Added Table 2
Browse files
README.md
CHANGED
@@ -44,6 +44,329 @@ model-index:
|
|
44 |
# OctoCoder
|
45 |
|
46 |
Play with the model on the [TODO Playground](https://huggingface.co/spaces/bigcode/bigcode-playground).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
|
48 |
## Table of Contents
|
49 |
|
|
|
44 |
# OctoCoder
|
45 |
|
46 |
Play with the model on the [TODO Playground](https://huggingface.co/spaces/bigcode/bigcode-playground).
|
47 |
+
<style>
|
48 |
+
table{
|
49 |
+
border-collapse: collapse;
|
50 |
+
}
|
51 |
+
</style>
|
52 |
+
<table>
|
53 |
+
<tr>
|
54 |
+
<th>Model (↓)</th>
|
55 |
+
<th>Python</th>
|
56 |
+
<th>JavaScript</th>
|
57 |
+
<th>Java</th>
|
58 |
+
<th>Go</th>
|
59 |
+
<th>C++</th>
|
60 |
+
<th>Rust</th>
|
61 |
+
<th>Avg.</th>
|
62 |
+
</tr>
|
63 |
+
</table>
|
64 |
+
<hr style="background-color: black;">
|
65 |
+
<center><strong>HumanEvalFix</strong></center>
|
66 |
+
<hr style="background-color: black;">
|
67 |
+
<center>Non-permissive models</center>
|
68 |
+
<hr style="background-color: black;">
|
69 |
+
<table>
|
70 |
+
<tr>
|
71 |
+
<td>WizardCoder</td>
|
72 |
+
<td>31.8</td>
|
73 |
+
<td>29.5</td>
|
74 |
+
<td>12.7</td>
|
75 |
+
<td>30.4</td>
|
76 |
+
<td>18.7</td>
|
77 |
+
<td>13.0</td>
|
78 |
+
<td>22.7</td>
|
79 |
+
</tr>
|
80 |
+
<tr>
|
81 |
+
<td>GPT-4</td>
|
82 |
+
<td>47.0 </td>
|
83 |
+
<td>48.2</td>
|
84 |
+
<td>50.0</td>
|
85 |
+
<td>50.6</td>
|
86 |
+
<td>47.6</td>
|
87 |
+
<td>43.3</td>
|
88 |
+
<td><u>47.8</u></td>
|
89 |
+
</tr>
|
90 |
+
</table>
|
91 |
+
<hr style="background-color: black;">
|
92 |
+
<center>Permissive models</center>
|
93 |
+
<hr style="background-color: black;">
|
94 |
+
<table>
|
95 |
+
<tr>
|
96 |
+
<td>InstructCodeT5+<sup>‡</sup></td>
|
97 |
+
<td>2.7</td>
|
98 |
+
<td>1.2</td>
|
99 |
+
<td>4.3</td>
|
100 |
+
<td>2.1</td>
|
101 |
+
<td>0.2</td>
|
102 |
+
<td>0.5</td>
|
103 |
+
<td>1.8</td>
|
104 |
+
</tr>
|
105 |
+
<tr>
|
106 |
+
<td>BLOOMZ<sup>+</sup></td>
|
107 |
+
<td>16.6</td>
|
108 |
+
<td>15.5</td>
|
109 |
+
<td>15.2</td>
|
110 |
+
<td>16.4</td>
|
111 |
+
<td>6.7</td>
|
112 |
+
<td>5.7</td>
|
113 |
+
<td>12.5</td>
|
114 |
+
</tr>
|
115 |
+
<tr>
|
116 |
+
<td>StarChat-β</td>
|
117 |
+
<td>18.1</td>
|
118 |
+
<td>18.1</td>
|
119 |
+
<td>24.1</td>
|
120 |
+
<td>18.1</td>
|
121 |
+
<td>8.2</td>
|
122 |
+
<td>3.6</td>
|
123 |
+
<td>11.2</td>
|
124 |
+
</tr>
|
125 |
+
<tr>
|
126 |
+
<td>CodeGeeX2<sup>*</sup></td>
|
127 |
+
<td>15.9</td>
|
128 |
+
<td>14.7</td>
|
129 |
+
<td>18.0</td>
|
130 |
+
<td>13.6</td>
|
131 |
+
<td>4.3</td>
|
132 |
+
<td>6.1</td>
|
133 |
+
<td>12.1</td>
|
134 |
+
</tr>
|
135 |
+
<tr>
|
136 |
+
<td>StarCoder</td>
|
137 |
+
<td>8.7</td>
|
138 |
+
<td>15.7</td>
|
139 |
+
<td>13.3</td>
|
140 |
+
<td>20.1</td>
|
141 |
+
<td>15.6</td>
|
142 |
+
<td>6.7</td>
|
143 |
+
<td>13.4</td>
|
144 |
+
</tr>
|
145 |
+
<tr>
|
146 |
+
<td>OctoGeeX<sup>*</sup></td>
|
147 |
+
<td>28.1</td>
|
148 |
+
<td>27.7</td>
|
