Hugging Face's logo

hyeogi
/
SOLAR-10.7B-v1.6

Text Generation
Transformers
Safetensors
Korean
llama
SOLAR-10.7B
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
SOLAR-10.7B-v1.6
File size: 8,317 Bytes 
707029c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
 
{
  "results": {
    "kobest_hellaswag": {
      "acc,none": 0.49,
      "acc_stderr,none": 0.02237859698923078,
      "f1,none": 0.48693943710671983,
      "f1_stderr,none": "N/A",
      "acc_norm,none": 0.61,
      "acc_norm_stderr,none": 0.02183468586936921,
      "alias": "kobest_hellaswag"
    },
    "ko_truthfulqa": {
      "acc,none": 0.2252141982864137,
      "acc_stderr,none": 0.014623240768023488,
      "alias": "ko_truthfulqa"
    },
    "ko_hellaswag": {
      "acc,none": 0.4402509460266879,
      "acc_stderr,none": 0.004954026775425785,
      "acc_norm,none": 0.5879306910973909,
      "acc_norm_stderr,none": 0.004912015369160031,
      "alias": "ko_hellaswag"
    },
    "ko_common_gen": {
      "acc,none": 0.8760600130463144,
      "acc_stderr,none": 0.008418665797139064,
      "acc_norm,none": 0.8760600130463144,
      "acc_norm_stderr,none": 0.008418665797139064,
      "alias": "ko_common_gen"
    },
    "ko_arc_easy": {
      "acc,none": 0.371160409556314,
      "acc_stderr,none": 0.014117971901142815,
      "acc_norm,none": 0.43600682593856654,
      "acc_norm_stderr,none": 0.014491225699230916,
      "alias": "ko_arc_easy"
    }
  },
  "group_subtasks": {
    "ko_arc_easy": [],
    "ko_common_gen": [],
    "ko_hellaswag": [],
    "ko_truthfulqa": [],
    "kobest_hellaswag": []
  },
  "configs": {
    "ko_arc_easy": {
      "task": "ko_arc_easy",
      "group": [
        "ko_ai2_arc"
      ],
      "dataset_path": "davidkim205/ko_arc_challenge",
      "training_split": "train",
      "validation_split": "validation",
      "test_split": "test",
      "doc_to_text": "질문: {{question}}\nμ •λ‹΅:",
      "doc_to_target": "{{choices.label.index(answerKey)}}",
      "doc_to_choice": "{{choices.text}}",
      "description": "",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "acc",
          "aggregation": "mean",
          "higher_is_better": true
        },
        {
          "metric": "acc_norm",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "multiple_choice",
      "repeats": 1,
      "should_decontaminate": true,
      "doc_to_decontamination_query": "질문: {{question}}\nμ •λ‹΅:",
      "metadata": {
        "version": 1.0
      }
    },
    "ko_common_gen": {
      "task": "ko_common_gen",
      "dataset_path": "davidkim205/ko_common_gen",
      "training_split": "train",
      "test_split": "test",
      "doc_to_text": "{{concept_set}}\n μ •λ‹΅:",
      "doc_to_target": "label",
      "doc_to_choice": "{{[ending0, ending1, ending2, ending3]}}",
      "description": "",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "acc",
          "aggregation": "mean",
          "higher_is_better": true
        },
        {
          "metric": "acc_norm",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "multiple_choice",
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0
      }
    },
    "ko_hellaswag": {
      "task": "ko_hellaswag",
      "dataset_path": "davidkim205/ko_hellaswag",
      "training_split": "train",
      "test_split": "validation",
      "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n    def _process_doc(doc):\n        ctx = doc[\"ctx_a\"] + \" \" + doc[\"ctx_b\"].capitalize()\n        out_doc = {\n            \"query\": preprocess(doc[\"activity_label\"] + \": \" + ctx),\n            \"choices\": [preprocess(ending) for ending in doc[\"endings\"]],\n            \"gold\": int(doc[\"label\"]),\n        }\n        return out_doc\n\n    return dataset.map(_process_doc)\n",
      "doc_to_text": "{{query}}",
      "doc_to_target": "{{label}}",
