Update README.md

README.md

@@ -34,27 +34,49 @@ You can use FineMedLM in the same way as `Llama-3.1-8B-Instruct`:
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model = AutoModelForCausalLM.from_pretrained("hongzhouyu/FineMedLM")
-tokenizer = AutoTokenizer.from_pretrained("hongzhouyu/FineMedLM")
+main_model_name = "hongzhouyu/FineMedLM"  
+model = AutoModelForCausalLM.from_pretrained(main_model_name, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained(main_model_name)
+
+# 构造输入
+prompt = (
+    """The following are multiple choice questions (with answers) about health. Think step by step and then finish your answer with "the answer is (X)" where X is the correct letter choice.
+
+
+Question:
+Polio can be eradicated by which of the following?
+Options:
+A. Herbal remedies
+B. Use of antibiotics
+C. Regular intake of vitamins
+D. Administration of tetanus vaccine
+E. Attention to sewage control and hygiene
+F. Natural immunity acquired through exposure
+G. Use of antiviral drugs
+Answer: Let's think step by step.
+"""
+)
+
 
-prompt = "How do the interactions between neuronal activity, gonadal hormones, and neurotrophins influence axon regeneration post-injury, and what are the potential therapeutic implications of this research? Please think step by step."
 messages = [
-    {"role": "system", "content": "You are a helpful professional doctor."},
+    {"role": "system", "content": "You are a helpful professional doctor. The user will give you a medical question, and you should answer it in a professional way."},
     {"role": "user", "content": prompt}
 ]
+
 text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-model_inputs = tokenizer([text], return_tensors="pt")
+print(text)
 
+model_inputs = tokenizer(text, return_tensors="pt").to(model.device)
+
+print("-----start generate-----")
 generated_ids = model.generate(
     model_inputs.input_ids,
-    max_new_tokens=4096
+    max_new_tokens=2048,
+    eos_token_id=tokenizer.eos_token_id
 )
-generated_ids = [
-    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
-]
-response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 
-print(response)
+answer = tokenizer.decode(generated_ids[0], skip_special_tokens=False)
+print(answer)
 ```
 
 # <span>Citation</span>