CoreyMorris
commited on
Commit
•
28fcccf
1
Parent(s):
3ebf7a7
update
Browse files- generate_csv.ipynb +500 -1
generate_csv.ipynb
CHANGED
@@ -22,7 +22,16 @@
|
|
22 |
"1100\n",
|
23 |
"1200\n",
|
24 |
"1300\n",
|
25 |
-
"1400\n"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
]
|
27 |
}
|
28 |
],
|
@@ -31,6 +40,496 @@
|
|
31 |
"result = ResultDataProcessor()"
|
32 |
]
|
33 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
{
|
35 |
"cell_type": "code",
|
36 |
"execution_count": null,
|
|
|
22 |
"1100\n",
|
23 |
"1200\n",
|
24 |
"1300\n",
|
25 |
+
"1400\n",
|
26 |
+
"1500\n",
|
27 |
+
"1600\n",
|
28 |
+
"1700\n",
|
29 |
+
"1800\n",
|
30 |
+
"full_model_names\n",
|
31 |
+
"1889\n",
|
32 |
+
"organization_names\n",
|
33 |
+
"12\n",
|
34 |
+
"['Parameters', 'drop|3', 'gsm8k', 'MMLU_average', 'winogrande', 'all', 'arc:challenge|25', 'hellaswag|10', 'MMLU_abstract_algebra', 'MMLU_anatomy', 'MMLU_astronomy', 'MMLU_business_ethics', 'MMLU_clinical_knowledge', 'MMLU_college_biology', 'MMLU_college_chemistry', 'MMLU_college_computer_science', 'MMLU_college_mathematics', 'MMLU_college_medicine', 'MMLU_college_physics', 'MMLU_computer_security', 'MMLU_conceptual_physics', 'MMLU_econometrics', 'MMLU_electrical_engineering', 'MMLU_elementary_mathematics', 'MMLU_formal_logic', 'MMLU_global_facts', 'MMLU_high_school_biology', 'MMLU_high_school_chemistry', 'MMLU_high_school_computer_science', 'MMLU_high_school_european_history', 'MMLU_high_school_geography', 'MMLU_high_school_government_and_politics', 'MMLU_high_school_macroeconomics', 'MMLU_high_school_mathematics', 'MMLU_high_school_microeconomics', 'MMLU_high_school_physics', 'MMLU_high_school_psychology', 'MMLU_high_school_statistics', 'MMLU_high_school_us_history', 'MMLU_high_school_world_history', 'MMLU_human_aging', 'MMLU_human_sexuality', 'MMLU_international_law', 'MMLU_jurisprudence', 'MMLU_logical_fallacies', 'MMLU_machine_learning', 'MMLU_management', 'MMLU_marketing', 'MMLU_medical_genetics', 'MMLU_miscellaneous', 'MMLU_moral_disputes', 'MMLU_moral_scenarios', 'MMLU_nutrition', 'MMLU_philosophy', 'MMLU_prehistory', 'MMLU_professional_accounting', 'MMLU_professional_law', 'MMLU_professional_medicine', 'MMLU_professional_psychology', 'MMLU_public_relations', 'MMLU_security_studies', 'MMLU_sociology', 'MMLU_us_foreign_policy', 'MMLU_virology', 'MMLU_world_religions', 'truthfulqa:mc|0', 'full_model_name']\n"
|
35 |
]
|
36 |
}
|
37 |
],
|
|
|
40 |
"result = ResultDataProcessor()"
|
41 |
]
|
42 |
},
|
43 |
+
{
|
44 |
+
"cell_type": "code",
|
45 |
+
"execution_count": 2,
|
46 |
+
"metadata": {},
|
47 |
+
"outputs": [
|
48 |
+
{
|
