fix kwargs in generate method and update readme

README.md

@@ -42,9 +42,21 @@ The features of Qwen-7B include:
 
 For more details about the open-source model of Qwen-7B, please refer to the [Github](https://github.com/QwenLM/Qwen-7B) code repository.
 
+## 要求（Requirements）
+
+* python 3.8及以上版本
+* pytorch 1.12及以上版本，推荐2.0及以上版本
+* 建议使用CUDA 11.4及以上（GPU用户、flash-attention用户等需考虑此选项）
+
+
+
+* python 3.8 and above
+* pytorch 1.12 and above, 2.0 and above are recommended
+* CUDA 11.4 and above are recommended (this is for GPU users, flash-attention users, etc.)
+
 ## 依赖项 (Dependency)
 
-运行Qwen-7B，请确保机器环境torch版本不低于1.12，再执行以下pip命令安装依赖库
+运行Qwen-7B，请确保满足上述要求，再执行以下pip命令安装依赖库
 
 To run Qwen-7B, please make sure that pytorch version is not lower than 1.12, and then execute the following pip commands to install the dependent libraries.
 
@@ -75,18 +87,18 @@ from transformers.generation import GenerationConfig
 
 # Note: The default behavior now has injection attack prevention off.
 tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True)
-# We recommend checking the support of BF16 first. Run the command below:
-# import torch
-# torch.cuda.is_bf16_supported()
+
 # use bf16
 # model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B", device_map="auto", trust_remote_code=True, bf16=True).eval()
 # use fp16
 # model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B", device_map="auto", trust_remote_code=True, fp16=True).eval()
 # use cpu only
 # model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B", device_map="cpu", trust_remote_code=True).eval()
-# use fp32
+# use auto mode, automatically select precision based on the device.
 model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B", device_map="auto", trust_remote_code=True).eval()
-model.generation_config = GenerationConfig.from_pretrained("Qwen/Qwen-7B", trust_remote_code=True) # 可指定不同的生成长度、top_p等相关超参
+
+# Specify hyperparameters for generation
+model.generation_config = GenerationConfig.from_pretrained("Qwen/Qwen-7B", trust_remote_code=True)
 
 inputs = tokenizer('蒙古国的首都是乌兰巴托（Ulaanbaatar）\n冰岛的首都是雷克雅未克（Reykjavik）\n埃塞俄比亚的首都是', return_tensors='pt')
 inputs = inputs.to('cuda:0')
@@ -309,9 +321,17 @@ We introduce NTK-aware interpolation, LogN attention scaling, Window attention,
 
 ## 量化（Quantization）
 
-如希望使用更低精度的量化模型，如4比特和8比特的模型，我们提供了简单的示例来说明如何快速使用量化模型。在开始前，确保你已经安装了`bitsandbytes`。
+如希望使用更低精度的量化模型，如4比特和8比特的模型，我们提供了简单的示例来说明如何快速使用量化模型。在开始前，确保你已经安装了`bitsandbytes`。请注意：`bitsandbytes`的安装要求是：
 
-We provide examples to show how to load models in `NF4` and `Int8`. For starters, make sure you have implemented `bitsandbytes`.
+We provide examples to show how to load models in `NF4` and `Int8`. For starters, make sure you have implemented `bitsandbytes`. Note that the requirements for `bitsandbytes` is:
+
+```
+**Requirements** Python >=3.8. Linux distribution (Ubuntu, MacOS, etc.) + CUDA > 10.0.
+```
+
+Windows用户需安装特定版本的`bitsandbytes`，可选项包括[bitsandbytes-windows-webui](https://github.com/jllllll/bitsandbytes-windows-webui/releases/tag/wheels)。
+
+Windows users should find another option, which might be [bitsandbytes-windows-webui](https://github.com/jllllll/bitsandbytes-windows-webui/releases/tag/wheels).
 
 ```bash
 pip install bitsandbytes
@@ -369,4 +389,5 @@ Our code and checkpoints are open to research purpose, and they are allowed for
 
 如果你想给我们的研发团队和产品团队留言，请通过邮件（[email protected]）联系我们。
 
-If you are interested to leave a message to either our research team or product team, feel free to send an email to [email protected].
+If you are interested to leave a message to either our research team or product team, feel free to send an email to [email protected].
+

modeling_qwen.py

@@ -958,12 +958,14 @@ class QWenLMHeadModel(QWenPreTrainedModel):
         history: Optional[HistoryType],
         system: str = "You are a helpful assistant.",
         append_history: bool = True,
-        stream: Optional[bool] = False
+        stream: Optional[bool] = False,
+        stop_words_ids: Optional[List[List[int]]] = None,
+        **kwargs,
     ) -> Tuple[str, HistoryType]:
-
-
         if history is None:
             history = []
+        if stop_words_ids is None:
+            stop_words_ids = []
 
         raw_text, context_tokens = make_context(
             tokenizer,
@@ -974,9 +976,9 @@ class QWenLMHeadModel(QWenPreTrainedModel):
             chat_format=self.generation_config.chat_format,
         )
 
-        stop_words_ids = get_stop_words_ids(
+        stop_words_ids.extend(get_stop_words_ids(
             self.generation_config.chat_format, tokenizer
-        )
+        ))
         input_ids = torch.tensor([context_tokens]).to(self.device)
         if stream:
             assert self.generation_config.chat_format == 'chatml'
@@ -986,7 +988,8 @@ class QWenLMHeadModel(QWenPreTrainedModel):
             stream_config = StreamGenerationConfig(**self.generation_config.to_dict(), do_stream=True)
             def stream_generator():
                 outputs = []
-                for token in self.generate(input_ids, return_dict_in_generate=False, generation_config=stream_config):
+                for token in self.generate(
+                        input_ids, return_dict_in_generate=False, generation_config=stream_config, **kwargs):
                     outputs.append(token.item())
                     if outputs[-1] in (tokenizer.im_end_id, tokenizer.im_start_id):
                         break
@@ -998,6 +1001,7 @@ class QWenLMHeadModel(QWenPreTrainedModel):
                         input_ids,
                         stop_words_ids = stop_words_ids,
                         return_dict_in_generate = False,
+                        **kwargs,
                     )
 
             response = decode_tokens(