Upload README.md

README.md

@@ -167,7 +167,8 @@ from transformers import AutoTokenizer
 model_name_or_path = "TheBloke/Llama-2-7b-Chat-AWQ"
 
 # Load model
-model = AutoAWQForCausalLM.from_quantized(model_name_or_path, fuse_layers=True, trust_remote_code=False)
+model = AutoAWQForCausalLM.from_quantized(model_name_or_path, fuse_layers=True,
+                                          trust_remote_code=False, safetensors=True)
 tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=False)
 
 prompt = "Tell me about AI"
@@ -195,9 +196,10 @@ generation_output = model.generate(
     max_new_tokens=512
 )
 
-print("Output: ", tokenizer.decode(output[0]))
+print("Output: ", tokenizer.decode(generation_output[0]))
 
 # Inference can also be done using transformers' pipeline
+from transformers import pipeline
 
 print("*** Pipeline:")
 pipe = pipeline(