49 |
+
"data": {
|
50 |
+
"text/html": [
|
51 |
+
"<div>\n",
|
52 |
+
"<style scoped>\n",
|
53 |
+
" .dataframe tbody tr th:only-of-type {\n",
|
54 |
+
" vertical-align: middle;\n",
|
55 |
+
" }\n",
|
56 |
+
"\n",
|
57 |
+
" .dataframe tbody tr th {\n",
|
58 |
+
" vertical-align: top;\n",
|
59 |
+
" }\n",
|
60 |
+
"\n",
|
61 |
+
" .dataframe thead th {\n",
|
62 |
+
" text-align: right;\n",
|
63 |
+
" }\n",
|
64 |
+
"</style>\n",
|
65 |
+
"<table border=\"1\" class=\"dataframe\">\n",
|
66 |
+
" <thead>\n",
|
67 |
+
" <tr style=\"text-align: right;\">\n",
|
68 |
+
" <th></th>\n",
|
69 |
+
" <th>URL</th>\n",
|
70 |
+
" <th>full_model_name</th>\n",
|
71 |
+
" <th>Parameters</th>\n",
|
72 |
+
" <th>MMLU_average</th>\n",
|
73 |
+
" <th>arc:challenge|25</th>\n",
|
74 |
+
" <th>hellaswag|10</th>\n",
|
75 |
+
" <th>MMLU_abstract_algebra</th>\n",
|
76 |
+
" <th>MMLU_anatomy</th>\n",
|
77 |
+
" <th>MMLU_astronomy</th>\n",
|
78 |
+
" <th>MMLU_business_ethics</th>\n",
|
79 |
+
" <th>...</th>\n",
|
80 |
+
" <th>MMLU_professional_accounting</th>\n",
|
81 |
+
" <th>MMLU_professional_law</th>\n",
|
82 |
+
" <th>MMLU_professional_medicine</th>\n",
|
83 |
+
" <th>MMLU_professional_psychology</th>\n",
|
84 |
+
" <th>MMLU_public_relations</th>\n",
|
85 |
+
" <th>MMLU_security_studies</th>\n",
|
86 |
+
" <th>MMLU_sociology</th>\n",
|
87 |
+
" <th>MMLU_us_foreign_policy</th>\n",
|
88 |
+
" <th>MMLU_virology</th>\n",
|
89 |
+
" <th>MMLU_world_religions</th>\n",
|
90 |
+
" </tr>\n",
|
91 |
+
" </thead>\n",
|
92 |
+
" <tbody>\n",
|
93 |
+
" <tr>\n",
|
94 |
+
" <th>SparseOPT-1.3B</th>\n",
|
95 |
+
" <td>https://huggingface.co/shaohang/SparseOPT-1.3B</td>\n",
|
96 |
+
" <td>shaohang/SparseOPT-1.3B</td>\n",
|
97 |
+
" <td>1.3</td>\n",
|
98 |
+
" <td>0.255963</td>\n",
|
99 |
+
" <td>0.240614</td>\n",
|
100 |
+
" <td>0.383689</td>\n",
|
101 |
+
" <td>0.22</td>\n",
|
102 |
+
" <td>0.214815</td>\n",
|
103 |
+
" <td>0.157895</td>\n",
|
104 |
+
" <td>0.20</td>\n",
|
105 |
+
" <td>...</td>\n",
|
106 |
+
" <td>0.262411</td>\n",
|
107 |
+
" <td>0.238592</td>\n",
|
108 |
+
" <td>0.448529</td>\n",
|
109 |
+
" <td>0.254902</td>\n",
|
110 |
+
" <td>0.236364</td>\n",
|
111 |
+
" <td>0.171429</td>\n",
|
112 |
+
" <td>0.228856</td>\n",
|
113 |
+
" <td>0.27</td>\n",
|
114 |
+
" <td>0.283133</td>\n",
|
115 |
+
" <td>0.216374</td>\n",
|
116 |
+
" </tr>\n",
|
117 |
+
" <tr>\n",
|
118 |
+
" <th>Athena-v1</th>\n",
|
119 |
+
" <td>https://huggingface.co/IkariDev/Athena-v1</td>\n",
|
120 |
+
" <td>IkariDev/Athena-v1</td>\n",
|
121 |
+
" <td>NaN</td>\n",
|
122 |
+
" <td>0.556052</td>\n",
|
123 |
+
" <td>0.560580</td>\n",
|
124 |
