update README & demo

README.md

@@ -14,11 +14,14 @@ The current release supports:
 
 ## Contents
 
-- [Install](#install)
-- [AWQ Model Zoo](#awq-model-zoo)
-- [Examples](#examples)
-- [Usage](#usage)
-- [Reference](#reference)
+- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration \[Paper\]](#awq-activation-aware-weight-quantization-for-llm-compression-and-acceleration-paper)
+  - [Contents](#contents)
+  - [Install](#install)
+  - [AWQ Model Zoo](#awq-model-zoo)
+  - [Examples](#examples)
+  - [Usage](#usage)
+  - [Reference](#reference)
+  - [Related Projects](#related-projects)
 
 ## Install
 
@@ -81,7 +84,7 @@ python -m awq.entry --model_path /PATH/TO/OPT/opt-6.7b \
     --run_awq --dump_awq awq_cache/opt-6.7b-w4-g128.pt
 ```
 
-2. Evaluate the AWQ quantize model on WikiText-2 (simulated pseudo quantization)
+2. Evaluate the AWQ quantized model on WikiText-2 (simulated pseudo quantization)
 ```bash
 python -m awq.entry --model_path /PATH/TO/OPT/opt-6.7b \
     --tasks wikitext \

examples/chat_demo.ipynb

@@ -22,7 +22,7 @@
    "metadata": {},
    "source": [
     "In order to run this notebook, you need to install the following packages:\n",
-    "- [AWQ]()\n",
+    "- [AWQ](https://github.com/mit-han-lab/llm-awq)\n",
     "- [Pytorch](https://pytorch.org/)\n",
     "- [Accelerate](https://github.com/huggingface/accelerate)\n",
     "- [FastChat](https://github.com/lm-sys/FastChat)\n",

examples/llava_demo.ipynb

 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -8,6 +9,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -15,11 +17,12 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     "In order to run this notebook, you need to install the following packages:\n",
-    "- [AWQ]()\n",
+    "- [AWQ](https://github.com/mit-han-lab/llm-awq)\n",
     "- [Pytorch](https://pytorch.org/)\n",
     "- [Accelerate](https://github.com/huggingface/accelerate)\n",
     "- [LLaVA](https://github.com/haotian-liu/LLaVA)\n",
@@ -66,6 +69,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -104,6 +108,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -125,6 +130,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [