fix compatibility issue for transformers 4.46+

configuration_intern_vit.py

@@ -3,6 +3,7 @@
 # Copyright (c) 2024 OpenGVLab
 # Licensed under The MIT License [see LICENSE for details]
 # --------------------------------------------------------
+
 import os
 from typing import Union
 

configuration_internvl_chat.py

@@ -47,9 +47,9 @@ class InternVLChatConfig(PretrainedConfig):
             logger.info('llm_config is None. Initializing the LlamaConfig config with default values (`LlamaConfig`).')
 
         self.vision_config = InternVisionConfig(**vision_config)
-        if llm_config['architectures'][0] == 'LlamaForCausalLM':
+        if llm_config.get('architectures', ['Qwen2ForCausalLM'])[0] == 'LlamaForCausalLM':
             self.llm_config = LlamaConfig(**llm_config)
-        elif llm_config['architectures'][0] == 'InternLM2ForCausalLM':
+        elif llm_config.get('architectures', ['InternLM2ForCausalLM'])[0] == 'InternLM2ForCausalLM':
             self.llm_config = InternLM2Config(**llm_config)
         else:
             raise ValueError('Unsupported architecture: {}'.format(llm_config['architectures'][0]))

conversation.py

@@ -3,6 +3,8 @@ Conversation prompt templates.
 
 We kindly request that you import fastchat instead of copying this file if you wish to use it.
 If you have changes in mind, please contribute back so the community can benefit collectively and continue to maintain these valuable templates.
+
+Modified from https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py
 """
 
 import dataclasses
@@ -344,12 +346,6 @@ register_conv_template(
         roles=('<|im_start|>user\n', '<|im_start|>assistant\n'),
         sep_style=SeparatorStyle.MPT,
         sep='<|im_end|>',
-        stop_token_ids=[
-            2,
-            6,
-            7,
-            8,
-        ],
         stop_str='<|endoftext|>',
     )
 )
@@ -365,11 +361,6 @@ register_conv_template(
         roles=('<|im_start|>user\n', '<|im_start|>assistant\n'),
         sep_style=SeparatorStyle.MPT,
         sep='<|im_end|>',
-        stop_token_ids=[
-            2,
-            92543,
-            92542
-        ]
     )
 )
 
@@ -384,10 +375,17 @@ register_conv_template(
         roles=('<|user|>\n', '<|assistant|>\n'),
         sep_style=SeparatorStyle.MPT,
         sep='<|end|>',
-        stop_token_ids=[
-            2,
-            32000,
-            32007
-        ]
+    )
+)
+
+
+register_conv_template(
+    Conversation(
+        name='internvl2_5',
+        system_template='<|im_start|>system\n{system_message}',
+        system_message='你是书生·万象，英文名是InternVL，是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。',
+        roles=('<|im_start|>user\n', '<|im_start|>assistant\n'),
+        sep_style=SeparatorStyle.MPT,
+        sep='<|im_end|>\n',
     )
 )

modeling_intern_vit.py

@@ -3,6 +3,7 @@
 # Copyright (c) 2024 OpenGVLab
 # Licensed under The MIT License [see LICENSE for details]
 # --------------------------------------------------------
+
 from typing import Optional, Tuple, Union
 
 import torch

modeling_internvl_chat.py

@@ -3,8 +3,9 @@
 # Copyright (c) 2024 OpenGVLab
 # Licensed under The MIT License [see LICENSE for details]
 # --------------------------------------------------------
+
 import warnings
-from typing import Any, List, Optional, Tuple, Union
+from typing import List, Optional, Tuple, Union
 
 import torch.utils.checkpoint
 import transformers
@@ -237,7 +238,7 @@ class InternVLChatModel(PreTrainedModel):
         model_inputs = tokenizer(queries, return_tensors='pt', padding=True)
         input_ids = model_inputs['input_ids'].to(self.device)
         attention_mask = model_inputs['attention_mask'].to(self.device)
-        eos_token_id = tokenizer.convert_tokens_to_ids(template.sep)
+        eos_token_id = tokenizer.convert_tokens_to_ids(template.sep.strip())
         generation_config['eos_token_id'] = eos_token_id
         generation_output = self.generate(
             pixel_values=pixel_values,
@@ -246,7 +247,7 @@ class InternVLChatModel(PreTrainedModel):
             **generation_config
         )
         responses = tokenizer.batch_decode(generation_output, skip_special_tokens=True)
-        responses = [response.split(template.sep)[0].strip() for response in responses]
+        responses = [response.split(template.sep.strip())[0].strip() for response in responses]
         return responses
 
     def chat(self, tokenizer, pixel_values, question, generation_config, history=None, return_history=False,
@@ -265,7 +266,7 @@ class InternVLChatModel(PreTrainedModel):
 
         template = get_conv_template(self.template)
         template.system_message = self.system_message
-        eos_token_id = tokenizer.convert_tokens_to_ids(template.sep)
+        eos_token_id = tokenizer.convert_tokens_to_ids(template.sep.strip())
 
         history = [] if history is None else history
         for (old_question, old_answer) in history:
@@ -294,7 +295,7 @@ class InternVLChatModel(PreTrainedModel):
             **generation_config
         )
         response = tokenizer.batch_decode(generation_output, skip_special_tokens=True)[0]
-        response = response.split(template.sep)[0].strip()
+        response = response.split(template.sep.strip())[0].strip()
         history.append((question, response))
         if return_history:
             return response, history
@@ -314,7 +315,6 @@ class InternVLChatModel(PreTrainedModel):
             visual_features: Optional[torch.FloatTensor] = None,
             generation_config: Optional[GenerationConfig] = None,
             output_hidden_states: Optional[bool] = None,
-            return_dict: Optional[bool] = None,
             **generate_kwargs,
     ) -> torch.LongTensor:
 
@@ -342,7 +342,6 @@ class InternVLChatModel(PreTrainedModel):
             attention_mask=attention_mask,
             generation_config=generation_config,
             output_hidden_states=output_hidden_states,
-            return_dict=return_dict,
             use_cache=True,
             **generate_kwargs,
         )