+
" <td>0.631548</td>\n",
|
125 |
+
" <td>0.31</td>\n",
|
126 |
+
" <td>0.496296</td>\n",
|
127 |
+
" <td>0.526316</td>\n",
|
128 |
+
" <td>0.58</td>\n",
|
129 |
+
" <td>...</td>\n",
|
130 |
+
" <td>0.404255</td>\n",
|
131 |
+
" <td>0.392438</td>\n",
|
132 |
+
" <td>0.525735</td>\n",
|
133 |
+
" <td>0.540850</td>\n",
|
134 |
+
" <td>0.645455</td>\n",
|
135 |
+
" <td>0.640816</td>\n",
|
136 |
+
" <td>0.751244</td>\n",
|
137 |
+
" <td>0.83</td>\n",
|
138 |
+
" <td>0.493976</td>\n",
|
139 |
+
" <td>0.725146</td>\n",
|
140 |
+
" </tr>\n",
|
141 |
+
" <tr>\n",
|
142 |
+
" <th>Athena-tmp</th>\n",
|
143 |
+
" <td>https://huggingface.co/IkariDev/Athena-tmp</td>\n",
|
144 |
+
" <td>IkariDev/Athena-tmp</td>\n",
|
145 |
+
" <td>NaN</td>\n",
|
146 |
+
" <td>0.588685</td>\n",
|
147 |
+
" <td>0.567406</td>\n",
|
148 |
+
" <td>0.621888</td>\n",
|
149 |
+
" <td>0.29</td>\n",
|
150 |
+
" <td>0.518519</td>\n",
|
151 |
+
" <td>0.638158</td>\n",
|
152 |
+
" <td>0.62</td>\n",
|
153 |
+
" <td>...</td>\n",
|
154 |
+
" <td>0.450355</td>\n",
|
155 |
+
" <td>0.462842</td>\n",
|
156 |
+
" <td>0.569853</td>\n",
|
157 |
+
" <td>0.588235</td>\n",
|
158 |
+
" <td>0.645455</td>\n",
|
159 |
+
" <td>0.653061</td>\n",
|
160 |
+
" <td>0.721393</td>\n",
|
161 |
+
" <td>0.81</td>\n",
|
162 |
+
" <td>0.463855</td>\n",
|
163 |
+
" <td>0.801170</td>\n",
|
164 |
+
" </tr>\n",
|
165 |
+
" <tr>\n",
|
166 |
+
" <th>13B-Legerdemain-L2</th>\n",
|
167 |
+
" <td>https://huggingface.co/CalderaAI/13B-Legerdema...</td>\n",
|
168 |
+
" <td>CalderaAI/13B-Legerdemain-L2</td>\n",
|
169 |
+
" <td>13.0</td>\n",
|
170 |
+
" <td>0.560030</td>\n",
|
171 |
+
" <td>0.573379</td>\n",
|
172 |
+
" <td>0.635431</td>\n",
|
173 |
+
" <td>0.36</td>\n",
|
174 |
+
" <td>0.525926</td>\n",
|
175 |
+
" <td>0.572368</td>\n",
|
176 |
+
" <td>0.53</td>\n",
|
177 |
+
" <td>...</td>\n",
|
178 |
+
" <td>0.429078</td>\n",
|
179 |
+
" <td>0.424381</td>\n",
|
180 |
+
" <td>0.522059</td>\n",
|
181 |
+
" <td>0.532680</td>\n",
|
182 |
+
" <td>0.609091</td>\n",
|
183 |
+
" <td>0.636735</td>\n",
|
184 |
+
" <td>0.766169</td>\n",
|
185 |
+
" <td>0.87</td>\n",
|
186 |
+
" <td>0.427711</td>\n",
|
187 |
+
" <td>0.777778</td>\n",
|
188 |
+
" </tr>\n",
|
189 |
+
" <tr>\n",
|
190 |
+
" <th>13B-Ouroboros</th>\n",
|
191 |
+
" <td>https://huggingface.co/CalderaAI/13B-Ouroboros</td>\n",
|
192 |
+
" <td>CalderaAI/13B-Ouroboros</td>\n",
|
193 |
+
" <td>13.0</td>\n",
|
194 |
+
" <td>0.514311</td>\n",
|
195 |
+
" <td>0.560580</td>\n",
|
196 |
+
" <td>0.624378</td>\n",
|
197 |
+
" <td>0.31</td>\n",
|
198 |
+
" <td>0.466667</td>\n",
|
199 |
+
" <td>0.506579</td>\n",
|
200 |
+
