Deployed 8f657c7 with MkDocs version: 1.4.3

model_zoo/index.html

@@ -602,6 +602,7 @@ <h1 id="public-model-zoo">Public Model Zoo<a class="headerlink" href="#public-mo
 <th>Inference APIs Available</th>
 <th>Fine-tuning APIs Available</th>
 <th>Inference Frameworks Available</th>
+<th>Inference max total tokens (prompt + response)</th>
 </tr>
 </thead>
 <tbody>
@@ -610,144 +611,168 @@ <h1 id="public-model-zoo">Public Model Zoo<a class="headerlink" href="#public-mo
 <td>✅</td>
 <td>✅</td>
 <td>deepspeed, text-generation-inference</td>
+<td>2048</td>
 </tr>
 <tr>
 <td><code>llama-2-7b</code></td>
 <td>✅</td>
 <td>✅</td>
 <td>text-generation-inference, vllm</td>
+<td>4096</td>
 </tr>
 <tr>
 <td><code>llama-2-7b-chat</code></td>
 <td>✅</td>
 <td></td>
 <td>text-generation-inference, vllm</td>
+<td>4096</td>
 </tr>
 <tr>
 <td><code>llama-2-13b</code></td>
 <td>✅</td>
 <td></td>
 <td>text-generation-inference, vllm</td>
+<td>4096</td>
 </tr>
 <tr>
 <td><code>llama-2-13b-chat</code></td>
 <td>✅</td>
 <td></td>
 <td>text-generation-inference, vllm</td>
+<td>4096</td>
 </tr>
 <tr>
 <td><code>llama-2-70b</code></td>
 <td>✅</td>
 <td>✅</td>
 <td>text-generation-inference, vllm</td>
+<td>4096</td>
 </tr>
 <tr>
 <td><code>llama-2-70b-chat</code></td>
 <td>✅</td>
 <td></td>
 <td>text-generation-inference, vllm</td>
+<td>4096</td>
 </tr>
 <tr>
 <td><code>falcon-7b</code></td>
 <td>✅</td>
 <td></td>
 <td>text-generation-inference, vllm</td>
+<td>2048</td>
 </tr>
 <tr>
 <td><code>falcon-7b-instruct</code></td>
 <td>✅</td>
 <td></td>
 <td>text-generation-inference, vllm</td>
+<td>2048</td>
 </tr>
 <tr>
 <td><code>falcon-40b</code></td>
 <td>✅</td>
 <td></td>
 <td>text-generation-inference, vllm</td>
+<td>2048</td>
 </tr>
 <tr>
 <td><code>falcon-40b-instruct</code></td>
 <td>✅</td>
 <td></td>
 <td>text-generation-inference, vllm</td>
+<td>2048</td>
 </tr>
 <tr>
 <td><code>mpt-7b</code></td>
 <td>✅</td>
 <td></td>
 <td>deepspeed, text-generation-inference, vllm</td>
+<td>2048</td>
 </tr>
 <tr>
 <td><code>mpt-7b-instruct</code></td>
 <td>✅</td>
 <td>✅</td>
 <td>deepspeed, text-generation-inference, vllm</td>
+<td>2048</td>
 </tr>
 <tr>
 <td><code>flan-t5-xxl</code></td>
 <td>✅</td>
 <td></td>
 <td>deepspeed, text-generation-inference</td>
+<td>2048</td>
 </tr>
 <tr>
 <td><code>mistral-7b</code></td>
 <td>✅</td>
 <td>✅</td>
 <td>vllm</td>
+<td>8000</td>
 </tr>
 <tr>
 <td><code>mistral-7b-instruct</code></td>
 <td>✅</td>
 <td>✅</td>
 <td>vllm</td>
+<td>8000</td>
 </tr>
 <tr>
 <td><code>codellama-7b</code></td>
 <td>✅</td>
 <td>✅</td>
 <td>text-generation-inference, vllm</td>
+<td>16384</td>
 </tr>
 <tr>
 <td><code>codellama-7b-instruct</code></td>
 <td>✅</td>
 <td>✅</td>
 <td>text-generation-inference, vllm</td>
+<td>16384</td>
 </tr>
 <tr>
 <td><code>codellama-13b</code></td>
 <td>✅</td>
 <td>✅</td>
 <td>text-generation-inference, vllm</td>
+<td>16384</td>
 </tr>
 <tr>
 <td><code>codellama-13b-instruct</code></td>
 <td>✅</td>
 <td>✅</td>
 <td>text-generation-inference, vllm</td>
+<td>16384</td>
 </tr>
 <tr>
 <td><code>codellama-34b</code></td>
 <td>✅</td>
 <td>✅</td>
 <td>text-generation-inference, vllm</td>
+<td>16384</td>
 </tr>
 <tr>
 <td><code>codellama-34b-instruct</code></td>
 <td>✅</td>
 <td>✅</td>
 <td>text-generation-inference, vllm</td>
+<td>16384</td>
 </tr>
 <tr>
 <td><code>zephyr-7b-alpha</code></td>
 <td>✅</td>
 <td></td>
 <td>text-generation-inference, vllm</td>
+<td>32768</td>
 </tr>
 <tr>
 <td><code>zephyr-7b-beta</code></td>
 <td>✅</td>
 <td></td>
 <td>text-generation-inference, vllm</td>
+<td>32768</td>
 </tr>
 </tbody>
 </table>