Update README.md

README.md

@@ -6,7 +6,42 @@ language:
 - zh
 pipeline_tag: text-generation
 ---
-示例
+此模型由[atom-7b-chat](https://huggingface.co/FlagAlpha/Atom-7B-Chat)经过lora微调得到，通过线性位置插值，将文本长度从4k扩展到16k，可以完成多文档检索、论文总结等任务。\
+此版本为v1，初步具有长对话能力，但回答错误依然较多，可能是因为微调数据质量低（[yuyijiong/LongData-instruction-chinese](https://huggingface.co/datasets/yuyijiong/LongData-instruction-chinese) 都是谷歌翻译过来的英文数据）。未来将会持续改进，改进版本很快推出。\
+使用方法：
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers.generation import GenerationConfig
+import os
+os.environ["CUDA_VISIBLE_DEVICES"] = "0"
+
+model_path="yuyijiong/atom-7b-chat-16k"
+tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
+
+# use auto mode, automatically select precision based on the device.
+model = AutoModelForCausalLM.from_pretrained(model_path, device_map="auto", load_in_8bit=True).eval()
+
+question="中国的首都是什么？"
+input_text = "<s>Human: " + question + "\n</s><s>Assistant: "
+input_ids = tokenizer(input_text, return_tensors='pt').input_ids.to(model.device)
+
+with torch.no_grad():
+    with torch.autocast('cuda'):
+        output = model.generate(input_ids=input_ids,
+                                max_new_tokens=max_new_tokens,
+                                do_sample=True,
+                                temperature=0.85,
+                                top_k=None,
+                                top_p=0.9,
+                                use_cache=True,
+                                **kwargs)
+
+reply = tokenizer.decode(output[0], skip_special_tokens=False)
+reply_return=reply.split('Assistant:')[-1].replace('</s>', '')
+print('模型回答：', reply_return)
+```
+
+示例（多文档检索（问答）任务，输入文本大于10000字）
 ```
 先阅读以下多个参考文档，然后根据文档内容，详细地回答问题，并指出所参考的文档的序号：
 
@@ -75,36 +110,4 @@ pipeline_tag: text-generation
 以上回答参考了文档-43。
 ```
 
-使用方法：
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-from transformers.generation import GenerationConfig
-import os
-os.environ["CUDA_VISIBLE_DEVICES"] = "0"
-
-model_path="yuyijiong/atom-7b-chat-16k"
-tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
-
-# use auto mode, automatically select precision based on the device.
-model = AutoModelForCausalLM.from_pretrained(model_path, device_map="auto", load_in_8bit=True).eval()
-
-question="中国的首都是什么？"
-input_text = "<s>Human: " + question + "\n</s><s>Assistant: "
-input_ids = tokenizer(input_text, return_tensors='pt').input_ids.to(model.device)
 
-with torch.no_grad():
-    with torch.autocast('cuda'):
-        output = model.generate(input_ids=input_ids,
-                                max_new_tokens=max_new_tokens,
-                                do_sample=True,
-                                temperature=0.85,
-                                top_k=None,
-                                top_p=0.9,
-                                use_cache=True,
-                                **kwargs)
-
-reply = tokenizer.decode(output[0], skip_special_tokens=False)
-reply_return=reply.split('Assistant:')[-1].replace('</s>', '')
-print('模型回答：', reply_return)
-
-```