" <td>0.52</td>\n",
|
201 |
+
" <td>...</td>\n",
|
202 |
+
" <td>0.365248</td>\n",
|
203 |
+
" <td>0.405476</td>\n",
|
204 |
+
" <td>0.481618</td>\n",
|
205 |
+
" <td>0.524510</td>\n",
|
206 |
+
" <td>0.609091</td>\n",
|
207 |
+
" <td>0.538776</td>\n",
|
208 |
+
" <td>0.691542</td>\n",
|
209 |
+
" <td>0.83</td>\n",
|
210 |
+
" <td>0.457831</td>\n",
|
211 |
+
" <td>0.760234</td>\n",
|
212 |
+
" </tr>\n",
|
213 |
+
" <tr>\n",
|
214 |
+
" <th>...</th>\n",
|
215 |
+
" <td>...</td>\n",
|
216 |
+
" <td>...</td>\n",
|
217 |
+
" <td>...</td>\n",
|
218 |
+
" <td>...</td>\n",
|
219 |
+
" <td>...</td>\n",
|
220 |
+
" <td>...</td>\n",
|
221 |
+
" <td>...</td>\n",
|
222 |
+
" <td>...</td>\n",
|
223 |
+
" <td>...</td>\n",
|
224 |
+
" <td>...</td>\n",
|
225 |
+
" <td>...</td>\n",
|
226 |
+
" <td>...</td>\n",
|
227 |
+
" <td>...</td>\n",
|
228 |
+
" <td>...</td>\n",
|
229 |
+
" <td>...</td>\n",
|
230 |
+
" <td>...</td>\n",
|
231 |
+
" <td>...</td>\n",
|
232 |
+
" <td>...</td>\n",
|
233 |
+
" <td>...</td>\n",
|
234 |
+
" <td>...</td>\n",
|
235 |
+
" <td>...</td>\n",
|
236 |
+
" </tr>\n",
|
237 |
+
" <tr>\n",
|
238 |
+
" <th>Robin-v2</th>\n",
|
239 |
+
" <td>https://huggingface.co/HanningZhang/Robin-v2</td>\n",
|
240 |
+
" <td>HanningZhang/Robin-v2</td>\n",
|
241 |
+
" <td>NaN</td>\n",
|
242 |
+
" <td>0.392680</td>\n",
|
243 |
+
" <td>0.435154</td>\n",
|
244 |
+
" <td>0.545310</td>\n",
|
245 |
+
" <td>0.32</td>\n",
|
246 |
+
" <td>0.437037</td>\n",
|
247 |
+
" <td>0.335526</td>\n",
|
248 |
+
" <td>0.46</td>\n",
|
249 |
+
" <td>...</td>\n",
|
250 |
+
" <td>0.290780</td>\n",
|
251 |
+
" <td>0.302477</td>\n",
|
252 |
+
" <td>0.382353</td>\n",
|
253 |
+
" <td>0.374183</td>\n",
|
254 |
+
" <td>0.445455</td>\n",
|
255 |
+
" <td>0.326531</td>\n",
|
256 |
+
" <td>0.457711</td>\n",
|
257 |
+
" <td>0.59</td>\n",
|
258 |
+
" <td>0.379518</td>\n",
|
259 |
+
" <td>0.590643</td>\n",
|
260 |
+
" </tr>\n",
|
261 |
+
" <tr>\n",
|
262 |
+
" <th>CodeUp-Llama-2-13b-chat-hf</th>\n",
|
263 |
+
" <td>https://huggingface.co/deepse/CodeUp-Llama-2-1...</td>\n",
|
264 |
+
" <td>deepse/CodeUp-Llama-2-13b-chat-hf</td>\n",
|
265 |
+
" <td>13.0</td>\n",
|
266 |
+
" <td>0.546262</td>\n",
|
267 |
+
" <td>0.558020</td>\n",
|
268 |
+
" <td>0.629257</td>\n",
|
269 |
+
" <td>0.31</td>\n",
|
270 |
+
" <td>0.474074</td>\n",
|
271 |
+
" <td>0.546053</td>\n",
|
272 |
+
" <td>0.53</td>\n",
|
273 |
+
" <td>...</td>\n",
|
274 |
+
" <td>0.390071</td>\n",
|
275 |
+
" <td>0.391786</td>\n",
|
276 |
+
" <td>0.500000</td>\n",
|
277 |
+
" <td>0.544118</td>\n",
|
278 |
+
" <td>0.663636</td>\n",
|
279 |
+
" <td>0.636735</td>\n",
|
280 |
+
