
+ {
1482
+ "name": "model.layers.8.input_layernorm.weight",
1483
+ "shape": [
1484
+ 4096
1485
+ ],
1486
+ "dtype": "float16",
1487
+ "format": "f32-to-bf16",
1488
+ "nbytes": 8192,
1489
+ "byteOffset": 237568
1490
+ },
1491
+ {
1492
+ "name": "model.layers.8.post_attention_layernorm.weight",
1493
+ "shape": [
1494
+ 4096
1495
+ ],
1496
+ "dtype": "float16",
1497
+ "format": "f32-to-bf16",
1498
+ "nbytes": 8192,
1499
+ "byteOffset": 245760
1500
+ }
1501
+ ],
1502
+ "md5sum": "f4709a0c1b375f977fc08c1b20616202"
1503
+ }
1504
+ ]
1505
+ }
params_shard_0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8b5fce399afcc59e11dbb6729d9f40155b348f8e14e6fbacbd175656edc9529
3
+ size 1050673152
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fbef6745cd24b72b6775d78879f64025dcacf06a71b2d58d1b749a524ca4431
3
+ size 117440512
params_shard_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a521c8209f4fca8cbe4ebbba590c2a0086932187ba9bd60cbbd2b6db1b4b60ff
3
+ size 234881024
params_shard_11.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:810eb95e4f305d8eee55edf64288c0de7d8ec61a8f0c6d118e8f75c28d002628
3
+ size 50331648
params_shard_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e07b6ff70adfeac995b63ab0be376db1a7c288f479c970b79d3ac26e921a000c
3
+ size 33554432
params_shard_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98af95125c83db1859367ee1940c9a9f8433ed1e7715c6d6492e2c78c7708ee4
3
+ size 117440512
params_shard_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6db4c5db4d5a20e8d660fc7e82fca9b9ad428baf4d59b726249ee2b83b6e7077
3
+ size 234881024
params_shard_15.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e504807b8b8b5d9ec941efa8419fa8b1b4cac6d49e2b4abe7d4e07a4592ec82e
3
+ size 50331648
params_shard_16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a87555cf9df8d59d47691a592617452679955516e8ff4d533e9f9029cae1a6c1
3
+ size 33554432
params_shard_17.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:931b2bedde6b1868951ec3b430308fb3b2e277b0b6edfe0d954c6ec78d740128
3
+ size 117440512
params_shard_18.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fbb9995aece85f1f91016737d71f00a5b9503d4ecc50be60cccdf4f67b691b1
3
+ size 234881024
params_shard_19.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:055a426df652d9534ccd8e430d9ce1d9eae61afd795392ba751ce8cfb1014f29
3
+ size 50331648
params_shard_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7828cbe52e0031fda2ff82a1da4c771f2cd1ee5d4296c9908612b25077866c70
3
+ size 234881024
params_shard_20.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d6cff412a9949cb551120c7caeae4b29615a54410c6bb70510abfa19d024e10
3
+ size 33554432
params_shard_21.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8754bf081556453775e69d4a759c981b66748c122b807f6538f7a1541649aa8d
3
+ size 117440512
params_shard_22.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b6fcb3f44b6bc432f11a22ea326908ab95f68cb028caf2a41204be54271639c
3
+ size 234881024
params_shard_23.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdb7d320cf1489a4fe650e01783ad51cc0925dc1ecc1567ae88b609f2fde0c45
3
+ size 50331648
params_shard_24.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6db0a082a0752d1431d5171393de32f7a757d66ee0ce5263e2f4aee35af7bbb
3
+ size 33554432
params_shard_25.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11c64552ca79b31b6a4ea72aca4a45d5c6fe8b1c6dbb4341ac407870271c8fb7
3
+ size 1050673152
params_shard_26.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08052acce8f57e3d36a5ad0d30c06fa8c667fbafc686991f5e997d9dadd1e1ec
3
+ size 117440512
params_shard_27.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f7bad52352f9832325461ff3a33e28ce18abf452a56f82b9bbced8abec38be3
3
+ size 234881024
params_shard_28.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef227c0e450e06c812a01a082afd147c5947181953c519eb13fdc61902eb5c27
3
+ size 50331648
