Update README.md
Browse files
README.md
CHANGED
@@ -207,10 +207,10 @@ By implementing this innovative prevention strategy, we can significantly reduce
|
|
207 |
**Evaluation Results:**
|
208 |
<table>
|
209 |
<thead>
|
210 |
-
<caption style="text-align:center"><b>Comparison with different models over various benchmarks
|
211 |
<tr>
|
212 |
<th style="text-align:left; background-color: #001d6c; color: white;">Models</th>
|
213 |
-
<th style="text-align:center; background-color: #001d6c; color: white;">
|
214 |
<th style="text-align:center; background-color: #001d6c; color: white;">AlpacaEval-2.0</th>
|
215 |
<th style="text-align:center; background-color: #001d6c; color: white;">MMLU</th>
|
216 |
<th style="text-align:center; background-color: #001d6c; color: white;">PopQA</th>
|
@@ -255,114 +255,114 @@ By implementing this innovative prevention strategy, we can significantly reduce
|
|
255 |
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">83.23</td>
|
256 |
</tr>
|
257 |
<tr>
|
258 |
-
<td style="text-align:left; background-color: #
|
259 |
-
<td style="text-align:center; background-color: #
|
260 |
-
<td style="text-align:center; background-color: #
|
261 |
-
<td style="text-align:center; background-color: #
|
262 |
-
<td style="text-align:center; background-color: #
|
263 |
-
<td style="text-align:center; background-color: #
|
264 |
-
<td style="text-align:center; background-color: #
|
265 |
-
<td style="text-align:center; background-color: #
|
266 |
-
<td style="text-align:center; background-color: #
|
267 |
-
<td style="text-align:center; background-color: #
|
268 |
-
<td style="text-align:center; background-color: #
|
269 |
-
<td style="text-align:center; background-color: #
|
270 |
-
<td style="text-align:center; background-color: #
|
271 |
</tr>
|
272 |
|
273 |
<tr>
|
274 |
-
<td style="text-align:left; background-color: #
|
275 |
-
<td style="text-align:center; background-color: #
|
276 |
-
<td style="text-align:center; background-color: #
|
277 |
-
<td style="text-align:center; background-color: #
|
278 |
-
<td style="text-align:center; background-color: #
|
279 |
-
<td style="text-align:center; background-color: #
|
280 |
-
<td style="text-align:center; background-color: #
|
281 |
-
<td style="text-align:center; background-color: #
|
282 |
-
<td style="text-align:center; background-color: #
|
283 |
-
<td style="text-align:center; background-color: #
|
284 |
-
<td style="text-align:center; background-color: #
|
285 |
-
<td style="text-align:center; background-color: #
|
286 |
-
<td style="text-align:center; background-color: #
|
287 |
</tr>
|
288 |
|
289 |
<tr>
|
290 |
-
<td style="text-align:left; background-color: #
|
291 |
-
<td style="text-align:center; background-color: #
|
292 |
-
<td style="text-align:center; background-color: #
|
293 |
-
<td style="text-align:center; background-color: #
|
294 |
-
<td style="text-align:center; background-color: #
|
295 |
-
<td style="text-align:center; background-color: #
|
296 |
-
<td style="text-align:center; background-color: #
|
297 |
-
<td style="text-align:center; background-color: #
|
298 |
-
<td style="text-align:center; background-color: #
|
299 |
-
<td style="text-align:center; background-color: #
|
300 |
-
<td style="text-align:center; background-color: #
|
301 |
-
<td style="text-align:center; background-color: #
|
302 |
-
<td style="text-align:center; background-color: #
|
303 |
</tr>
|
304 |
|
305 |
<tr>
|
306 |
-
<td style="text-align:left; background-color: #
|
307 |
-
<td style="text-align:center; background-color: #
|
308 |
-
<td style="text-align:center; background-color: #
|
309 |
-
<td style="text-align:center; background-color: #
|
310 |
-
<td style="text-align:center; background-color: #
|
311 |
-
<td style="text-align:center; background-color: #
|
312 |
-
<td style="text-align:center; background-color: #
|
313 |
-
<td style="text-align:center; background-color: #
|
314 |
-
<td style="text-align:center; background-color: #
|
315 |
-
<td style="text-align:center; background-color: #
|
316 |
-
<td style="text-align:center; background-color: #
|
317 |
-
<td style="text-align:center; background-color: #
|
318 |
-
<td style="text-align:center; background-color: #
|
319 |
</tr>
|
320 |
|
321 |
<tr>
|
322 |
-
<td style="text-align:left; background-color: #
|
323 |
-
<td style="text-align:center; background-color: #
|
324 |
-
<td style="text-align:center; background-color: #
|
325 |
-
<td style="text-align:center; background-color: #
|
326 |
-
<td style="text-align:center; background-color: #
|
327 |
-
