wip

README.md

@@ -32,7 +32,7 @@ language models. picoLLM Inference Engine is:
 
 - [picoLLM](#picollm)
     - [Table of Contents](#table-of-contents)
-    - [Supported Models](#supported-models)
+    - [Models](#models)
     - [AccessKey](#accesskey)
     - [Demos](#demos)
       - [Python](#python-demos)
@@ -50,8 +50,16 @@ language models. picoLLM Inference Engine is:
     - [Releases](#releases)
     - [FAQ](#faq)
 
-## Supported Models
+## Models
 
+PicoLLM Inference Engine supports the following open-weight models. You can download them from
+[Picovoice Console](https://console.picovoice.ai/). 
+
+- Gemma
+    - `gemma-2b`
+    - `gemma-2b-it`
+    - `gemma-7b`
+    - `gemma-7b-it`
 - Llama-2
     - `llama-2-7b`
     - `llama-2-7b-chat`
@@ -61,21 +69,16 @@ language models. picoLLM Inference Engine is:
     - `llama-2-70b-chat`
 - Llama-3
     - `llama-3-8b`
-    - `llama-3-8b-chat`
+    - `llama-3-8b-instruct`
     - `llama-3-70b`
-    - `llama-3-70b-chat`
+    - `llama-3-70b-instruct`
 - Mistral
     - `mistral-7b-v0.1`
     - `mistral-7b-instruct-v0.1`
     - `mistral-7b-instruct-v0.2`
 - Mixtral
     - `mixtral-8x7b-v0.1`
     - `mixtral-8x7b-instruct-v0.1`
-- Gemma
-    - `gemma-2b`
-    - `gemma-2b-it`
-    - `gemma-7b`
-    - `gemma-7b-it`
 - Phi-2
 
 ## AccessKey