Update README_cn.md

README_cn.md

@@ -154,6 +154,42 @@ Monkey训练使用的json文件可以在[链接](https://drive.google.com/file/d
  - 添加LoRA：需要将```model_qwen.py```的内容替换为```model_qwen_nvdia3090.py```的内容
  - 冻结LLM：需要在```finetune_multitask.py```中冻结除LoRA和Resampler模块的其他模块
 
+## 推理
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+checkpoint = "echo840/Monkey"
+model = AutoModelForCausalLM.from_pretrained(checkpoint, device_map='cuda', trust_remote_code=True).eval()
+tokenizer = AutoTokenizer.from_pretrained(checkpoint, trust_remote_code=True)
+tokenizer.padding_side = 'left'
+tokenizer.pad_token_id = tokenizer.eod_id
+img_path = ""
+question = ""
+query = f'<img>{img_path}</img> {question} Answer: ' #VQA
+# query = f'<img>{img_path}</img> Generate the detailed caption in English: ' #detailed caption
+
+input_ids = tokenizer(query, return_tensors='pt', padding='longest')
+attention_mask = input_ids.attention_mask
+input_ids = input_ids.input_ids
+
+pred = model.generate(
+            input_ids=input_ids.cuda(),
+            attention_mask=attention_mask.cuda(),
+            do_sample=False,
+            num_beams=1,
+            max_new_tokens=512,
+            min_new_tokens=1,
+            length_penalty=1,
+            num_return_sequences=1,
+            output_hidden_states=True,
+            use_cache=True,
+            pad_token_id=tokenizer.eod_id,
+            eos_token_id=tokenizer.eod_id,
+            )
+response = tokenizer.decode(pred[0][input_ids.size(1):].cpu(), skip_special_tokens=True).strip()
+print(response)
+```
+
 ## 性能
 
 <br>