" <td>0.751244</td>\n",
|
281 |
+
" <td>0.81</td>\n",
|
282 |
+
" <td>0.481928</td>\n",
|
283 |
+
" <td>0.730994</td>\n",
|
284 |
+
" </tr>\n",
|
285 |
+
" <tr>\n",
|
286 |
+
" <th>Hermes-Platypus2-mini-7B</th>\n",
|
287 |
+
" <td>https://huggingface.co/edor/Hermes-Platypus2-m...</td>\n",
|
288 |
+
" <td>edor/Hermes-Platypus2-mini-7B</td>\n",
|
289 |
+
" <td>7.0</td>\n",
|
290 |
+
" <td>0.470828</td>\n",
|
291 |
+
" <td>0.523038</td>\n",
|
292 |
+
" <td>0.601573</td>\n",
|
293 |
+
" <td>0.33</td>\n",
|
294 |
+
" <td>0.488889</td>\n",
|
295 |
+
" <td>0.421053</td>\n",
|
296 |
+
" <td>0.48</td>\n",
|
297 |
+
" <td>...</td>\n",
|
298 |
+
" <td>0.390071</td>\n",
|
299 |
+
" <td>0.353977</td>\n",
|
300 |
+
" <td>0.470588</td>\n",
|
301 |
+
" <td>0.446078</td>\n",
|
302 |
+
" <td>0.518182</td>\n",
|
303 |
+
" <td>0.563265</td>\n",
|
304 |
+
" <td>0.621891</td>\n",
|
305 |
+
" <td>0.68</td>\n",
|
306 |
+
" <td>0.421687</td>\n",
|
307 |
+
" <td>0.637427</td>\n",
|
308 |
+
" </tr>\n",
|
309 |
+
" <tr>\n",
|
310 |
+
" <th>Stable-Platypus2-mini-7B</th>\n",
|
311 |
+
" <td>https://huggingface.co/edor/Stable-Platypus2-m...</td>\n",
|
312 |
+
" <td>edor/Stable-Platypus2-mini-7B</td>\n",
|
313 |
+
" <td>7.0</td>\n",
|
314 |
+
" <td>0.517800</td>\n",
|
315 |
+
" <td>0.523891</td>\n",
|
316 |
+
" <td>0.596594</td>\n",
|
317 |
+
" <td>0.37</td>\n",
|
318 |
+
" <td>0.488889</td>\n",
|
319 |
+
" <td>0.407895</td>\n",
|
320 |
+
" <td>0.50</td>\n",
|
321 |
+
" <td>...</td>\n",
|
322 |
+
" <td>0.390071</td>\n",
|
323 |
+
" <td>0.391786</td>\n",
|
324 |
+
" <td>0.518382</td>\n",
|
325 |
+
" <td>0.509804</td>\n",
|
326 |
+
" <td>0.618182</td>\n",
|
327 |
+
" <td>0.657143</td>\n",
|
328 |
+
" <td>0.631841</td>\n",
|
329 |
+
" <td>0.73</td>\n",
|
330 |
+
" <td>0.427711</td>\n",
|
331 |
+
" <td>0.695906</td>\n",
|
332 |
+
" </tr>\n",
|
333 |
+
" <tr>\n",
|
334 |
+
" <th>llava-v1.5-13b-hf</th>\n",
|
335 |
+
" <td>https://huggingface.co/Community-LM/llava-v1.5...</td>\n",
|
336 |
+
" <td>Community-LM/llava-v1.5-13b-hf</td>\n",
|
337 |
+
" <td>13.0</td>\n",
|
338 |
+
" <td>0.568868</td>\n",
|
339 |
+
" <td>0.532423</td>\n",
|
340 |
+
" <td>0.601175</td>\n",
|
341 |
+
" <td>0.30</td>\n",
|
342 |
+
" <td>0.496296</td>\n",
|
343 |
+
" <td>0.585526</td>\n",
|
344 |
+
" <td>0.67</td>\n",
|
345 |
+
" <td>...</td>\n",
|
346 |
+
" <td>0.407801</td>\n",
|
347 |
+
" <td>0.415906</td>\n",
|
348 |
+
" <td>0.547794</td>\n",
|
349 |
+
" <td>0.578431</td>\n",
|
350 |
+
" <td>0.600000</td>\n",
|
351 |
+
" <td>0.653061</td>\n",
|
352 |
+
" <td>0.761194</td>\n",
|
353 |
+
" <td>0.81</td>\n",
|
354 |
+
" <td>0.506024</td>\n",
|
