From a70e88f514b4190342addf9a618364434e7d8a36 Mon Sep 17 00:00:00 2001
From: Jun Siang Cheah <git@jscheah.me>
Date: Fri, 17 Jan 2025 20:18:06 +0000
Subject: [PATCH] Update README and model mapping with new model details

---
 README.md                    | 16 ++++++----------
 src/pull_available_models.py | 10 ++++------
 2 files changed, 10 insertions(+), 16 deletions(-)

diff --git a/README.md b/README.md
index 3f35e58..609baee 100644
--- a/README.md
+++ b/README.md
@@ -112,15 +112,11 @@ This lists various services that provide free access or credits towards API-base
 <tr><td>Qwen 2.5 Coder 32B</td><td>20 requests/minute</td></tr>
 <tr><td>QwQ 32B Preview</td><td>10 requests/minute</td></tr>
 <tr>
-        <td rowspan="3"><a href="https://cloud.cerebras.ai/" target="_blank">Cerebras</a></td>
-        <td rowspan="3">Free tier restricted to 8K context</td>
+        <td rowspan="2"><a href="https://cloud.cerebras.ai/" target="_blank">Cerebras</a></td>
+        <td rowspan="2">Free tier restricted to 8K context</td>
         <td>Llama 3.1 8B</td>
         <td>30 requests/minute<br>60,000 tokens/minute<br>900 requests/hour<br>1,000,000 tokens/hour<br>14,400 requests/day<br>1,000,000 tokens/day</td>
     </tr>
-    <tr>
-        <td>Llama 3.1 70B</td>
-        <td>30 requests/minute<br>60,000 tokens/minute<br>900 requests/hour<br>1,000,000 tokens/hour<br>14,400 requests/day<br>1,000,000 tokens/day</td>
-    </tr>
     <tr>
         <td>Llama 3.3 70B</td>
         <td>30 requests/minute<br>60,000 tokens/minute<br>900 requests/hour<br>1,000,000 tokens/hour<br>14,400 requests/day<br>1,000,000 tokens/day</td>
@@ -140,26 +136,26 @@ This lists various services that provide free access or credits towards API-base
 <tr><td>Mixtral 8x7B</td><td>14,400 requests/day<br>5,000 tokens/minute</td></tr>
 <tr><td>Whisper Large v3</td><td>7,200 audio-seconds/minute<br>2,000 requests/day</td></tr>
 <tr><td>Whisper Large v3 Turbo</td><td>7,200 audio-seconds/minute<br>2,000 requests/day</td></tr>
-<tr><td rowspan="8"><a href="https://console.scaleway.com/generative-api/models" target="_blank">Scaleway Generative APIs (Free Beta)</a></td><td rowspan="8"></td><td>BGE-Multilingual-Gemma2</td><td>600 requests/minute<br>1,000,000 tokens/minute</td></tr>
+<tr><td rowspan="8"><a href="https://console.scaleway.com/generative-api/models" target="_blank">Scaleway Generative APIs (Free Beta)</a></td><td rowspan="8"></td><td>BGE-Multilingual-Gemma2</td><td>100 requests/minute<br>200,000 tokens/minute</td></tr>
 <tr><td>Llama 3.1 70B Instruct</td><td>300 requests/minute<br>100,000 tokens/minute</td></tr>
 <tr><td>Llama 3.1 8B Instruct</td><td>300 requests/minute<br>100,000 tokens/minute</td></tr>
+<tr><td>Llama 3.3 70B Instruct</td><td></td></tr>
 <tr><td>Mistral Nemo 2407</td><td>300 requests/minute<br>100,000 tokens/minute</td></tr>
 <tr><td>Pixtral 12B (2409)</td><td>300 requests/minute<br>100,000 tokens/minute</td></tr>
 <tr><td>Qwen2.5 Coder 32B Instruct</td><td></td></tr>
-<tr><td>llama-3.3-70b-instruct</td><td></td></tr>
-<tr><td>sentence-t5-xxl</td><td>600 requests/minute<br>1,000,000 tokens/minute</td></tr>
+<tr><td>sentence-t5-xxl</td><td>100 requests/minute<br>200,000 tokens/minute</td></tr>
 <tr><td rowspan="12"><a href="https://endpoints.ai.cloud.ovh.net/" target="_blank">OVH AI Endpoints (Free Beta)</a></td><td rowspan="12"></td><td>CodeLlama 13B Instruct</td><td>12 requests/minute</td></tr>
 <tr><td>Codestral Mamba 7B v0.1</td><td>12 requests/minute</td></tr>
 <tr><td>Llama 2 13B Chat</td><td>12 requests/minute</td></tr>
 <tr><td>Llama 3 70B Instruct</td><td>12 requests/minute</td></tr>
 <tr><td>Llama 3 8B Instruct</td><td>12 requests/minute</td></tr>
 <tr><td>Llama 3.1 70B Instruct</td><td>12 requests/minute</td></tr>
+<tr><td>Llava Next Mistral 7B</td><td>12 requests/minute</td></tr>
 <tr><td>Mathstral 7B v0.1</td><td>12 requests/minute</td></tr>
 <tr><td>Mistral 7B Instruct</td><td>12 requests/minute</td></tr>
 <tr><td>Mistral Nemo 2407</td><td>12 requests/minute</td></tr>
 <tr><td>Mixtral 8x22B Instruct</td><td>12 requests/minute</td></tr>
 <tr><td>Mixtral 8x7B Instruct</td><td>12 requests/minute</td></tr>
-<tr><td>llava-next-mistral-7b</td><td>12 requests/minute</td></tr>
 <tr>
         <td><a href="https://together.ai">Together</a></td>
         <td></td>
diff --git a/src/pull_available_models.py b/src/pull_available_models.py
index f3d271d..50634e7 100644
--- a/src/pull_available_models.py
+++ b/src/pull_available_models.py
@@ -168,6 +168,8 @@ MODEL_TO_NAME_MAPPING = {
     "meta-llama/meta-llama-3.1-405b-instruct-virtuals": "Llama 3.1 405B Instruct Virtuals",
     "llama-3.1-8b-instruct": "Llama 3.1 8B Instruct",
     "deepseek-ai/deepseek-v3": "DeepSeek V3",
+    "llava-next-mistral-7b": "Llava Next Mistral 7B",
+    "llama-3.3-70b-instruct": "Llama 3.3 70B Instruct",
 }
 
 
@@ -861,15 +863,11 @@ def main():
         table += "</tr>\n"
 
     table += """<tr>
-        <td rowspan="3"><a href="https://cloud.cerebras.ai/" target="_blank">Cerebras</a></td>
-        <td rowspan="3">Free tier restricted to 8K context</td>
+        <td rowspan="2"><a href="https://cloud.cerebras.ai/" target="_blank">Cerebras</a></td>
+        <td rowspan="2">Free tier restricted to 8K context</td>
         <td>Llama 3.1 8B</td>
         <td>30 requests/minute<br>60,000 tokens/minute<br>900 requests/hour<br>1,000,000 tokens/hour<br>14,400 requests/day<br>1,000,000 tokens/day</td>
     </tr>
-    <tr>
-        <td>Llama 3.1 70B</td>
-        <td>30 requests/minute<br>60,000 tokens/minute<br>900 requests/hour<br>1,000,000 tokens/hour<br>14,400 requests/day<br>1,000,000 tokens/day</td>
-    </tr>
     <tr>
         <td>Llama 3.3 70B</td>
         <td>30 requests/minute<br>60,000 tokens/minute<br>900 requests/hour<br>1,000,000 tokens/hour<br>14,400 requests/day<br>1,000,000 tokens/day</td>