<td style="text-align:center; background-color: #
|
328 |
-
<td style="text-align:center; background-color: #
|
329 |
-
<td style="text-align:center; background-color: #
|
330 |
-
<td style="text-align:center; background-color: #
|
331 |
-
<td style="text-align:center; background-color: #
|
332 |
-
<td style="text-align:center; background-color: #
|
333 |
-
<td style="text-align:center; background-color: #
|
334 |
-
<td style="text-align:center; background-color: #
|
335 |
</tr>
|
336 |
<tr>
|
337 |
-
<td style="text-align:left; background-color: #
|
338 |
-
<td style="text-align:center; background-color: #
|
339 |
-
<td style="text-align:center; background-color: #
|
340 |
-
<td style="text-align:center; background-color: #
|
341 |
-
<td style="text-align:center; background-color: #
|
342 |
-
<td style="text-align:center; background-color: #
|
343 |
-
<td style="text-align:center; background-color: #
|
344 |
-
<td style="text-align:center; background-color: #
|
345 |
-
<td style="text-align:center; background-color: #
|
346 |
-
<td style="text-align:center; background-color: #
|
347 |
-
<td style="text-align:center; background-color: #
|
348 |
-
<td style="text-align:center; background-color: #
|
349 |
-
<td style="text-align:center; background-color: #
|
350 |
</tr>
|
351 |
|
352 |
<tr>
|
353 |
-
<td style="text-align:left; background-color: #
|
354 |
-
<td style="text-align:center; background-color: #
|
355 |
-
<td style="text-align:center; background-color: #
|
356 |
-
<td style="text-align:center; background-color: #
|
357 |
-
<td style="text-align:center; background-color: #
|
358 |
-
<td style="text-align:center; background-color: #
|
359 |
-
<td style="text-align:center; background-color: #
|
360 |
-
<td style="text-align:center; background-color: #
|
361 |
-
<td style="text-align:center; background-color: #
|
362 |
-
<td style="text-align:center; background-color: #
|
363 |
-
<td style="text-align:center; background-color: #
|
364 |
-
<td style="text-align:center; background-color: #
|
365 |
-
<td style="text-align:center; background-color: #
|
366 |
</tr>
|
367 |
<tr>
|
368 |
<td style="text-align:left; background-color: #DAE8FF; color: black;"><b>Granite-3.3-8B-Instruct</b></td>
|
@@ -387,7 +387,7 @@ By implementing this innovative prevention strategy, we can significantly reduce
|
|
387 |
<tr>
|
388 |
<th style="text-align:left; background-color: #001d6c; color: white;">Models</th>
|
389 |
<th style="text-align:center; background-color: #001d6c; color: white;">AIME24</th>
|
390 |
-
<th style="text-align:center; background-color: #001d6c; color: white;">
|
391 |
</tr></thead>
|
392 |
<tbody>
|
393 |
<tr>
|
@@ -401,19 +401,19 @@ By implementing this innovative prevention strategy, we can significantly reduce
|
|
401 |
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 35.54 </td>
|
402 |
</tr>
|
403 |
<tr>
|
404 |
-
<td style="text-align:left; background-color: #
|
405 |
-
<td style="text-align:center; background-color: #
|
406 |
-
<td style="text-align:center; background-color: #
|
407 |
</tr>
|
408 |
<tr>
|
409 |
-
<td style="text-align:left; background-color: #
|
410 |
-
<td style="text-align:center; background-color: #
|
411 |
-
<td style="text-align:center; background-color: #
|
412 |
</tr>
|
413 |
<tr>
|
414 |
-
<td style="text-align:left; background-color: #
|
415 |
-
<td style="text-align:center; background-color: #
|
416 |
-
<td style="text-align:center; background-color: #
|
417 |
</tr>
|
418 |
<tr>
|
419 |
<td style="text-align:left; background-color: #DAE8FF; color: black;"><b>Granite-3.3-8B-Instruct</b></td>
|
@@ -527,15 +527,4 @@ Granite-3.3-2B-Instruct builds upon Granite-3.3-2B-Base, leveraging both permiss
|
|
527 |
|
528 |
|
529 |
|
530 |
-
<p><a href="#fnref1" title="Jump back to reference">[1]</a> Evaluated using <a href="https://github.com/allenai/olmes">OLMES</a> (except
|
531 |
-
<!-- ## Citation
|
532 |
-
```
|
533 |
-
@misc{granite-models,
|
534 |
-
author = {author 1, author2, ...},
|
535 |
-
title = {},
|
536 |
-
journal = {},
|
537 |
-
volume = {},
|
538 |
-
year = {2024},
|
539 |
-
url = {https://arxiv.org/abs/0000.00000},
|
540 |
-
}
|
541 |
-
``` -->
|
|
|
207 |
**Evaluation Results:**
|
208 |
<table>
|
209 |
<thead>
|
210 |
+
<caption style="text-align:center"><b>Comparison with different models over various benchmarks<sup id="fnref1"><a href="#fn1">1</a></sup>. Scores of AlpacaEval-2.0 and Arena-Hard are calculated with thinking=True</b></caption>
|
211 |
<tr>
|
212 |
<th style="text-align:left; background-color: #001d6c; color: white;">Models</th>
|
