Update README.md

README.md

@@ -42,22 +42,31 @@ dtype: bfloat16
 ```python
 !pip install -qU transformers accelerate
 
-from transformers import AutoTokenizer
-import transformers
-import torch
-
-model = "shanchen/llama3-8B-slerp-biomed-chat-chinese"
-messages = [{"role": "user", "content": "What is a large language model?"}]
-
-tokenizer = AutoTokenizer.from_pretrained(model)
-prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-pipeline = transformers.pipeline(
-    "text-generation",
-    model=model,
-    torch_dtype=torch.float16,
-    device_map="auto",
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_id = "shenzhi-wang/Llama3-8B-Chinese-Chat"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id, torch_dtype="auto", device_map="auto"
+)
+
+messages = [
+    {"role": "user", "content": "Tell me about yourself"},
+]
+
+input_ids = tokenizer.apply_chat_template(
+    messages, add_generation_prompt=True, return_tensors="pt"
+).to(model.device)
+
+outputs = model.generate(
+    input_ids,
+    max_new_tokens=8192,
+    do_sample=True,
+    temperature=0.6,
+    top_p=0.9,
 )
+response = outputs[0][input_ids.shape[-1]:]
+print(tokenizer.decode(response, skip_special_tokens=True))
 
-outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
-print(outputs[0]["generated_text"])
 ```