149 |
+
<td>30.4</td>
|
150 |
+
<td>27.6</td>
|
151 |
+
<td>22.9</td>
|
152 |
+
<td>9.6</td>
|
153 |
+
<td>24.4</td>
|
154 |
+
</tr>
|
155 |
+
<tr>
|
156 |
+
<td>OctoCoder</td>
|
157 |
+
<td><strong>30.2</strong></td>
|
158 |
+
<td><strong>28.4</strong></td>
|
159 |
+
<td><strong>30.6</strong></td>
|
160 |
+
<td><strong>30.2</strong></td>
|
161 |
+
<td><strong>26.1</strong></td>
|
162 |
+
<td><strong>16.5</strong></td>
|
163 |
+
<td><strong>27.0</strong></td>
|
164 |
+
</tr>
|
165 |
+
</table>
|
166 |
+
<hr style="background-color: black;">
|
167 |
+
<center><h4>HumanEvalExplain</h4></center>
|
168 |
+
<hr style="background-color: black;">
|
169 |
+
<center>Non-permissive models</center>
|
170 |
+
<hr style="background-color: black;">
|
171 |
+
<table>
|
172 |
+
<tr>
|
173 |
+
<td>WizardCoder</td>
|
174 |
+
<td>32.5</td>
|
175 |
+
<td>33.0</td>
|
176 |
+
<td>27.4</td>
|
177 |
+
<td>26.7</td>
|
178 |
+
<td>28.2</td>
|
179 |
+
<td>16.9</td>
|
180 |
+
<td>27.5</td>
|
181 |
+
</tr>
|
182 |
+
<tr>
|
183 |
+
<td>GPT-4</td>
|
184 |
+
<td>64.6</td>
|
185 |
+
<td>57.3</td>
|
186 |
+
<td>51.2</td>
|
187 |
+
<td>58.5</td>
|
188 |
+
<td>38.4</td>
|
189 |
+
<td>42.7</td>
|
190 |
+
<td><u>52.1</u></td>
|
191 |
+
</tr>
|
192 |
+
</table>
|
193 |
+
<hr style="background-color: black;">
|
194 |
+
<center>Permissive models</center>
|
195 |
+
<hr style="background-color: black;">
|
196 |
+
<table>
|
197 |
+
<tr>
|
198 |
+
<td>InstructCodeT5+<sup>‡</sup></td>
|
199 |
+
<td>20.8</td>
|
200 |
+
<td>0.0</td>
|
201 |
+
<td>0.0</td>
|
202 |
+
<td>0.0</td>
|
203 |
+
<td>0.1</td>
|
204 |
+
<td>0.0</td>
|
205 |
+
<td>3.5</td>
|
206 |
+
</tr>
|
207 |
+
<tr>
|
208 |
+
<td>BLOOMZ<sup>+</sup></td>
|
209 |
+
<td>14.7</td>
|
210 |
+
<td>8.8</td>
|
211 |
+
<td>12.1</td>
|
212 |
+
<td>8.5</td>
|
213 |
+
<td>0.6</td>
|
214 |
+
<td>0.0</td>
|
215 |
+
<td>7.5</td>
|
216 |
+
</tr>
|
217 |
+
<tr>
|
218 |
+
<td>StarChat-β</td>
|
219 |
+
<td>25.4</td>
|
220 |
+
<td>21.5</td>
|
221 |
+
<td>24.5</td>
|
222 |
+
<td>18.4</td>
|
223 |
+
<td>17.6</td>
|
224 |
+
<td>13.2</td>
|
225 |
+
<td>20.1</td>
|
226 |
+
</tr>
|
227 |
+
<tr>
|
228 |
+
<td>CodeGeeX2<sup>*</sup></td>
|
229 |
+
<td>0.0</td>
|
230 |
+
<td>0.0</td>
|
231 |
+
<td>0.0</td>
|
232 |
+
<td>0.0</td>
|
233 |
+
<td>0.0</td>
|
234 |
+
<td>0.0</td>
|
235 |
+
<td>0.0</td>
|
236 |
+
</tr>
|
237 |
+
<tr>
|
238 |
+
<td>StarCoder</td>
|
239 |
+
<td>0.0</td>
|
240 |
+
<td>0.0</td>
|
241 |
+
<td>0.0</td>
|
242 |
+
<td>0.0</td>
|
243 |
+
<td>0.0</td>
|
244 |
+
<td>0.0</td>
|
245 |
+
<td>0.0</td>
|
246 |
+
</tr>
|
247 |
+
<tr>
|
248 |
+
<td>OctoGeeX<sup>*</sup></td>
|
249 |
+
<td>30.4</td>
|
250 |
+
<td>24.0</td>
|
251 |
+
<td>24.7</td>
|
252 |
+
<td><strong>21.7</strong></td>
|
253 |
+
<td>21.0</td>
|
254 |
+
<td><strong>15.9</strong></td>
|
255 |
+
<td>22.9</td>
|
256 |
+
</tr>
|
257 |
+
<tr>
|
258 |
+
<td>OctoCoder</td>
|
259 |
+
<td><strong>35.1</strong></td>
|
260 |
+
<td><strong>24.5</strong></td>
