improved description

README.md

@@ -1,13 +1,30 @@
 ---
 license: mit
-base_model:
-- deepseek-ai/DeepSeek-R1-Distill-Llama-70B
+base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-70B
+pipeline_tag: text-generation
 library_name: transformers
+tags:
+- deepseek
+- llama
+- quantization
+- fp8
+- llm-compressor
+- text-generation
 ---
 
-The [deepseek-ai/DeepSeek-R1-Distill-Llama-70B](https://huggingface.co/perplexity-ai/r1-1776-distill-llama-70b) model quantized to fp8.
+# DeepSeek-R1-Distill-Llama-70B-FP8-Dynamic
+FP8 dynamic quantization pipeline for DeepSeek-R1-Distill-Llama-70B using `llm_compressor`.
 
-# quantization using llm_compressor
+---
+## Overview
+- This repository demonstrates how to apply FP8 dynamic quantization to the DeepSeek-R1-Distill-Llama-70B model.
+- The goal is to reduce memory usage and improve inference efficiency while maintaining strong performance for large language model tasks.
+
+> ⚠️ This is a quantization pipeline, not a pre-quantized checkpoint.
+
+---
+
+## Usage
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
 from llmcompressor.transformers import oneshot