Hugging Face's logo

DistillationDiffusion
/
ModelFineTunedCheckpointsReal

Safetensors
Model card Files
xet
 Community
DrewPhi commited on
Commit
4460549
·
verified ·
1 Parent(s): ba151ca

Upload teacher checkpoint qwen1p5b

Browse files
Files changed (13) hide show
  1. .gitattributes +1 -0
  2. teacher_checkpoints/clinc_fine/qwen1p5b/added_tokens.json +24 -0
  3. teacher_checkpoints/clinc_fine/qwen1p5b/chat_template.jinja +54 -0
  4. teacher_checkpoints/clinc_fine/qwen1p5b/checkpoint_metrics.json +5 -0
  5. teacher_checkpoints/clinc_fine/qwen1p5b/config.json +365 -0
  6. teacher_checkpoints/clinc_fine/qwen1p5b/merges.txt +0 -0
  7. teacher_checkpoints/clinc_fine/qwen1p5b/model-00001-of-00002.safetensors +3 -0
  8. teacher_checkpoints/clinc_fine/qwen1p5b/model-00002-of-00002.safetensors +3 -0
  9. teacher_checkpoints/clinc_fine/qwen1p5b/model.safetensors.index.json +347 -0
  10. teacher_checkpoints/clinc_fine/qwen1p5b/special_tokens_map.json +31 -0
  11. teacher_checkpoints/clinc_fine/qwen1p5b/tokenizer.json +3 -0
  12. teacher_checkpoints/clinc_fine/qwen1p5b/tokenizer_config.json +207 -0
  13. teacher_checkpoints/clinc_fine/qwen1p5b/vocab.json +0 -0
.gitattributes CHANGED
@@ -42,3 +42,4 @@ teacher_checkpoints/clinc_coarse/qwen1p5b/tokenizer.json filter=lfs diff=lfs mer
42
  teacher_checkpoints/clinc_coarse/qwen3b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
  teacher_checkpoints/clinc_coarse/qwen7b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
44
  teacher_checkpoints/clinc_fine/qwen0p5b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
42
  teacher_checkpoints/clinc_coarse/qwen3b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
  teacher_checkpoints/clinc_coarse/qwen7b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
44
  teacher_checkpoints/clinc_fine/qwen0p5b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
45
+ teacher_checkpoints/clinc_fine/qwen1p5b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
teacher_checkpoints/clinc_fine/qwen1p5b/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
teacher_checkpoints/clinc_fine/qwen1p5b/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
teacher_checkpoints/clinc_fine/qwen1p5b/checkpoint_metrics.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "update": 150,
3
+ "heldout_accuracy": 0.91,
4
+ "heldout_loss": 0.43289546731937056
5
+ }
teacher_checkpoints/clinc_fine/qwen1p5b/config.json ADDED
@@ -0,0 +1,365 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForSequenceClassification"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "float32",
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1536,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15",
28
+ "16": "LABEL_16",
29
+ "17": "LABEL_17",
30
+ "18": "LABEL_18",
31
+ "19": "LABEL_19",
32
+ "20": "LABEL_20",
33
+ "21": "LABEL_21",
34
+ "22": "LABEL_22",
35
+ "23": "LABEL_23",
36
+ "24": "LABEL_24",
37
+ "25": "LABEL_25",
38
+ "26": "LABEL_26",
39
+ "27": "LABEL_27",
40
+ "28": "LABEL_28",
41
+ "29": "LABEL_29",
42
+ "30": "LABEL_30",
43
+ "31": "LABEL_31",
44
+ "32": "LABEL_32",
45
+ "33": "LABEL_33",
46
+ "34": "LABEL_34",
47
+ "35": "LABEL_35",
48
+ "36": "LABEL_36",
49
+ "37": "LABEL_37",
50
+ "38": "LABEL_38",
51
+ "39": "LABEL_39",
52
+ "40": "LABEL_40",
53
+ "41": "LABEL_41",
54
+ "42": "LABEL_42",
55
+ "43": "LABEL_43",
56
+ "44": "LABEL_44",
57
+ "45": "LABEL_45",
58
+ "46": "LABEL_46",
59
+ "47": "LABEL_47",
60
+ "48": "LABEL_48",
61
+ "49": "LABEL_49",
62
+ "50": "LABEL_50",
63
+ "51": "LABEL_51",
64
+ "52": "LABEL_52",
65
+ "53": "LABEL_53",
66
+ "54": "LABEL_54",
67
+ "55": "LABEL_55",
68
+ "56": "LABEL_56",
69
+ "57": "LABEL_57",
70
+ "58": "LABEL_58",
71
+ "59": "LABEL_59",
72
+ "60": "LABEL_60",
73
+ "61": "LABEL_61",
74
+ "62": "LABEL_62",
75
+ "63": "LABEL_63",
76
+ "64": "LABEL_64",
77
+ "65": "LABEL_65",
78
+ "66": "LABEL_66",
79
+ "67": "LABEL_67",
80
+ "68": "LABEL_68",
81
+ "69": "LABEL_69",
82
+ "70": "LABEL_70",
83
