Update README.md

README.md

@@ -16,14 +16,65 @@ It is the result of quantising to 4bit using GPTQ-for-LLaMa.
 The model is open for COMMERCIAL USE.
 
 
-## How to use this GPTQ model from Python code
+# How to use this GPTQ model from Python code
 
 First, make sure you have [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) installed:
 
 #### pip install auto-gptq
 
 
+<code>
 
+from transformers import AutoTokenizer, pipeline, logging
+from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
+import argparse
+
+model_name_or_path = "SearchUnify-ML/xgen-7b-8k-open-instruct-gptq"
+model_basename = "gptq_model-4bit-128g"
+
+use_triton = False
+
+tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
+
+model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
+        model_basename=model_basename,
+        use_safetensors=True,
+        trust_remote_code=False,
+        device="cuda:0",
+        use_triton=use_triton,
+        quantize_config=None)
+
+# Note: check the prompt template is correct for this model.
+prompt = "Tell me about AI"
+prompt_template=f'''### Instruction: {prompt}
+### Response:'''
+
+print("\n\n*** Generate:")
+
+input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
+output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
+print(tokenizer.decode(output[0]))
+
+# Inference can also be done using transformers' pipeline
+
+# Prevent printing spurious transformers error when using pipeline with AutoGPTQ
+logging.set_verbosity(logging.CRITICAL)
+
+print("*** Pipeline:")
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    max_new_tokens=1024,
+    temperature=0.3,
+    top_p=0.95,
+    repetition_penalty=1.15
+)
+
+print(pipe(prompt_template)[0]['generated_text'])
+
+
+</code>