update hyperbolic with 405B base

README.md

@@ -76,9 +76,10 @@ This lists various services that provide free access or credits towards API-base
             <td>Dynamic Rate Limits.<br>Limited to models smaller than 10GB.<br>Some popular models are supported even if they exceed 10GB.</td>
             <td>Various open models</td>
             <td></td>
-        </tr><tr><td rowspan="4"><a href="https://app.hyperbolic.xyz/">Hyperbolic (Free Testing Period)</a></td><td rowspan="4"></td><td>Llama 3 70B Instruct</td><td>200 requests/minute</td></tr>
+        </tr><tr><td rowspan="5"><a href="https://app.hyperbolic.xyz/">Hyperbolic (Free Testing Period)</a></td><td rowspan="5"></td><td>Llama 3 70B Instruct</td><td>200 requests/minute</td></tr>
 <tr><td>Llama 3.1 70B Instruct</td><td>200 requests/minute</td></tr>
 <tr><td>Llama 3.1 405B Instruct</td><td>200 requests/minute</td></tr>
+<tr><td>Llama 3.1 405B Base (FP8)</td><td>200 requests/minute</td></tr>
 <tr><td>Llama 3.1 8B Instruct</td><td>200 requests/minute</td></tr>
 <tr><td rowspan="7"><a href="https://endpoints.ai.cloud.ovh.net/">OVH AI Endpoints (Free Alpha)</a></td><td rowspan="7">Token expires every 2 weeks.</td><td>CodeLlama 13B Instruct</td><td>12 requests/minute</td></tr>
 <tr><td>Llama 2 13B Chat</td><td>12 requests/minute</td></tr>

src/pull_available_models.py

@@ -78,6 +78,7 @@ MODEL_TO_NAME_MAPPING = {
     "meta-llama/meta-llama-3-70b-instruct": "Llama 3 70B Instruct",
     "meta-llama/meta-llama-3.1-70b-instruct": "Llama 3.1 70B Instruct",
     "meta-llama/meta-llama-3.1-405b-instruct": "Llama 3.1 405B Instruct",
+    "meta-llama/meta-llama-3.1-405b-fp8": "Llama 3.1 405B Base (FP8)",
     "meta-llama/meta-llama-3.1-8b-instruct": "Llama 3.1 8B Instruct",
     "qwen/qwen2-72b-instruct": "Qwen 2 72B Instruct",
 }