Update README.md

README.md

@@ -14,23 +14,13 @@ base_model: QCRI/Fanar-1-9B-Instruct
 
 # Fanar-1-9B-Instruct-AWQ
 
-AWQ 4-bit quantized version of [QCRI/Fanar-1-9B-Instruct](https://huggingface.co/QCRI/Fanar-1-9B-Instruct).
+GPTQ 4-bit quantized version of [QCRI/Fanar-1-9B-Instruct](https://huggingface.co/QCRI/Fanar-1-9B-Instruct).
 
-## Quick Start
 
-```python
-from vllm import LLM
-
-llm = LLM(
-    model="buthainaaa/Fanar-1-9B-Instruct-GPTQ",
-    quantization="awq",
-    dtype="half"
-)
-```
 
 ## Details
 
-- **Quantization:** AWQ 4-bit (w4a16)
+- **Quantization:** GPTQ 4-bit (w4a16)
 - **Size:** ~5GB (vs ~18GB original)
 - **Memory:** 75% reduction
 - **Quality:** 95%+ retention