Update README.md

README.md

@@ -31,7 +31,9 @@ This model was successfully tested on CUDA driver v12.1 and toolkit v11.7 with P
 git clone https://github.com/mit-han-lab/llm-awq \
 && cd llm-awq \
 && git checkout 71d8e68df78de6c0c817b029a568c064bf22132d \
-&& pip install -e .
+&& pip install -e . \
+&& cd awq/kernels \\
+&& python setup.py install
 ```
 
 ```python
@@ -80,7 +82,7 @@ output = model.generate(
     repetition_penalty=1.1,
     eos_token_id=tokenizer.eos_token_id
 )
-print(tokenizer.decode(output[0]))
+print(tokenizer.decode(output[0], skip_special_tokens=True))
 ```
 
 ## Evaluation