DhiyaEddine wdevazelhes commited on
Commit
677a2de
1 Parent(s): c8d5bc8

Update README.md (#6)

Browse files

- Update README.md (44e53a1bce02d9da2e8373f49ad10b711826e9a5)


Co-authored-by: William de Vazelhes <[email protected]>

Files changed (1) hide show
  1. README.md +0 -14
README.md CHANGED
@@ -149,7 +149,6 @@ Falcon3-7B is trained on 256 H100 nodes (world size 2048).
149
  <th>Llama-3.2-1B</th>
150
  <th>Qwen2.5-1.5B</th>
151
  <th>SmolLM2-1.7B</th>
152
- <th>gemma-2-2b</th>
153
  <th>Falcon3-1B-Base</th>
154
  </tr>
155
  </thead>
@@ -160,7 +159,6 @@ Falcon3-7B is trained on 256 H100 nodes (world size 2048).
160
  <td>31.1</td>
161
  <td>61.0</td>
162
  <td>50.1</td>
163
- <td>53.0</td>
164
  <td>42.5</td>
165
  </tr>
166
  <tr>
@@ -168,7 +166,6 @@ Falcon3-7B is trained on 256 H100 nodes (world size 2048).
168
  <td>11.7</td>
169
  <td>28.4</td>
170
  <td>21.3</td>
171
- <td>22.1</td>
172
  <td>16.1</td>
173
  </tr>
174
  <tr>
@@ -176,7 +173,6 @@ Falcon3-7B is trained on 256 H100 nodes (world size 2048).
176
  <td>14.8</td>
177
  <td>26.0</td>
178
  <td>24.2</td>
179
- <td>20.3</td>
180
  <td>25.2</td>
181
  </tr>
182
  <tr>
@@ -185,7 +181,6 @@ Falcon3-7B is trained on 256 H100 nodes (world size 2048).
185
  <td>6.6</td>
186
  <td>62.2</td>
187
  <td>31.0</td>
188
- <td>25.5</td>
189
  <td>34.3</td>
190
  </tr>
191
  <tr>
@@ -193,7 +188,6 @@ Falcon3-7B is trained on 256 H100 nodes (world size 2048).
193
  <td>0.2</td>
194
  <td>6.7</td>
195
  <td>1.4</td>
196
- <td>2.6</td>
197
  <td>2.2</td>
198
  </tr>
199
  <tr>
@@ -202,7 +196,6 @@ Falcon3-7B is trained on 256 H100 nodes (world size 2048).
202
  <td>40.2</td>
203
  <td>54.8</td>
204
  <td>54.1</td>
205
- <td>53.7</td>
206
  <td>48.1</td>
207
  </tr>
208
  <tr>
@@ -210,7 +203,6 @@ Falcon3-7B is trained on 256 H100 nodes (world size 2048).
210
  <td>24.2</td>
211
  <td>28.1</td>
212
  <td>28.9</td>
213
- <td>25.5</td>
214
  <td>28.1</td>
215
  </tr>
216
  <tr>
@@ -218,7 +210,6 @@ Falcon3-7B is trained on 256 H100 nodes (world size 2048).
218
  <td>34.5</td>
219
  <td>35.5</td>
220
  <td>34.7</td>
221
- <td>42.7</td>
222
  <td>41.9</td>
223
  </tr>
224
  <tr>
@@ -226,7 +217,6 @@ Falcon3-7B is trained on 256 H100 nodes (world size 2048).
226
  <td>31.2</td>
227
  <td>41.1</td>
228
  <td>34.2</td>
229
- <td>36.8</td>
230
  <td>36.0</td>
231
  </tr>
232
  <tr>
@@ -235,7 +225,6 @@ Falcon3-7B is trained on 256 H100 nodes (world size 2048).
235
  <td>74.5</td>
236
  <td>76.0</td>
237
  <td>77.5</td>
238
- <td>79.2</td>
239
  <td>74.5</td>
240
  </tr>
241
  <tr>
@@ -243,7 +232,6 @@ Falcon3-7B is trained on 256 H100 nodes (world size 2048).
243
  <td>88.5</td>
244
  <td>93.1</td>
245
  <td>90.8</td>
246
- <td>95.7</td>
247
  <td>91.1</td>
248
  </tr>
249
  <tr>
@@ -251,7 +239,6 @@ Falcon3-7B is trained on 256 H100 nodes (world size 2048).
251
  <td>60.4</td>
252
  <td>63.0</td>
253
  <td>66.1</td>
254
- <td>68.6</td>
255
  <td>61.2</td>
256
  </tr>
257
  <tr>
@@ -259,7 +246,6 @@ Falcon3-7B is trained on 256 H100 nodes (world size 2048).
259
  <td>37.4</td>
260
  <td>40.4</td>
261
  <td>44.0</td>
262
- <td>41.8</td>
263
  <td>41.0</td>
264
  </tr>
265
  </tbody>
 
149
  <th>Llama-3.2-1B</th>
150
  <th>Qwen2.5-1.5B</th>
151
  <th>SmolLM2-1.7B</th>
 
152
  <th>Falcon3-1B-Base</th>
153
  </tr>
154
  </thead>
 
159
  <td>31.1</td>
160
  <td>61.0</td>
161
  <td>50.1</td>
 
162
  <td>42.5</td>
163
  </tr>
164
  <tr>
 
166
  <td>11.7</td>
167
  <td>28.4</td>
168
  <td>21.3</td>
 
169
  <td>16.1</td>
170
  </tr>
171
  <tr>
 
173
  <td>14.8</td>
174
  <td>26.0</td>
175
  <td>24.2</td>
 
176
  <td>25.2</td>
177
  </tr>
178
  <tr>
 
181
  <td>6.6</td>
182
  <td>62.2</td>
183
  <td>31.0</td>
 
184
  <td>34.3</td>
185
  </tr>
186
  <tr>
 
188
  <td>0.2</td>
189
  <td>6.7</td>
190
  <td>1.4</td>
 
191
  <td>2.2</td>
192
  </tr>
193
  <tr>
 
196
  <td>40.2</td>
197
  <td>54.8</td>
198
  <td>54.1</td>
 
199
  <td>48.1</td>
200
  </tr>
201
  <tr>
 
203
  <td>24.2</td>
204
  <td>28.1</td>
205
  <td>28.9</td>
 
206
  <td>28.1</td>
207
  </tr>
208
  <tr>
 
210
  <td>34.5</td>
211
  <td>35.5</td>
212
  <td>34.7</td>
 
213
  <td>41.9</td>
214
  </tr>
215
  <tr>
 
217
  <td>31.2</td>
218
  <td>41.1</td>
219
  <td>34.2</td>
 
220
  <td>36.0</td>
221
  </tr>
222
  <tr>
 
225
  <td>74.5</td>
226
  <td>76.0</td>
227
  <td>77.5</td>
 
228
  <td>74.5</td>
229
  </tr>
230
  <tr>
 
232
  <td>88.5</td>
233
  <td>93.1</td>
234
  <td>90.8</td>
 
235
  <td>91.1</td>
236
  </tr>
237
  <tr>
 
239
  <td>60.4</td>
240
  <td>63.0</td>
241
  <td>66.1</td>
 
242
  <td>61.2</td>
243
  </tr>
244
  <tr>
 
246
  <td>37.4</td>
247
  <td>40.4</td>
248
  <td>44.0</td>
 
249
  <td>41.0</td>
250
  </tr>
251
  </tbody>