支持batch形式的对话

— 添加chat_batch方法，可以同时进行多次多伦对话



modeling_chatglm.py

@@ -721,7 +721,6 @@ CHATGLM_6B_START_DOCSTRING = r"""
     This model is a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) sub-class.
     Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general
     usage and behavior.
-
     Parameters:
         config ([`~ChatGLM6BConfig`]): Model configuration class with all the parameters of the model.
             Initializing with a config file does not load the weights associated with the model, only the configuration.
@@ -732,37 +731,28 @@ CHATGLM_6B_INPUTS_DOCSTRING = r"""
     Args:
         input_ids (`torch.LongTensor` of shape `({0})`):
             Indices of input sequence tokens in the vocabulary.
-
             Indices can be obtained using [`ChatGLM6BTokenizer`].
             See [`PreTrainedTokenizer.encode`] and
             [`PreTrainedTokenizer.__call__`] for details.
-
             [What are input IDs?](../glossary#input-ids)
         attention_mask (`torch.FloatTensor` of shape `({0})`, *optional*):
             Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:
-
             - 1 for tokens that are **not masked**,
             - 0 for tokens that are **masked**.
-
             [What are attention masks?](../glossary#attention-mask)
         token_type_ids (`torch.LongTensor` of shape `({0})`, *optional*):
             Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`:
-
             - 0 corresponds to a *sentence A* token,
             - 1 corresponds to a *sentence B* token.
-
             [What are token type IDs?](../glossary#token-type-ids)
         position_ids (`torch.LongTensor` of shape `({0})`, *optional*):
             Indices of positions of each input sequence tokens in the position embeddings.
             Selected in the range `[0, config.max_position_embeddings - 1]`.
-
             [What are position IDs?](../glossary#position-ids)
         head_mask (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*):
             Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:
-
             - 1 indicates the head is **not masked**,
             - 0 indicates the head is **masked**.
-
         inputs_embeds (`torch.FloatTensor` of shape `({0}, hidden_size)`, *optional*):
             Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation.
             This is useful if you want more control over how to convert *input_ids* indices into associated vectors
@@ -784,13 +774,11 @@ CHATGLM_6B_INPUTS_DOCSTRING = r"""
 )
 class ChatGLMModel(ChatGLMPreTrainedModel):
     """
-
     The model can behave as an encoder (with only self-attention) as well
     as a decoder, in which case a layer of cross-attention is added between
     the self-attention layers, following the architecture described in [Attention is
     all you need](https://arxiv.org/abs/1706.03762) by Ashish Vaswani,
     Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser and Illia Polosukhin.
-
     To behave as an decoder the model needs to be initialized with the
     `is_decoder` argument of the configuration set to `True`.
     To be used in a Seq2Seq model, the model needs to initialized with both `is_decoder`
@@ -1237,7 +1225,6 @@ class ChatGLMForConditionalGeneration(ChatGLMPreTrainedModel):
         This function is used to re-order the `past_key_values` cache if [`~PreTrainedModel.beam_search`] or
         [`~PreTrainedModel.beam_sample`] is called. This is required to match `past_key_values` with the correct
         beam_idx at every generation step.
-
         Output shares the same memory storage as `past`.
         """
         return tuple(
@@ -1288,6 +1275,36 @@ class ChatGLMForConditionalGeneration(ChatGLMPreTrainedModel):
         response = self.process_response(response)
         history = history + [(query, response)]
         return response, history
+	
+	@torch.no_grad()
+    def chat_batch(self, tokenizer, querys=List[str], historys=List[List[Tuple[str, str]]], max_length: int = 2048, num_beams=1,
+             do_sample=True, top_p=0.7, temperature=0.95, logits_processor=None, **kwargs):
+        responses = []
+        prompts = []
+        for query, history in zip(querys, historys):
+            if history is None:
+                history = []
+            if logits_processor is None:
+                logits_processor = LogitsProcessorList()
+            logits_processor.append(InvalidScoreLogitsProcessor())
+            gen_kwargs = {"max_length": max_length, "num_beams": num_beams, "do_sample": do_sample, "top_p": top_p,
+                        "temperature": temperature, "logits_processor": logits_processor, **kwargs}
+            if not history:
+                prompt = query
+            else:
+                prompt = ""
+                for i, (old_query, response) in enumerate(history):
+                    prompt += "[Round {}]\n问：{}\n答：{}\n".format(i, old_query, response)
+                prompt += "[Round {}]\n问：{}\n答：".format(len(history), query)
+            prompts.append(prompt)
+        inputs = tokenizer(prompts, return_tensors="pt", padding=True)
+        inputs = inputs.to(self.device)
+        outputs = self.generate(**inputs, **gen_kwargs)
+        outputs = outputs.tolist()
+        outputs = [x[len(inputs["input_ids"][0]):] for x in outputs]
+        responses = [tokenizer.decode(output) for output in outputs]
+        responses = [self.process_response(response) for response in responses]
+        return responses
 
     @torch.no_grad()
     def stream_chat(self, tokenizer, query: str, history: List[Tuple[str, str]] = None, max_length: int = 2048,