213 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">Arena-Hard</th>
|
214 |
<th style="text-align:center; background-color: #001d6c; color: white;">AlpacaEval-2.0</th>
|
215 |
<th style="text-align:center; background-color: #001d6c; color: white;">MMLU</th>
|
216 |
<th style="text-align:center; background-color: #001d6c; color: white;">PopQA</th>
|
|
|
255 |
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">83.23</td>
|
256 |
</tr>
|
257 |
<tr>
|
258 |
+
<td style="text-align:left; background-color: #DAE8FF; color: black;"><b>Granite-3.3-2B-Instruct</b></td>
|
259 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;"> 28.86 </td>
|
260 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;"> 43.45 </td>
|
261 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;"> 55.88 </td>
|
262 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;"> 18.4 </td>
|
263 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;"> 58.97 </td>
|
264 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;"> 52.51 </td>
|
265 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;"> 35.98 </td>
|
266 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;"> 72.48 </td>
|
267 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;"> 80.51 </td>
|
268 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;"> 75.68 </td>
|
269 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;"> 65.8 </td>
|
270 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">87.47</td>
|
271 |
</tr>
|
272 |
|
273 |
<tr>
|
274 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Llama-3.1-8B-Instruct</td>
|
275 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">36.43</td>
|
276 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">27.22</td>
|
277 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">69.15</td>
|
278 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">28.79</td>
|
279 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">52.79</td>
|
280 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">72.66</td>
|
281 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">61.48</td>
|
282 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">83.24</td>
|
283 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">85.32</td>
|
284 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">80.15</td>
|
285 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">79.10</td>
|
286 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">83.43</td>
|
287 |
</tr>
|
288 |
|
289 |
<tr>
|
290 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">DeepSeek-R1-Distill-Llama-8B</td>
|
291 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">17.17</td>
|
292 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">21.85</td>
|
293 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">45.80</td>
|
294 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">13.25</td>
|
295 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">47.43</td>
|
296 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">65.71</td>
|
297 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">44.46</td>
|
298 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">72.18</td>
|
299 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">67.54</td>
|
300 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">62.91</td>
|
301 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">66.50</td>
|
302 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">42.87</td>
|
303 |
</tr>
|
304 |
|
305 |
<tr>
|
306 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Qwen-2.5-7B-Instruct</td>
|
307 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">25.44</td>
|
308 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">30.34</td>
|
309 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">74.30</td>
|
310 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">18.12</td>
|
311 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">63.06</td>
|
312 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">70.40</td>
|
313 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">54.71</td>
|
314 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">84.46</td>
|
315 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">93.35</td>
|
316 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">89.91</td>
|
317 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">74.90</td>
|
318 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">81.90</td>
|
319 |
</tr>
|
320 |
|
321 |
<tr>
|
322 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">DeepSeek-R1-Distill-Qwen-7B</td>
|