+ "71": "LABEL_71",
84
+ "72": "LABEL_72",
85
+ "73": "LABEL_73",
86
+ "74": "LABEL_74",
87
+ "75": "LABEL_75",
88
+ "76": "LABEL_76",
89
+ "77": "LABEL_77",
90
+ "78": "LABEL_78",
91
+ "79": "LABEL_79",
92
+ "80": "LABEL_80",
93
+ "81": "LABEL_81",
94
+ "82": "LABEL_82",
95
+ "83": "LABEL_83",
96
+ "84": "LABEL_84",
97
+ "85": "LABEL_85",
98
+ "86": "LABEL_86",
99
+ "87": "LABEL_87",
100
+ "88": "LABEL_88",
101
+ "89": "LABEL_89",
102
+ "90": "LABEL_90",
103
+ "91": "LABEL_91",
104
+ "92": "LABEL_92",
105
+ "93": "LABEL_93",
106
+ "94": "LABEL_94",
107
+ "95": "LABEL_95",
108
+ "96": "LABEL_96",
109
+ "97": "LABEL_97",
110
+ "98": "LABEL_98",
111
+ "99": "LABEL_99",
112
+ "100": "LABEL_100",
113
+ "101": "LABEL_101",
114
+ "102": "LABEL_102",
115
+ "103": "LABEL_103",
116
+ "104": "LABEL_104",
117
+ "105": "LABEL_105",
118
+ "106": "LABEL_106",
119
+ "107": "LABEL_107",
120
+ "108": "LABEL_108",
121
+ "109": "LABEL_109",
122
+ "110": "LABEL_110",
123
+ "111": "LABEL_111",
124
+ "112": "LABEL_112",
125
+ "113": "LABEL_113",
126
+ "114": "LABEL_114",
127
+ "115": "LABEL_115",
128
+ "116": "LABEL_116",
129
+ "117": "LABEL_117",
130
+ "118": "LABEL_118",
131
+ "119": "LABEL_119",
132
+ "120": "LABEL_120",
133
+ "121": "LABEL_121",
134
+ "122": "LABEL_122",
135
+ "123": "LABEL_123",
136
+ "124": "LABEL_124",
137
+ "125": "LABEL_125",
138
+ "126": "LABEL_126",
139
+ "127": "LABEL_127",
140
+ "128": "LABEL_128",
141
+ "129": "LABEL_129",
142
+ "130": "LABEL_130",
143
+ "131": "LABEL_131",
144
+ "132": "LABEL_132",
145
+ "133": "LABEL_133",
146
+ "134": "LABEL_134",
147
+ "135": "LABEL_135",
148
+ "136": "LABEL_136",
149
+ "137": "LABEL_137",
150
+ "138": "LABEL_138",
151
+ "139": "LABEL_139",
152
+ "140": "LABEL_140",
153
+ "141": "LABEL_141",
154
+ "142": "LABEL_142",
155
+ "143": "LABEL_143",
156
+ "144": "LABEL_144",
157
+ "145": "LABEL_145",
158
+ "146": "LABEL_146",
159
+ "147": "LABEL_147",
160
+ "148": "LABEL_148",
161
+ "149": "LABEL_149"
162
+ },
163
+ "initializer_range": 0.02,
164
+ "intermediate_size": 8960,
165
+ "label2id": {
166
+ "LABEL_0": 0,
167
+ "LABEL_1": 1,
168
+ "LABEL_10": 10,
169
+ "LABEL_100": 100,
170
+ "LABEL_101": 101,
171
+ "LABEL_102": 102,
172
+ "LABEL_103": 103,
173
+ "LABEL_104": 104,
174
+ "LABEL_105": 105,
175
+ "LABEL_106": 106,
176
+ "LABEL_107": 107,
177
+ "LABEL_108": 108,
178
+ "LABEL_109": 109,
179
+ "LABEL_11": 11,
180
+ "LABEL_110": 110,
181
+ "LABEL_111": 111,
182
+ "LABEL_112": 112,
183
+ "LABEL_113": 113,
184
+ "LABEL_114": 114,
185
+ "LABEL_115": 115,
186
+ "LABEL_116": 116,
187
+ "LABEL_117": 117,
188
+ "LABEL_118": 118,
189
+ "LABEL_119": 119,
190
+ "LABEL_12": 12,
191
+ "LABEL_120": 120,
192
+ "LABEL_121": 121,
193
+ "LABEL_122": 122,
194
+ "LABEL_123": 123,
195
+ "LABEL_124": 124,
196
+ "LABEL_125": 125,
197
+ "LABEL_126": 126,
198
+ "LABEL_127": 127,
199
+ "LABEL_128": 128,
200
+ "LABEL_129": 129,
201
+ "LABEL_13": 13,
202
+ "LABEL_130": 130,
203
+ "LABEL_131": 131,
204
+ "LABEL_132": 132,
205
+ "LABEL_133": 133,
206
+ "LABEL_134": 134,
207
+ "LABEL_135": 135,
208
+ "LABEL_136": 136,
209
+ "LABEL_137": 137,
210
+ "LABEL_138": 138,
211
+ "LABEL_139": 139,
212
+ "LABEL_14": 14,
213
+ "LABEL_140": 140,
214
+ "LABEL_141": 141,
215
+ "LABEL_142": 142,
216
+ "LABEL_143": 143,
217
+ "LABEL_144": 144,
218
+ "LABEL_145": 145,
219
+ "LABEL_146": 146,
220
+ "LABEL_147": 147,
221
+ "LABEL_148": 148,
222
+ "LABEL_149": 149,
223
+ "LABEL_15": 15,
224
+ "LABEL_16": 16,
225
+ "LABEL_17": 17,
226
+ "LABEL_18": 18,
227
+ "LABEL_19": 19,
228
+ "LABEL_2": 2,
229
+ "LABEL_20": 20,
230
+ "LABEL_21": 21,
231
+ "LABEL_22": 22,
232
+ "LABEL_23": 23,
233
+ "LABEL_24": 24,
234
+ "LABEL_25": 25,
235
+ "LABEL_26": 26,
236
+ "LABEL_27": 27,
237
+ "LABEL_28": 28,
238
+ "LABEL_29": 29,
239
+ "LABEL_3": 3,
240
+ "LABEL_30": 30,
241
+ "LABEL_31": 31,
242
+ "LABEL_32": 32,
243
+ "LABEL_33": 33,
244
+ "LABEL_34": 34,
245
+ "LABEL_35": 35,
246
+ "LABEL_36": 36,
247
+ "LABEL_37": 37,
