From b4910fb37356f17d35a681a4ffcd505f1ef6736b Mon Sep 17 00:00:00 2001
From: Jun Siang Cheah <git@jscheah.me>
Date: Wed, 25 Sep 2024 20:24:57 +0100
Subject: [PATCH] groq: add llama 3.2

---
 README.md                    | 6 +++++-
 src/pull_available_models.py | 4 ++++
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 6724f01..c6bd95c 100644
--- a/README.md
+++ b/README.md
@@ -20,7 +20,7 @@ This lists various services that provide free access or credits towards API-base
         </tr>
     </thead>
     <tbody>
-<tr><td rowspan="13"><a href="https://console.groq.com" target="_blank">Groq</a></td><td rowspan="13"></td><td>Distil Whisper Large v3</td><td>7200 audio-seconds/minute<br>2000 requests/day</td></tr>
+<tr><td rowspan="17"><a href="https://console.groq.com" target="_blank">Groq</a></td><td rowspan="17"></td><td>Distil Whisper Large v3</td><td>7200 audio-seconds/minute<br>2000 requests/day</td></tr>
 <tr><td>Gemma 2 9B Instruct</td><td>14400 requests/day<br>15000 tokens/minute</td></tr>
 <tr><td>Gemma 7B Instruct</td><td>14400 requests/day<br>15000 tokens/minute</td></tr>
 <tr><td>LLaVA 1.5 7B</td><td>14400 requests/day<br>30000 tokens/minute</td></tr>
@@ -30,6 +30,10 @@ This lists various services that provide free access or credits towards API-base
 <tr><td>Llama 3 8B - Groq Tool Use Preview</td><td>14400 requests/day<br>15000 tokens/minute</td></tr>
 <tr><td>Llama 3.1 70B</td><td>14400 requests/day<br>20000 tokens/minute</td></tr>
 <tr><td>Llama 3.1 8B</td><td>14400 requests/day<br>20000 tokens/minute</td></tr>
+<tr><td>Llama 3.2 11B</td><td>7000 requests/day<br>7000 tokens/minute</td></tr>
+<tr><td>Llama 3.2 1B</td><td>7000 requests/day<br>7000 tokens/minute</td></tr>
+<tr><td>Llama 3.2 3B</td><td>7000 requests/day<br>7000 tokens/minute</td></tr>
+<tr><td>Llama 3.2 90B</td><td>7000 requests/day<br>7000 tokens/minute</td></tr>
 <tr><td>Llama Guard 3 8B</td><td>14400 requests/day<br>15000 tokens/minute</td></tr>
 <tr><td>Mixtral 8x7B</td><td>14400 requests/day<br>5000 tokens/minute</td></tr>
 <tr><td>Whisper Large v3</td><td>7200 audio-seconds/minute<br>2000 requests/day</td></tr>
diff --git a/src/pull_available_models.py b/src/pull_available_models.py
index 11431a0..ca2f786 100644
--- a/src/pull_available_models.py
+++ b/src/pull_available_models.py
@@ -106,6 +106,10 @@ MODEL_TO_NAME_MAPPING = {
     "qwen/qwen-2-vl-7b-instruct:free": "Qwen2-VL 7B Instruct",
     'qwen/qwen2-vl-72b-instruct': "Qwen2-VL 72B Instruct",
     'qwen/qwen2.5-72b-instruct': "Qwen2.5 72B Instruct",
+    "llama-3.2-90b-text-preview": "Llama 3.2 90B",
+    "llama-3.2-3b-preview": "Llama 3.2 3B",
+    "llama-3.2-11b-text-preview": "Llama 3.2 11B",
+    "llama-3.2-1b-preview": "Llama 3.2 1B",
 }