|
261 |
+
<td><strong>27.3</strong></td>
|
262 |
+
<td>21.1</td>
|
263 |
+
<td><strong>24.1</strong></td>
|
264 |
+
<td>14.8</td>
|
265 |
+
<td><strong>24.5</strong></td>
|
266 |
+
</tr>
|
267 |
+
</table>
|
268 |
+
<hr style="background-color: black;">
|
269 |
+
<center><h4>HumanEvalSynthesize</h4></center>
|
270 |
+
<hr style="background-color: black;">
|
271 |
+
<center>Non-permissive models</center>
|
272 |
+
<hr style="background-color: black;">
|
273 |
+
<table>
|
274 |
+
<tr>
|
275 |
+
<td>WizardCoder</td>
|
276 |
+
<td>57.3</td>
|
277 |
+
<td>49.5</td>
|
278 |
+
<td>36.1</td>
|
279 |
+
<td>36.4</td>
|
280 |
+
<td>40.9</td>
|
281 |
+
<td>20.2</td>
|
282 |
+
<td>40.1</td>
|
283 |
+
</tr>
|
284 |
+
<tr>
|
285 |
+
<td>GPT-4</td>
|
286 |
+
<td>86.6</td>
|
287 |
+
<td>82.9</td>
|
288 |
+
<td>81.7</td>
|
289 |
+
<td>72.6</td>
|
290 |
+
<td>78.7</td>
|
291 |
+
<td>67.1</td>
|
292 |
+
<td><u>78.3</u></td>
|
293 |
+
</tr>
|
294 |
+
</table>
|
295 |
+
<hr style="background-color: black;">
|
296 |
+
<center>Permissive models</center>
|
297 |
+
<hr style="background-color: black;">
|
298 |
+
<table>
|
299 |
+
<tr>
|
300 |
+
<td>InstructCodeT5+<sup>‡</sup></td>
|
301 |
+
<td>37.0</td>
|
302 |
+
<td>18.9</td>
|
303 |
+
<td>17.4</td>
|
304 |
+
<td>9.5</td>
|
305 |
+
<td>19.8</td>
|
306 |
+
<td>0.3</td>
|
307 |
+
<td>17.1</td>
|
308 |
+
</tr>
|
309 |
+
<tr>
|
310 |
+
<td>BLOOMZ<sup>+</sup></td>
|
311 |
+
<td>15.6</td>
|
312 |
+
<td>14.8</td>
|
313 |
+
<td>18.4</td>
|
314 |
+
<td>8.4</td>
|
315 |
+
<td>6.5</td>
|
316 |
+
<td>5.5</td>
|
317 |
+
<td>11.5</td>
|
318 |
+
</tr>
|
319 |
+
<tr>
|
320 |
+
<td>StarChat-β</td>
|
321 |
+
<td>33.5</td>
|
322 |
+
<td>31.4</td>
|
323 |
+
<td>26.7</td>
|
324 |
+
<td>25.5</td>
|
325 |
+
<td>26.6</td>
|
326 |
+
<td>14.0</td>
|
327 |
+
<td>26.3</td>
|
328 |
+
</tr>
|
329 |
+
<tr>
|
330 |
+
<td>CodeGeeX2<sup>*</sup></td>
|
331 |
+
<td>35.9</td>
|
332 |
+
<td>32.2</td>
|
333 |
+
<td>30.8</td>
|
334 |
+
<td>22.5</td>
|
335 |
+
<td>29.3</td>
|
336 |
+
<td>18.1</td>
|
337 |
+
<td>28.1</td>
|
338 |
+
</tr>
|
339 |
+
<tr>
|
340 |
+
<td>StarCoder</td>
|
341 |
+
<td>33.6</td>
|
342 |
+
<td>30.8</td>
|
343 |
+
<td>30.2</td>
|
344 |
+
<td>17.6</td>
|
345 |
+
<td>31.6</td>
|
346 |
+
<td>21.8</td>
|
347 |
+
<td>27.6</td>
|
348 |
+
</tr>
|
349 |
+
<tr>
|
350 |
+
<td>OctoGeeX<sup>*</sup></td>
|
351 |
+
<td>44.7</td>
|
352 |
+
<td>33.8</td>
|
353 |
+
<td>36.9</td>
|
354 |
+
<td>21.9</td>
|
355 |
+
<td>32.3</td>
|
356 |
+
<td>15.7</td>
|
357 |
+
<td>30.9</td>
|
358 |
+
</tr>
|
359 |
+
<tr>
|
360 |
+
<td>OctoCoder</td>
|
361 |
+
<td><strong>46.2</strong></td>
|
362 |
+
<td><strong>39.2</strong></td>
|
363 |
+
<td><strong>38.2</strong></td>
|
364 |
+
<td><strong>30.4</strong></td>
|
365 |
+
<td><strong>35.6</strong></td>
|
366 |
+
<td><strong>23.4</strong></td>
|
367 |
+
<td><strong>35.5</strong></td>
|
368 |
+
</tr>
|
369 |
+
</table>
|
370 |
|
371 |
## Table of Contents
|
372 |
|