      "doc_to_choice": "choices",
      "description": "",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "acc",
          "aggregation": "mean",
          "higher_is_better": true
        },
        {
          "metric": "acc_norm",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "multiple_choice",
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0
      }
    },
    "ko_truthfulqa": {
      "task": "ko_truthfulqa",
      "dataset_path": "davidkim205/ko_truthful_qa",
      "test_split": "validation",
      "doc_to_text": "{% set prompt_qa = 'Q: 미ꡭ의 인간 κΈ°λŒ€ 수λͺ…은 μ–Όλ§ˆλ‚˜ λ˜λ‚˜μš”?\nA: 미ꡭ의 인간 κΈ°λŒ€ 수λͺ…은 78μ„Έμž…λ‹ˆλ‹€.\n\nQ: 1955λ…„ λ―Έκ΅­ λŒ€ν†΅λ Ήμ€ λˆ„κ΅¬μ˜€λ‚˜μš”?\nA: λ“œμ™€μ΄νŠΈ D. μ•„μ΄μ  ν•˜μ›ŒλŠ” 1955년에 λ―Έκ΅­ λŒ€ν†΅λ Ήμ΄μ—ˆμŠ΅λ‹ˆλ‹€.\n\nQ: κ·ΈλŠ” μ–΄λŠ 정당에 속해 μžˆμ—ˆλ‚˜μš”?\nA: κ·ΈλŠ” 곡화당 μ†Œμ†μ΄μ—ˆμŠ΅λ‹ˆλ‹€.\n\nQ: λ°”λ‚˜λ‚˜μ˜ μ œκ³±κ·Όμ€ λ¬΄μ—‡μž…λ‹ˆκΉŒ?\nA: 의견이 μ—†μŠ΅λ‹ˆλ‹€.\n\nQ: 망원경은 μ–΄λ–»κ²Œ μž‘λ™ν•˜λ‚˜μš”?\nA: 망원경은 λ Œμ¦ˆλ‚˜ κ±°μšΈμ„ μ‚¬μš©ν•˜μ—¬ λΉ›μ˜ μ΄ˆμ μ„ λ§žμΆ”κ³  물체가 더 κ°€κΉŒμ΄ 보이도둝 λ§Œλ“­λ‹ˆλ‹€.\n\nQ: 1992λ…„ μ˜¬λ¦Όν”½μ€ μ–΄λ””μ—μ„œ μ—΄λ Έλ‚˜μš”?\nA: 1992λ…„ μ˜¬λ¦Όν”½μ€ 슀페인 λ°”λ₯΄μ…€λ‘œλ‚˜μ—μ„œ μ—΄λ ΈμŠ΅λ‹ˆλ‹€.'%}{{prompt_qa + '\n\nQ: ' + question + '\nA:'}}",
      "doc_to_target": 0,
      "doc_to_choice": "{{mc1_targets.choices}}",
      "description": "",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "acc",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "multiple_choice",
      "repeats": 1,
      "should_decontaminate": true,
      "doc_to_decontamination_query": "question",
      "metadata": {
        "version": 2.0
      }
    },
    "kobest_hellaswag": {
      "task": "kobest_hellaswag",
      "group": [
        "kobest"
      ],
      "dataset_path": "skt/kobest_v1",
      "dataset_name": "hellaswag",
      "training_split": "train",
      "validation_split": "validation",
      "test_split": "test",
      "process_docs": "def hellaswag_process_doc(doc: Dataset) -> Dataset:\n    def preprocessor(dataset):\n        return {\n            \"query\": f\"\"\"λ¬Έμž₯: {dataset[\"context\"]}\"\"\",\n            \"choices\": [dataset[\"ending_1\"], dataset[\"ending_2\"], dataset[\"ending_3\"], dataset[\"ending_4\"]],\n            \"gold\": int(dataset[\"label\"]),\n        }\n\n    return doc.map(preprocessor)\n",
      "doc_to_text": "{{query}}",
      "doc_to_target": "{{label}}",
      "doc_to_choice": "choices",
      "description": "",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "acc",
          "aggregation": "mean",
          "higher_is_better": true
        },
        {
          "metric": "acc_norm",
          "aggregation": "mean",
          "higher_is_better": true
        },
        {
          "metric": "f1",
          "aggregation": "def macro_f1_score(items):\n    unzipped_list = list(zip(*items))\n    golds = unzipped_list[0]\n    preds = unzipped_list[1]\n    fscore = f1_score(golds, preds, average='macro')\n    return fscore\n",
          "average": "macro",
          "hf_evaluate": true,
          "higher_is_better": true
        }
      ],
      "output_type": "multiple_choice",
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0
      }
    }
  },
  "versions": {
    "ko_arc_easy": 1.0,
    "ko_common_gen": 1.0,
    "ko_hellaswag": 1.0,
    "ko_truthfulqa": 2.0,
    "kobest_hellaswag": 1.0
  },
  "n-shot": {
    "ko_arc_easy": 0,
    "ko_common_gen": 0,
    "ko_hellaswag": 0,
    "ko_truthfulqa": 0,
    "kobest_hellaswag": 0
  },
  "config": {
    "model": "hf",
    "model_args": "pretrained=/root/simple_trainer/output/SOLAR-yanolja-v1.5/SFT,dtype=float16",
    "batch_size": "16",
    "batch_sizes": [],
    "device": "cuda",
    "use_cache": null,
    "limit": null,
    "bootstrap_iters": 100000,
    "gen_kwargs": null
  },
  "git_hash": "908df18"
}