Update README.md

README.md

@@ -63,6 +63,8 @@ from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
 import argparse
 
 model_name_or_path = "TheBloke/starchat-beta-GPTQ"
+# Or to load it locally, pass the local download path
+# model_name_or_path = "/path/to/models/The_Bloke_starchat-beta-GPTQ"
 
 use_triton = False
 
@@ -74,13 +76,17 @@ model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
         use_triton=use_triton,
         quantize_config=None)
 
-pipe = pipeline("text-generation", model=model)
+# Prevent printing spurious transformers error when using pipeline with AutoGPTQ
+logging.set_verbosity(logging.CRITICAL)
+
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
 prompt_template = "<|system|>\n<|end|>\n<|user|>\n{query}<|end|>\n<|assistant|>"
 prompt = prompt_template.format(query="How do I sort a list in Python?")
 # We use a special <|end|> token with ID 49155 to denote ends of a turn
 outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.2, top_k=50, top_p=0.95, eos_token_id=49155)
 # You can sort a list in Python by using the sort() method. Here's an example:\n\n```\nnumbers = [3, 1, 4, 1, 5, 9, 2, 6, 5, 3, 5]\nnumbers.sort()\nprint(numbers)\n```\n\nThis will sort the list in place and print the sorted list.
+print(outputs[0]['generated_text'])
 ```
 
 ## Provided files