355 |
+
" <td>0.795322</td>\n",
|
356 |
+
" </tr>\n",
|
357 |
+
" </tbody>\n",
|
358 |
+
"</table>\n",
|
359 |
+
"<p>1121 rows × 63 columns</p>\n",
|
360 |
+
"</div>"
|
361 |
+
],
|
362 |
+
"text/plain": [
|
363 |
+
" URL \\\n",
|
364 |
+
"SparseOPT-1.3B https://huggingface.co/shaohang/SparseOPT-1.3B \n",
|
365 |
+
"Athena-v1 https://huggingface.co/IkariDev/Athena-v1 \n",
|
366 |
+
"Athena-tmp https://huggingface.co/IkariDev/Athena-tmp \n",
|
367 |
+
"13B-Legerdemain-L2 https://huggingface.co/CalderaAI/13B-Legerdema... \n",
|
368 |
+
"13B-Ouroboros https://huggingface.co/CalderaAI/13B-Ouroboros \n",
|
369 |
+
"... ... \n",
|
370 |
+
"Robin-v2 https://huggingface.co/HanningZhang/Robin-v2 \n",
|
371 |
+
"CodeUp-Llama-2-13b-chat-hf https://huggingface.co/deepse/CodeUp-Llama-2-1... \n",
|
372 |
+
"Hermes-Platypus2-mini-7B https://huggingface.co/edor/Hermes-Platypus2-m... \n",
|
373 |
+
"Stable-Platypus2-mini-7B https://huggingface.co/edor/Stable-Platypus2-m... \n",
|
374 |
+
"llava-v1.5-13b-hf https://huggingface.co/Community-LM/llava-v1.5... \n",
|
375 |
+
"\n",
|
376 |
+
" full_model_name Parameters \\\n",
|
377 |
+
"SparseOPT-1.3B shaohang/SparseOPT-1.3B 1.3 \n",
|
378 |
+
"Athena-v1 IkariDev/Athena-v1 NaN \n",
|
379 |
+
"Athena-tmp IkariDev/Athena-tmp NaN \n",
|
380 |
+
"13B-Legerdemain-L2 CalderaAI/13B-Legerdemain-L2 13.0 \n",
|
381 |
+
"13B-Ouroboros CalderaAI/13B-Ouroboros 13.0 \n",
|
382 |
+
"... ... ... \n",
|
383 |
+
"Robin-v2 HanningZhang/Robin-v2 NaN \n",
|
384 |
+
"CodeUp-Llama-2-13b-chat-hf deepse/CodeUp-Llama-2-13b-chat-hf 13.0 \n",
|
385 |
+
"Hermes-Platypus2-mini-7B edor/Hermes-Platypus2-mini-7B 7.0 \n",
|
386 |
+
"Stable-Platypus2-mini-7B edor/Stable-Platypus2-mini-7B 7.0 \n",
|
387 |
+
"llava-v1.5-13b-hf Community-LM/llava-v1.5-13b-hf 13.0 \n",
|
388 |
+
"\n",
|
389 |
+
" MMLU_average arc:challenge|25 hellaswag|10 \\\n",
|
390 |
+
"SparseOPT-1.3B 0.255963 0.240614 0.383689 \n",
|
391 |
+
"Athena-v1 0.556052 0.560580 0.631548 \n",
|
392 |
+
"Athena-tmp 0.588685 0.567406 0.621888 \n",
|
393 |
+
"13B-Legerdemain-L2 0.560030 0.573379 0.635431 \n",
|
394 |
+
"13B-Ouroboros 0.514311 0.560580 0.624378 \n",
|
395 |
+
"... ... ... ... \n",
|
396 |
+
"Robin-v2 0.392680 0.435154 0.545310 \n",
|
397 |
+
"CodeUp-Llama-2-13b-chat-hf 0.546262 0.558020 0.629257 \n",
|
398 |
+
"Hermes-Platypus2-mini-7B 0.470828 0.523038 0.601573 \n",
|
399 |
+
"Stable-Platypus2-mini-7B 0.517800 0.523891 0.596594 \n",
|
400 |
+
"llava-v1.5-13b-hf 0.568868 0.532423 0.601175 \n",
|
401 |
+
"\n",
|
402 |
+
" MMLU_abstract_algebra MMLU_anatomy \\\n",
|
403 |
+
"SparseOPT-1.3B 0.22 0.214815 \n",
|
