Hugging Face's logo

steve-z-wang
/
llama3-8b-adapter

Text Classification
Safetensors
English
llama
arxiv
Model card Files Community
steve-z-wang commited on
Commit
8380be9
·
verified ·
1 Parent(s): ee0314c

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. README.md +5 -0
  2. config.json +335 -0
  3. model-00001-of-00007.safetensors +3 -0
  4. model-00002-of-00007.safetensors +3 -0
  5. model-00003-of-00007.safetensors +3 -0
  6. model-00004-of-00007.safetensors +3 -0
  7. model-00005-of-00007.safetensors +3 -0
  8. model-00006-of-00007.safetensors +3 -0
  9. model-00007-of-00007.safetensors +3 -0
  10. model.safetensors.index.json +298 -0
README.md CHANGED
@@ -1,7 +1,12 @@
1
  ---
 
2
  tags:
3
  - text-classification
 
 
4
  pipeline_tag: text-classification
 
5
  ---
6
  # Llama 3 ArXiv Classifier
 
7
  This model is fine-tuned for multi-label classification of arXiv papers.
 
1
  ---
2
+ language: en
3
  tags:
4
  - text-classification
5
+ - llama
6
+ - arxiv
7
  pipeline_tag: text-classification
8
+ inference: true
9
  ---
10
  # Llama 3 ArXiv Classifier
11
+
12
  This model is fine-tuned for multi-label classification of arXiv papers.
config.json ADDED
@@ -0,0 +1,335 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Meta-Llama-3-8B",
3
+ "architectures": [
4
+ "LlamaForSequenceClassification"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10",
25
+ "11": "LABEL_11",
26
+ "12": "LABEL_12",
27
+ "13": "LABEL_13",
28
+ "14": "LABEL_14",
29
+ "15": "LABEL_15",
30
+ "16": "LABEL_16",
31
+ "17": "LABEL_17",
32
+ "18": "LABEL_18",
33
+ "19": "LABEL_19",
34
+ "20": "LABEL_20",
35
+ "21": "LABEL_21",
36
+ "22": "LABEL_22",
37
+ "23": "LABEL_23",
38
+ "24": "LABEL_24",
39
+ "25": "LABEL_25",
40
+ "26": "LABEL_26",
41
+ "27": "LABEL_27",
42
+ "28": "LABEL_28",
43
+ "29": "LABEL_29",
44
+ "30": "LABEL_30",
45
+ "31": "LABEL_31",
46
+ "32": "LABEL_32",
47
+ "33": "LABEL_33",
48
+ "34": "LABEL_34",
49
+ "35": "LABEL_35",
50
+ "36": "LABEL_36",
51
+ "37": "LABEL_37",
52
+ "38": "LABEL_38",
53
+ "39": "LABEL_39",
54
+ "40": "LABEL_40",
55
+ "41": "LABEL_41",
56
+ "42": "LABEL_42",
57
+ "43": "LABEL_43",
58
+ "44": "LABEL_44",
59
+ "45": "LABEL_45",
60
+ "46": "LABEL_46",
61
+ "47": "LABEL_47",
62
+ "48": "LABEL_48",
63
+ "49": "LABEL_49",
64
+ "50": "LABEL_50",
65
+ "51": "LABEL_51",
66
+ "52": "LABEL_52",
67
+ "53": "LABEL_53",
68
+ "54": "LABEL_54",
69
+ "55": "LABEL_55",
70
+ "56": "LABEL_56",
71
+ "57": "LABEL_57",
72
+ "58": "LABEL_58",
73
+ "59": "LABEL_59",
74
+ "60": "LABEL_60",
75
+ "61": "LABEL_61",
76
+ "62": "LABEL_62",
77
+ "63": "LABEL_63",
78
+ "64": "LABEL_64",
79
+ "65": "LABEL_65",
80
+ "66": "LABEL_66",
81
+ "67": "LABEL_67",
82
+ "68": "LABEL_68",
83
+ "69": "LABEL_69",
84
+ "70": "LABEL_70",
85
+ "71": "LABEL_71",
86
+ "72": "LABEL_72",
87
+ "73": "LABEL_73",
88
+ "74": "LABEL_74",
89
+ "75": "LABEL_75",
90
+ "76": "LABEL_76",
91
+ "77": "LABEL_77",
92
+ "78": "LABEL_78",
93
+ "79": "LABEL_79",
94
+ "80": "LABEL_80",
95
+ "81": "LABEL_81",
96
+ "82": "LABEL_82",
97
+ "83": "LABEL_83",
98
+ "84": "LABEL_84",
99
+ "85": "LABEL_85",
100
+ "86": "LABEL_86",
101
+ "87": "LABEL_87",
102
+ "88": "LABEL_88",
103
+ "89": "LABEL_89",
104
+ "90": "LABEL_90",
105
+ "91": "LABEL_91",
106
+ "92": "LABEL_92",
107
+ "93": "LABEL_93",
108
+ "94": "LABEL_94",
109
+ "95": "LABEL_95",
110
+ "96": "LABEL_96",
111
+ "97": "LABEL_97",
112
+ "98": "LABEL_98",
113
+ "99": "LABEL_99",
114
+ "100": "LABEL_100",
115
+ "101": "LABEL_101",
116
+ "102": "LABEL_102",
117
+ "103": "LABEL_103",
118
+ "104": "LABEL_104",
119
+ "105": "LABEL_105",
120
+ "106": "LABEL_106",
121
+ "107": "LABEL_107",
122
+ "108": "LABEL_108",
123
+ "109": "LABEL_109",
124
+ "110": "LABEL_110",
125
+ "111": "LABEL_111",
126
+ "112": "LABEL_112",
127
+ "113": "LABEL_113",
128
+ "114": "LABEL_114",
129
+ "115": "LABEL_115",
130
+ "116": "LABEL_116",
131
+ "117": "LABEL_117",
132
+ "118": "LABEL_118",
133
+ "119": "LABEL_119",
134
+ "120": "LABEL_120",
135
+ "121": "LABEL_121",
136
+ "122": "LABEL_122",
137
+ "123": "LABEL_123",
138
+ "124": "LABEL_124",
139
+ "125": "LABEL_125",
140
+ "126": "LABEL_126",
141
+ "127": "LABEL_127",
142
+ "128": "LABEL_128",
143
+ "129": "LABEL_129",
144
+ "130": "LABEL_130",
145
+ "131": "LABEL_131",
146
+ "132": "LABEL_132",
147
+ "133": "LABEL_133",
148
+ "134": "LABEL_134",
149
+ "135": "LABEL_135",
150
+ "136": "LABEL_136",
151
+ "137": "LABEL_137",
152
+ "138": "LABEL_138",
153
+ "139": "LABEL_139",
154
+ "140": "LABEL_140",
155
+ "141": "LABEL_141",
156
+ "142": "LABEL_142",
157
+ "143": "LABEL_143",
158
+ "144": "LABEL_144",
159
+ "145": "LABEL_145",
160
+ "146": "LABEL_146",
161
+ "147": "LABEL_147",
162
+ "148": "LABEL_148",
163
+ "149": "LABEL_149"
164
+ },
165
+ "initializer_range": 0.02,
166
+ "intermediate_size": 14336,
167
+ "label2id": {
168
+ "LABEL_0": 0,
169
+ "LABEL_1": 1,
170
+ "LABEL_10": 10,
171
+ "LABEL_100": 100,
172
+ "LABEL_101": 101,
173
+ "LABEL_102": 102,
174
+ "LABEL_103": 103,
175
+ "LABEL_104": 104,
176
+ "LABEL_105": 105,
177
+ "LABEL_106": 106,
178
+ "LABEL_107": 107,
179
+ "LABEL_108": 108,
180
+ "LABEL_109": 109,
181
+ "LABEL_11": 11,
182
+ "LABEL_110": 110,
183
+ "LABEL_111": 111,
184
+ "LABEL_112": 112,
185
+ "LABEL_113": 113,
186
+ "LABEL_114": 114,
187
+ "LABEL_115": 115,
188
+ "LABEL_116": 116,
189
+ "LABEL_117": 117,
190
+ "LABEL_118": 118,
191
+ "LABEL_119": 119,
192
+ "LABEL_12": 12,
193
+ "LABEL_120": 120,
