Update README.md

README.md

@@ -61,46 +61,16 @@ Standard oobagooba works with exllama2 / autogptq loader
 ## Using in code
 
 ```python
-from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
-
-model_name_or_path = "cmeraki/OpenHathi-7B-Hi-v0.1-Base-gptq"
-model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
-                                             device_map="auto",
-                                             trust_remote_code=False,
-                                             revision="main")
-
-tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
-
-prompt = "do aur do"
-prompt_template=f'''[INST] <<SYS>>
-You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
-<</SYS>>
-{prompt}[/INST]
-
-'''
-
-print("\n\n*** Generate:")
-
-input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
-output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
-print(tokenizer.decode(output[0]))
-
-# Inference can also be done using transformers' pipeline
-
-print("*** Pipeline:")
-pipe = pipeline(
-    "text-generation",
-    model=model,
-    tokenizer=tokenizer,
-    max_new_tokens=512,
-    do_sample=True,
-    temperature=0.7,
-    top_p=0.95,
-    top_k=40,
-    repetition_penalty=1.1
-)
-
-print(pipe(prompt_template)[0]['generated_text'])
+from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
+from transformers import AutoTokenizer
+
+model_dir = 'cmeraki/OpenHathi-7B-Hi-v0.1-Base-gptq'
+
+model = AutoGPTQForCausalLM.from_quantized(model_dir, device="cuda:0")
+tokenizer = AutoTokenizer.from_pretrained(model_dir, fast=True)
+tokens = tokenizer("do aur do", return_tensors="pt").to(model.device)
+
+print(tokenizer.decode(model.generate(**tokens, max_length=1024)[0]))
 ```
 <!-- README_GPTQ.md-use-from-python end -->