248
+ "LABEL_38": 38,
249
+ "LABEL_39": 39,
250
+ "LABEL_4": 4,
251
+ "LABEL_40": 40,
252
+ "LABEL_41": 41,
253
+ "LABEL_42": 42,
254
+ "LABEL_43": 43,
255
+ "LABEL_44": 44,
256
+ "LABEL_45": 45,
257
+ "LABEL_46": 46,
258
+ "LABEL_47": 47,
259
+ "LABEL_48": 48,
260
+ "LABEL_49": 49,
261
+ "LABEL_5": 5,
262
+ "LABEL_50": 50,
263
+ "LABEL_51": 51,
264
+ "LABEL_52": 52,
265
+ "LABEL_53": 53,
266
+ "LABEL_54": 54,
267
+ "LABEL_55": 55,
268
+ "LABEL_56": 56,
269
+ "LABEL_57": 57,
270
+ "LABEL_58": 58,
271
+ "LABEL_59": 59,
272
+ "LABEL_6": 6,
273
+ "LABEL_60": 60,
274
+ "LABEL_61": 61,
275
+ "LABEL_62": 62,
276
+ "LABEL_63": 63,
277
+ "LABEL_64": 64,
278
+ "LABEL_65": 65,
279
+ "LABEL_66": 66,
280
+ "LABEL_67": 67,
281
+ "LABEL_68": 68,
282
+ "LABEL_69": 69,
283
+ "LABEL_7": 7,
284
+ "LABEL_70": 70,
285
+ "LABEL_71": 71,
286
+ "LABEL_72": 72,
287
+ "LABEL_73": 73,
288
+ "LABEL_74": 74,
289
+ "LABEL_75": 75,
290
+ "LABEL_76": 76,
291
+ "LABEL_77": 77,
292
+ "LABEL_78": 78,
293
+ "LABEL_79": 79,
294
+ "LABEL_8": 8,
295
+ "LABEL_80": 80,
296
+ "LABEL_81": 81,
297
+ "LABEL_82": 82,
298
+ "LABEL_83": 83,
299
+ "LABEL_84": 84,
300
+ "LABEL_85": 85,
301
+ "LABEL_86": 86,
302
+ "LABEL_87": 87,
303
+ "LABEL_88": 88,
304
+ "LABEL_89": 89,
305
+ "LABEL_9": 9,
306
+ "LABEL_90": 90,
307
+ "LABEL_91": 91,
308
+ "LABEL_92": 92,
309
+ "LABEL_93": 93,
310
+ "LABEL_94": 94,
311
+ "LABEL_95": 95,
312
+ "LABEL_96": 96,
313
+ "LABEL_97": 97,
314
+ "LABEL_98": 98,
315
+ "LABEL_99": 99
316
+ },
317
+ "layer_types": [
318
+ "full_attention",
319
+ "full_attention",
320
+ "full_attention",
321
+ "full_attention",
322
+ "full_attention",
323
+ "full_attention",
324
+ "full_attention",
325
+ "full_attention",
326
+ "full_attention",
327
+ "full_attention",
328
+ "full_attention",
329
+ "full_attention",
330
+ "full_attention",
331
+ "full_attention",
332
+ "full_attention",
333
+ "full_attention",
334
+ "full_attention",
335
+ "full_attention",
336
+ "full_attention",
337
+ "full_attention",
338
+ "full_attention",
339
+ "full_attention",
340
+ "full_attention",
341
+ "full_attention",
342
+ "full_attention",
343
+ "full_attention",
344
+ "full_attention",
345
+ "full_attention"
346
+ ],
347
+ "max_position_embeddings": 131072,
348
+ "max_window_layers": 28,
349
+ "model_type": "qwen2",
350
+ "num_attention_heads": 12,
351
+ "num_hidden_layers": 28,
352
+ "num_key_value_heads": 2,
353
+ "pad_token_id": 151643,
354
+ "problem_type": "single_label_classification",
355
+ "rms_norm_eps": 1e-06,
356
+ "rope_scaling": null,
357
+ "rope_theta": 1000000.0,
358
+ "sliding_window": null,
359
+ "tie_word_embeddings": true,
360
+ "transformers_version": "4.57.6",
361
+ "use_cache": false,
362
+ "use_mrope": false,
363
+ "use_sliding_window": false,
364
+ "vocab_size": 151936
365
+ }
teacher_checkpoints/clinc_fine/qwen1p5b/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
teacher_checkpoints/clinc_fine/qwen1p5b/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2af00e7702c6af1aefbad0ca9d8bf92d1b93f7b18802a0f2c752bda378650a0c
3
+ size 4996670464
teacher_checkpoints/clinc_fine/qwen1p5b/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:555d3e86f990b6148decc928f0c76b5fbe277580339fe0abb0e3d9f15c9abf8a
3
+ size 1179146656
teacher_checkpoints/clinc_fine/qwen1p5b/model.safetensors.index.json ADDED
@@ -0,0 +1,347 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 1543944704,
4
+ "total_size": 6175778816
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
260
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
262
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
266
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
269
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
274
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
276
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
278
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
279
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
280
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
281
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
282
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
283
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
284
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
290
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
293
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
294
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
295
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
296
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
297
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
298
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
299
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
300
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
301
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
302
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
303
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
304
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
305
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
306
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
307
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
308
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
309
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
310
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
311
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
312
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
313
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
314
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
315
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
316
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
317
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
318
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
319
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
320
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
321
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
322
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
323
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
324
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
325
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
326
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
327
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
328
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
329
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
330
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
331
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
332
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
333
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
334
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
335
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
336
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
337
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
338
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
339
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
340
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
341
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
342
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
343
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
344
+ "model.norm.weight": "model-00002-of-00002.safetensors",
345
+ "score.weight": "model-00002-of-00002.safetensors"
346
+ }
347
+ }
teacher_checkpoints/clinc_fine/qwen1p5b/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
teacher_checkpoints/clinc_fine/qwen1p5b/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:540b7fbf60b80e8293593a86960df91d2263723d69107ffc1afc89a7c08cda12
3
+ size 11422162
teacher_checkpoints/clinc_fine/qwen1p5b/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|endoftext|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
teacher_checkpoints/clinc_fine/qwen1p5b/vocab.json ADDED
The diff for this file is too large to render. See raw diff