Update README.md

README.md

@@ -7,4 +7,37 @@ metrics:
 - accuracy
 library_name: transformers
 pipeline_tag: text-generation
----
+---
+
+## Inference
+
+```
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained(
+  'Nanbeige/Nanbeige2-8B-Chat',
+  use_fast=False,
+  trust_remote_code=True
+)
+model = AutoModelForCausalLM.from_pretrained(
+  'Nanbeige/Nanbeige2-8B-Chat',
+  torch_dtype='auto',
+  device_map='auto',
+  trust_remote_code=True
+)
+
+messages = [
+  {'role': 'user', 'content': 'Hello'}
+]
+prompt = tokenizer.apply_chat_template(
+  messages,
+  add_generation_prompt=True,
+  tokenize=False
+)
+input_ids = tokenizer(prompt, add_special_tokens=False, return_tensors='pt').input_ids
+output_ids = model.generate(input_ids.to('cuda'))
+resp = tokenizer.decode(output_ids[0][len(input_ids[0]):], skip_special_tokens=True)
+
+print(resp)
+```
+