404 |
+
"Athena-v1 0.31 0.496296 \n",
|
405 |
+
"Athena-tmp 0.29 0.518519 \n",
|
406 |
+
"13B-Legerdemain-L2 0.36 0.525926 \n",
|
407 |
+
"13B-Ouroboros 0.31 0.466667 \n",
|
408 |
+
"... ... ... \n",
|
409 |
+
"Robin-v2 0.32 0.437037 \n",
|
410 |
+
"CodeUp-Llama-2-13b-chat-hf 0.31 0.474074 \n",
|
411 |
+
"Hermes-Platypus2-mini-7B 0.33 0.488889 \n",
|
412 |
+
"Stable-Platypus2-mini-7B 0.37 0.488889 \n",
|
413 |
+
"llava-v1.5-13b-hf 0.30 0.496296 \n",
|
414 |
+
"\n",
|
415 |
+
" MMLU_astronomy MMLU_business_ethics ... \\\n",
|
416 |
+
"SparseOPT-1.3B 0.157895 0.20 ... \n",
|
417 |
+
"Athena-v1 0.526316 0.58 ... \n",
|
418 |
+
"Athena-tmp 0.638158 0.62 ... \n",
|
419 |
+
"13B-Legerdemain-L2 0.572368 0.53 ... \n",
|
420 |
+
"13B-Ouroboros 0.506579 0.52 ... \n",
|
421 |
+
"... ... ... ... \n",
|
422 |
+
"Robin-v2 0.335526 0.46 ... \n",
|
423 |
+
"CodeUp-Llama-2-13b-chat-hf 0.546053 0.53 ... \n",
|
424 |
+
"Hermes-Platypus2-mini-7B 0.421053 0.48 ... \n",
|
425 |
+
"Stable-Platypus2-mini-7B 0.407895 0.50 ... \n",
|
426 |
+
"llava-v1.5-13b-hf 0.585526 0.67 ... \n",
|
427 |
+
"\n",
|
428 |
+
" MMLU_professional_accounting \\\n",
|
429 |
+
"SparseOPT-1.3B 0.262411 \n",
|
430 |
+
"Athena-v1 0.404255 \n",
|
431 |
+
"Athena-tmp 0.450355 \n",
|
432 |
+
"13B-Legerdemain-L2 0.429078 \n",
|
433 |
+
"13B-Ouroboros 0.365248 \n",
|
434 |
+
"... ... \n",
|
435 |
+
"Robin-v2 0.290780 \n",
|
436 |
+
"CodeUp-Llama-2-13b-chat-hf 0.390071 \n",
|
437 |
+
"Hermes-Platypus2-mini-7B 0.390071 \n",
|
438 |
+
"Stable-Platypus2-mini-7B 0.390071 \n",
|
439 |
+
"llava-v1.5-13b-hf 0.407801 \n",
|
440 |
+
"\n",
|
441 |
+
" MMLU_professional_law MMLU_professional_medicine \\\n",
|
442 |
+
"SparseOPT-1.3B 0.238592 0.448529 \n",
|
443 |
+
"Athena-v1 0.392438 0.525735 \n",
|
444 |
+
"Athena-tmp 0.462842 0.569853 \n",
|
445 |
+
"13B-Legerdemain-L2 0.424381 0.522059 \n",
|
446 |
+
"13B-Ouroboros 0.405476 0.481618 \n",
|
447 |
+
"... ... ... \n",
|
448 |
+
"Robin-v2 0.302477 0.382353 \n",
|
449 |
+
"CodeUp-Llama-2-13b-chat-hf 0.391786 0.500000 \n",
|
450 |
+
"Hermes-Platypus2-mini-7B 0.353977 0.470588 \n",
|
451 |
+
"Stable-Platypus2-mini-7B 0.391786 0.518382 \n",
|
452 |
+
"llava-v1.5-13b-hf 0.415906 0.547794 \n",
|
453 |
+
"\n",
|
454 |
+
" MMLU_professional_psychology \\\n",
|
455 |
+
"SparseOPT-1.3B 0.254902 \n",
|
456 |
+
"Athena-v1 0.540850 \n",
|
457 |
+
"Athena-tmp 0.588235 \n",
|
458 |
+
"13B-Legerdemain-L2 0.532680 \n",
|
459 |
+
"13B-Ouroboros 0.524510 \n",
|
460 |
+
"... ... \n",
|
461 |
+
"Robin-v2 0.374183 \n",
|
462 |
+
"CodeUp-Llama-2-13b-chat-hf 0.544118 \n",
|
463 |
+
"Hermes-Platypus2-mini-7B 0.446078 \n",
