From 3811cf43c92f1fc9597077b5065acf0ddeae82bb Mon Sep 17 00:00:00 2001
From: Heyang Sun <60865256+Uxito-Ada@users.noreply.github.com>
Date: Thu, 7 Dec 2023 16:02:20 +0800
Subject: [PATCH] [LLM] update AWQ documents (#9623)

* [LLM] update AWQ and verified models' documents

* refine

* refine links

* refine
---
 .../Advanced-Quantizations/AWQ/README.md                    | 6 ++++--
 .../Advanced-Quantizations/AWQ/README.md                    | 6 ++++--
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/python/llm/example/CPU/HF-Transformers-AutoModels/Advanced-Quantizations/AWQ/README.md b/python/llm/example/CPU/HF-Transformers-AutoModels/Advanced-Quantizations/AWQ/README.md
index f3f8755b..918499da 100644
--- a/python/llm/example/CPU/HF-Transformers-AutoModels/Advanced-Quantizations/AWQ/README.md
+++ b/python/llm/example/CPU/HF-Transformers-AutoModels/Advanced-Quantizations/AWQ/README.md
@@ -5,9 +5,11 @@ This example shows how to directly run 4-bit AWQ models using BigDL-LLM on Intel
 - [Llama-2-7B-Chat-AWQ](https://huggingface.co/TheBloke/Llama-2-7B-Chat-AWQ)
 - [Mistral-7B-Instruct-v0.1-AWQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-AWQ)
 - [Mistral-7B-v0.1-AWQ](https://huggingface.co/TheBloke/Mistral-7B-v0.1-AWQ)
+- [vicuna-7B-v1.5-AWQ](https://huggingface.co/TheBloke/vicuna-7B-v1.5-AWQ)
+- [vicuna-13B-v1.5-AWQ](https://huggingface.co/TheBloke/vicuna-13B-v1.5-AWQ)
 
 ## Requirements
-To run these examples with BigDL-LLM, we have some recommended requirements for your machine, please refer to [here](../README.md#recommended-requirements) for more information.
+To run these examples with BigDL-LLM, we have some recommended requirements for your machine, please refer to [here](../../../README.md#system-support) for more information.
 
 ## Example: Predict Tokens using `generate()` API
 In the example [generate.py](./generate.py), we show a basic use case for a AWQ model to predict the next N tokens using `generate()` API, with BigDL-LLM INT4 optimizations.
@@ -73,4 +75,4 @@ What is AI?
 ### RESPONSE:
 
 Artificial intelligence (AI) is the ability of machines to perform tasks that typically require human intelligence, such as learning, problem-solving, decision
-```
\ No newline at end of file
+```
diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Advanced-Quantizations/AWQ/README.md b/python/llm/example/GPU/HF-Transformers-AutoModels/Advanced-Quantizations/AWQ/README.md
index 52335c2d..c5464055 100644
--- a/python/llm/example/GPU/HF-Transformers-AutoModels/Advanced-Quantizations/AWQ/README.md
+++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Advanced-Quantizations/AWQ/README.md
@@ -5,9 +5,11 @@ This example shows how to directly run 4-bit AWQ models using BigDL-LLM on Intel
 - [Llama-2-7B-Chat-AWQ](https://huggingface.co/TheBloke/Llama-2-7B-Chat-AWQ)
 - [Mistral-7B-Instruct-v0.1-AWQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-AWQ)
 - [Mistral-7B-v0.1-AWQ](https://huggingface.co/TheBloke/Mistral-7B-v0.1-AWQ)
+- [vicuna-7B-v1.5-AWQ](https://huggingface.co/TheBloke/vicuna-7B-v1.5-AWQ)
+- [vicuna-13B-v1.5-AWQ](https://huggingface.co/TheBloke/vicuna-13B-v1.5-AWQ)
 
 ## Requirements
-To run these examples with BigDL-LLM, we have some recommended requirements for your machine, please refer to [here](../README.md#recommended-requirements) for more information.
+To run these examples with BigDL-LLM, we have some recommended requirements for your machine, please refer to [here](../../../README.md#requirements) for more information.
 
 ## Example: Predict Tokens using `generate()` API
 In the example [generate.py](./generate.py), we show a basic use case for a AWQ model to predict the next N tokens using `generate()` API, with BigDL-LLM INT4 optimizations.
@@ -67,4 +69,4 @@ What is AI?
 ### RESPONSE:
 
 Artificial intelligence (AI) is the ability of machines to perform tasks that typically require human intelligence, such as learning, problem-solving, decision
-```
\ No newline at end of file
+```