194
+ "LABEL_121": 121,
195
+ "LABEL_122": 122,
196
+ "LABEL_123": 123,
197
+ "LABEL_124": 124,
198
+ "LABEL_125": 125,
199
+ "LABEL_126": 126,
200
+ "LABEL_127": 127,
201
+ "LABEL_128": 128,
202
+ "LABEL_129": 129,
203
+ "LABEL_13": 13,
204
+ "LABEL_130": 130,
205
+ "LABEL_131": 131,
206
+ "LABEL_132": 132,
207
+ "LABEL_133": 133,
208
+ "LABEL_134": 134,
209
+ "LABEL_135": 135,
210
+ "LABEL_136": 136,
211
+ "LABEL_137": 137,
212
+ "LABEL_138": 138,
213
+ "LABEL_139": 139,
214
+ "LABEL_14": 14,
215
+ "LABEL_140": 140,
216
+ "LABEL_141": 141,
217
+ "LABEL_142": 142,
218
+ "LABEL_143": 143,
219
+ "LABEL_144": 144,
220
+ "LABEL_145": 145,
221
+ "LABEL_146": 146,
222
+ "LABEL_147": 147,
223
+ "LABEL_148": 148,
224
+ "LABEL_149": 149,
225
+ "LABEL_15": 15,
226
+ "LABEL_16": 16,
227
+ "LABEL_17": 17,
228
+ "LABEL_18": 18,
229
+ "LABEL_19": 19,
230
+ "LABEL_2": 2,
231
+ "LABEL_20": 20,
232
+ "LABEL_21": 21,
233
+ "LABEL_22": 22,
234
+ "LABEL_23": 23,
235
+ "LABEL_24": 24,
236
+ "LABEL_25": 25,
237
+ "LABEL_26": 26,
238
+ "LABEL_27": 27,
239
+ "LABEL_28": 28,
240
+ "LABEL_29": 29,
241
+ "LABEL_3": 3,
242
+ "LABEL_30": 30,
243
+ "LABEL_31": 31,
244
+ "LABEL_32": 32,
245
+ "LABEL_33": 33,
246
+ "LABEL_34": 34,
247
+ "LABEL_35": 35,
248
+ "LABEL_36": 36,
249
+ "LABEL_37": 37,
250
+ "LABEL_38": 38,
251
+ "LABEL_39": 39,
252
+ "LABEL_4": 4,
253
+ "LABEL_40": 40,
254
+ "LABEL_41": 41,
255
+ "LABEL_42": 42,
256
+ "LABEL_43": 43,
257
+ "LABEL_44": 44,
258
+ "LABEL_45": 45,
259
+ "LABEL_46": 46,
260
+ "LABEL_47": 47,
261
+ "LABEL_48": 48,
262
+ "LABEL_49": 49,
263
+ "LABEL_5": 5,
264
+ "LABEL_50": 50,
265
+ "LABEL_51": 51,
266
+ "LABEL_52": 52,
267
+ "LABEL_53": 53,
268
+ "LABEL_54": 54,
269
+ "LABEL_55": 55,
270
+ "LABEL_56": 56,
271
+ "LABEL_57": 57,
272
+ "LABEL_58": 58,
273
+ "LABEL_59": 59,
274
+ "LABEL_6": 6,
275
+ "LABEL_60": 60,
276
+ "LABEL_61": 61,
277
+ "LABEL_62": 62,
278
+ "LABEL_63": 63,
279
+ "LABEL_64": 64,
280
+ "LABEL_65": 65,
281
+ "LABEL_66": 66,
282
+ "LABEL_67": 67,
283
+ "LABEL_68": 68,
284
+ "LABEL_69": 69,
285
+ "LABEL_7": 7,
286
+ "LABEL_70": 70,
287
+ "LABEL_71": 71,
288
+ "LABEL_72": 72,
289
+ "LABEL_73": 73,
290
+ "LABEL_74": 74,
291
+ "LABEL_75": 75,
292
+ "LABEL_76": 76,
293
+ "LABEL_77": 77,
294
+ "LABEL_78": 78,
295
+ "LABEL_79": 79,
296
+ "LABEL_8": 8,
297
+ "LABEL_80": 80,
298
+ "LABEL_81": 81,
299
+ "LABEL_82": 82,
300
+ "LABEL_83": 83,
301
+ "LABEL_84": 84,
302
+ "LABEL_85": 85,
303
+ "LABEL_86": 86,
304
+ "LABEL_87": 87,
305
+ "LABEL_88": 88,
306
+ "LABEL_89": 89,
307
+ "LABEL_9": 9,
308
+ "LABEL_90": 90,
309
+ "LABEL_91": 91,
310
+ "LABEL_92": 92,
311
+ "LABEL_93": 93,
312
+ "LABEL_94": 94,
313
+ "LABEL_95": 95,
314
+ "LABEL_96": 96,
315
+ "LABEL_97": 97,
316
+ "LABEL_98": 98,
317
+ "LABEL_99": 99
318
+ },
319
+ "max_position_embeddings": 8192,
320
+ "mlp_bias": false,
321
+ "model_type": "llama",
322
+ "num_attention_heads": 32,
323
+ "num_hidden_layers": 32,
324
+ "num_key_value_heads": 8,
325
+ "pretraining_tp": 1,
326
+ "problem_type": "multi_label_classification",
327
+ "rms_norm_eps": 1e-05,
328
+ "rope_scaling": null,
329
+ "rope_theta": 500000.0,
330
+ "tie_word_embeddings": false,
331
+ "torch_dtype": "float32",
332
+ "transformers_version": "4.45.2",
333
+ "use_cache": true,
334
+ "vocab_size": 128256
335
+ }
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc0c87aec6d44d53343a3ccc6854c2388f890fc281573bb285fb5af54eac0fa4
3
+ size 4886466168
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd17c22fbbef242ebfa4fb3bb405f9679838c6c70675ac26963b2b87c800ab1d
3
+ size 4832007448
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49e8a798a452b77741a8b49bd89e665b1f91eafa55a7d0e94bbe234eeb8c6d0a
3
+ size 4999813112
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94ba13d2e26a80449ec45ba131395f0bb8473a7d6c200aaa8c63ea5a0566669b
3
+ size 4999813128
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58e18774e145665c7d6d990381e2758bcd76d7ad442e734975b517bb7c4087ec
3
+ size 4832007496
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28039300f31afe2f906334ca88d2f9d9b10b19809cfbaa5829ebdb70b75d93d5
3
+ size 4999813120
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3cc35341f472b086c8781edfd2f437dac42166524c37c243fff79fa427576da
3
+ size 472269456
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 30022156288
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
97
+ "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
98
+ "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
99
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
100
+ "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
101
+ "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
102
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
103
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
104
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
105
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
106
+ "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
107
+ "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
108
+ "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
109
+ "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
110
+ "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
111
+ "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
112
+ "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
113
+ "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
114