params_shard_29.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6462d81315be4b400e11da6de8efda789a6daf0df47ec9febeeb6f6591164d57
3
+ size 33554432
params_shard_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:917de923e0074d48167106a0dbf12cf73acbd4b19c1bfe6c217b2f85ae5d40de
3
+ size 50331648
params_shard_30.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd86fff40ef304387c851e9ef55786ca90230c2c6dda3d95361267660dbe789c
3
+ size 117440512
params_shard_31.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff4bb064325c9f02e42eaa8cd1f81155b22ef61908b1d1c543172264dd738276
3
+ size 234881024
params_shard_32.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87b85270994712fb1e0668519ea78f06de43080be8975562e478d25ac4a816b9
3
+ size 50331648
params_shard_33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d85a3d6a21174543380e48b3b191b29863c66acae97343bf4ff59091b0407007
3
+ size 33554432
params_shard_34.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80754398f0403aac2d6527435e2a1155002591c72352094b66c7c28075caa882
3
+ size 117440512
params_shard_35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed35d0cf6413a51c4480feabe731f200d109f3823cc77bf12f384c7cbc2d9d87
3
+ size 234881024
params_shard_36.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07ecebaeb8b54c9b714579a03d2eae95b85ff9525c3313beab5e0b89c8cb858f
3
+ size 50331648
params_shard_37.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7959db07f43077ae85705b0b0ec55f63d7be4ecc56c4b0181ae20bbc9a4cd4cf
3
+ size 33554432
params_shard_38.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32432a66c55c15320b5679d14c5b47413a03316de0bd6ca1437c8c7718c863fe
3
+ size 117440512
params_shard_39.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84075393d6db0bbdc87505912be1d91c1643f7f4d988b75a2369a6a98e244169
3
+ size 234881024
params_shard_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:349c8fd198079ea4ce8ee594fb6381011f0c18ecc50909351dd8a162de7f6d04
3
+ size 33554432
params_shard_40.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:953c4ea3d3e944a8f3f5c2bb60b2dedc8802986da0805e040b8966ad904c186a
3
+ size 50331648
params_shard_41.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4967fd4e72410056f8a9d18b18d86a68dd347d069f1f38c9bc654eac3bedc147
3
+ size 33554432
params_shard_42.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45b8957688c4e34cb81685c4c310420d7b34fa7b326a6f88161bc55a7e219df1
3
+ size 117440512
params_shard_43.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:392c40cfd52cf80d43adfcc16e6a821672d9e10309df5de66a656aab9f6fe5a1
3
+ size 234881024
params_shard_44.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f164a8de601675e11f0df8d3b133cf3487d76ecfc45ebbf1a2a152ea1536dbc7
3
+ size 50331648
params_shard_45.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:124a31254461d83624ca34308d35b8b49d5ef4a1db842804a32837638996be77
3
+ size 33554432
params_shard_46.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b024c1b488a0dc5b75ea04dc0fd89738e1f9e05ae4c68d9c6a1660cb786a01f6
3
+ size 117440512
params_shard_47.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:808001dfc776fee84720a766f805fd0b1939fa9821a8b8d02d0cd2142bd382bb
3
+ size 234881024
params_shard_48.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b310b43868453e072dfbe9dd45228ee8f2d82c81ef253138c6c45f04ce020d4b
3
+ size 50331648
params_shard_49.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba53a68774f949e8c8d3891fd7bd4f33ce12ff519ae175cc9ed98be63cb71ae0
3
+ size 33554432
params_shard_5.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff769f5731cffbf72eb615690a63ac202c74f6237d012e4c34136ca29cf0e7c0
3
+ size 117440512
params_shard_50.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8832a26df3c0031167c502e5f7f699ca5e54865b580416c62d2682fa8b568a42
3
+ size 117440512
params_shard_51.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b9d256114a884e8c3475886ee9b51402aa25448b7dab5b6ce3266e425c57a79
3
+ size 234881024