|
464 |
+
"Stable-Platypus2-mini-7B 0.509804 \n",
|
465 |
+
"llava-v1.5-13b-hf 0.578431 \n",
|
466 |
+
"\n",
|
467 |
+
" MMLU_public_relations MMLU_security_studies \\\n",
|
468 |
+
"SparseOPT-1.3B 0.236364 0.171429 \n",
|
469 |
+
"Athena-v1 0.645455 0.640816 \n",
|
470 |
+
"Athena-tmp 0.645455 0.653061 \n",
|
471 |
+
"13B-Legerdemain-L2 0.609091 0.636735 \n",
|
472 |
+
"13B-Ouroboros 0.609091 0.538776 \n",
|
473 |
+
"... ... ... \n",
|
474 |
+
"Robin-v2 0.445455 0.326531 \n",
|
475 |
+
"CodeUp-Llama-2-13b-chat-hf 0.663636 0.636735 \n",
|
476 |
+
"Hermes-Platypus2-mini-7B 0.518182 0.563265 \n",
|
477 |
+
"Stable-Platypus2-mini-7B 0.618182 0.657143 \n",
|
478 |
+
"llava-v1.5-13b-hf 0.600000 0.653061 \n",
|
479 |
+
"\n",
|
480 |
+
" MMLU_sociology MMLU_us_foreign_policy \\\n",
|
481 |
+
"SparseOPT-1.3B 0.228856 0.27 \n",
|
482 |
+
"Athena-v1 0.751244 0.83 \n",
|
483 |
+
"Athena-tmp 0.721393 0.81 \n",
|
484 |
+
"13B-Legerdemain-L2 0.766169 0.87 \n",
|
485 |
+
"13B-Ouroboros 0.691542 0.83 \n",
|
486 |
+
"... ... ... \n",
|
487 |
+
"Robin-v2 0.457711 0.59 \n",
|
488 |
+
"CodeUp-Llama-2-13b-chat-hf 0.751244 0.81 \n",
|
489 |
+
"Hermes-Platypus2-mini-7B 0.621891 0.68 \n",
|
490 |
+
"Stable-Platypus2-mini-7B 0.631841 0.73 \n",
|
491 |
+
"llava-v1.5-13b-hf 0.761194 0.81 \n",
|
492 |
+
"\n",
|
493 |
+
" MMLU_virology MMLU_world_religions \n",
|
494 |
+
"SparseOPT-1.3B 0.283133 0.216374 \n",
|
495 |
+
"Athena-v1 0.493976 0.725146 \n",
|
496 |
+
"Athena-tmp 0.463855 0.801170 \n",
|
497 |
+
"13B-Legerdemain-L2 0.427711 0.777778 \n",
|
498 |
+
"13B-Ouroboros 0.457831 0.760234 \n",
|
499 |
+
"... ... ... \n",
|
500 |
+
"Robin-v2 0.379518 0.590643 \n",
|
501 |
+
"CodeUp-Llama-2-13b-chat-hf 0.481928 0.730994 \n",
|
502 |
+
"Hermes-Platypus2-mini-7B 0.421687 0.637427 \n",
|
503 |
+
"Stable-Platypus2-mini-7B 0.427711 0.695906 \n",
|
504 |
+
"llava-v1.5-13b-hf 0.506024 0.795322 \n",
|
505 |
+
"\n",
|
506 |
+
"[1121 rows x 63 columns]"
|
507 |
+
]
|
508 |
+
},
|
509 |
+
"execution_count": 2,
|
510 |
+
"metadata": {},
|
511 |
+
"output_type": "execute_result"
|
512 |
+
}
|
513 |
+
],
|
514 |
+
"source": [
|
515 |
+
"df = result.data\n",
|
516 |
+
"df"
|
517 |
+
]
|
518 |
+
},
|
519 |
+
{
|
520 |
+
"cell_type": "code",
|
521 |
+
"execution_count": null,
|
522 |
+
"metadata": {},
|
523 |
+
"outputs": [],
|
524 |
+
"source": []
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"cell_type": "code",
|
528 |
+
"execution_count": null,
|
529 |
+
"metadata": {},
|
530 |
+
"outputs": [],
|
531 |
+
"source": []
|
532 |
+
},
|
533 |
{
|
534 |
"cell_type": "code",
|
535 |
"execution_count": null,
|