+ "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
115
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
116
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
117
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
118
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
119
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
120
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
121
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
122
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
123
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
124
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
125
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
126
+ "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
127
+ "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
128
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
129
+ "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
130
+ "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
131
+ "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
132
+ "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
133
+ "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
134
+ "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
135
+ "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
136
+ "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
137
+ "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
138
+ "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
139
+ "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
140
+ "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
141
+ "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
142
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
143
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
144
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
145
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
146
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
147
+ "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
148
+ "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
149
+ "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
150
+ "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
151
+ "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
152
+ "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
153
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
154
+ "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
155
+ "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
156
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
157
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
158
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
159
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
160
+ "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
161
+ "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
162
+ "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
163
+ "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
164
+ "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
165
+ "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
166
+ "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
167
+ "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
168
+ "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
169
+ "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
170
+ "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
171
+ "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
172
+ "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
173
+ "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
174
+ "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
175
+ "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
176
+ "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
177
+ "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
178
+ "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
179
+ "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
180
+ "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
181
+ "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
182
+ "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
183
+ "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
184
+ "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
185
+ "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
186
+ "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
187
+ "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
188
+ "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
189
+ "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
190
+ "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
191
+ "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
192
+ "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
193
+ "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
194
+ "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
195
+ "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
196
+ "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
197
+ "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
198
+ "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
199
+ "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
200
+ "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
201
+ "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
202
+ "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
203
+ "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
204
+ "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
205
+ "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
206
+ "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
207
+ "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
208
+ "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
209
+ "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
210
+ "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
211
+ "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
212
+ "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
213
+ "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
214
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
215
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
216
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
217
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
218
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
219
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
220
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
221
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
222
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
223
+ "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
224
+ "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
225
+ "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
226
+ "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
227
+ "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
228
+ "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
229
+ "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
230
+ "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
231
+ "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
232
+ "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
233
+ "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
234
+ "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
235
+ "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
236
+ "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
237
+ "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
238
+ "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
239
+ "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
240
+ "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
241
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
242
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
243
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
244
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
245
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
246
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
247
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
248
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
249
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
250
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
251
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
252
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
253
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
254
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
255
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
256
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
257
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
258
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
259
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
260
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
261
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
262
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
263
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
264
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
265
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
266
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
267
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
268
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
269
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
270
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
271
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
272
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
273
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
274
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
275
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
276
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
277
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
278
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
279
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
280
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
281
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
282
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
283
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
284
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
285
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
286
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
287
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
288
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
289
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
290
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
291
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
292
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
293
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
294
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
295
+ "model.norm.weight": "model-00007-of-00007.safetensors",
296
+ "score.weight": "model-00007-of-00007.safetensors"
297
+ }
298
+ }