Update README.md

README.md

@@ -38,24 +38,27 @@ messages = [
     {"role": "user", "content": "Who are you?"},
 ]
 
-input_ids = tokenizer.apply_chat_template(
-    messages,
-    add_generation_prompt=True,
-    return_tensors="pt"
-).to(model.device)
+
+prompt = pipeline.tokenizer.apply_chat_template(
+      messages,
+      tokenize=False,
+      add_generation_prompt=True
+)
 
 terminators = [
-    tokenizer.eos_token_id,
-    tokenizer.convert_tokens_to_ids("<|eot_id|>")
+      pipeline.tokenizer.eos_token_id,
+      pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
 ]
 
+
 outputs = model.generate(
-    input_ids,
-    max_new_tokens=256,
-    eos_token_id=terminators,
-    do_sample=True,
-    temperature=0.6,
-    top_p=0.9,
+      prompt,
+      max_new_tokens=2048,
+      eos_token_id=terminators,
+      do_sample=False,
+      temperature=0.6,
+      top_p=1,
+      repetition_penalty=1.05
 )
 response = outputs[0][input_ids.shape[-1]:]
 print(tokenizer.decode(response, skip_special_tokens=True))