323 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">10.36</td>
|
324 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">15.35</td>
|
325 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">50.72</td>
|
326 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">9.94</td>
|
327 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">47.14</td>
|
328 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">65.04</td>
|
329 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">42.76</td>
|
330 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">78.47</td>
|
331 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">79.89</td>
|
332 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">78.43</td>
|
333 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">59.10</td>
|
334 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">42.45</td>
|
335 |
</tr>
|
336 |
<tr>
|
337 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Granite-3.1-8B-Instruct</td>
|
338 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">37.58</td>
|
339 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">30.34</td>
|
340 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">66.77</td>
|
341 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">28.7</td>
|
342 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">65.84</td>
|
343 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">68.55</td>
|
344 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">50.78</td>
|
345 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">79.15</td>
|
346 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">89.63</td>
|
347 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">85.79</td>
|
348 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">73.20</td>
|
349 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">85.73</td>
|
350 |
</tr>
|
351 |
|
352 |
<tr>
|
353 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Granite-3.2-8B-Instruct</td>
|
354 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">55.25</td>
|
355 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">61.19</td>
|
356 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">66.79</td>
|
357 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">28.04</td>
|
358 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">66.92</td>
|
359 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">64.77</td>
|
360 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">50.95</td>
|
361 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">81.65</td>
|
362 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">89.35</td>
|
363 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">85.72</td>
|
364 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">74.31</td>
|
365 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">84.7</td>
|
366 |
</tr>
|
367 |
<tr>
|
368 |
<td style="text-align:left; background-color: #DAE8FF; color: black;"><b>Granite-3.3-8B-Instruct</b></td>
|
|
|
387 |
<tr>
|
388 |
<th style="text-align:left; background-color: #001d6c; color: white;">Models</th>
|
389 |
<th style="text-align:center; background-color: #001d6c; color: white;">AIME24</th>
|
390 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">MATH-500</th>
|
391 |
</tr></thead>
|
392 |
<tbody>
|
393 |
<tr>
|
|
|
401 |
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 35.54 </td>
|
402 |
</tr>
|
403 |
<tr>
|
404 |
+
<td style="text-align:left; background-color: #DAE8FF; color: black;"><b>Granite-3.3-2B-Instruct</b></td>
|
405 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;"> 3.28 </td>
|
406 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;"> 58.09 </td>
|
407 |
</tr>
|
408 |
<tr>
|
409 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Granite-3.1-8B-Instruct</td>
|
410 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 1.97 </td>
|
411 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 48.73 </td>
|
412 |
</tr>
|
413 |
<tr>
|
414 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Granite-3.2-8B-Instruct</td>
|
415 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 2.43 </td>
|
416 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 52.8 </td>
|
417 |
</tr>
|
418 |
<tr>
|
419 |
<td style="text-align:left; background-color: #DAE8FF; color: black;"><b>Granite-3.3-8B-Instruct</b></td>
|
|
|
527 |
|
528 |
|
529 |
|
530 |
+
<p><a href="#fnref1" title="Jump back to reference">[1]</a> Evaluated using <a href="https://github.com/allenai/olmes">OLMES</a> (except AttaQ and Arena-Hard scores)</p>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|