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

@@ -47,12 +47,12 @@ 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'])[0] == 'LlamaForCausalLM':
             self.llm_config = LlamaConfig(**llm_config)
-        elif llm_config['architectures'][0] == 'InternLM2ForCausalLM':
+        elif llm_config.get(['architectures'])[0] == 'InternLM2ForCausalLM':
             self.llm_config = InternLM2Config(**llm_config)
         else:
-            raise ValueError('Unsupported architecture: {}'.format(llm_config['architectures'][0]))
+            raise ValueError('Unsupported architecture: {}'.format(llm_config.get(['architectures'])[0]))
         self.use_backbone_lora = use_backbone_lora
         self.use_llm_lora = use_llm_lora
         self.select_layer = select_layer

conversation.py

@@ -3,11 +3,13 @@ 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
 from enum import IntEnum, auto
-from typing import Any, Dict, List, Tuple, Union
+from typing import Dict, List, Tuple, Union
 
 
 class SeparatorStyle(IntEnum):
@@ -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',
     )
 )

eval_llm_benchmark.log

@@ -0,0 +1,53 @@
+/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl_eval/lib/python3.10/site-packages/bitsandbytes/cextension.py:34: UserWarning: The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers, 8-bit multiplication, and GPU quantization are unavailable.
+  warn("The installed version of bitsandbytes was compiled without GPU support. "
+/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl_eval/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cpu.so: undefined symbol: cadam32bit_grad_fp32
+model path is /mnt/petrelfs/wangweiyun/workspace_cz/InternVL/internvl_chat_dev/share_internvl/InternVL2-8B
+09/30 19:08:03 - OpenCompass - WARNING - No previous results to reuse!
+09/30 19:08:03 - OpenCompass - INFO - Reusing experiements from 20240930_190803
+09/30 19:08:03 - OpenCompass - INFO - Current exp folder: /mnt/petrelfs/wangweiyun/workspace_cz/InternVL/internvl_chat_dev/share_internvl/InternVL2-8B/20240930_190803
+09/30 19:08:06 - OpenCompass - INFO - Partitioned into 64 tasks.
+[                                                  ] 0/64, elapsed: 0s, ETA:
+09/30 19:52:33 - OpenCompass - INFO - Partitioned into 287 tasks.
+[                                                  ] 0/287, elapsed: 0s, ETA:
+dataset                       version    metric                        mode    internvl-chat-20b
+----------------------------  ---------  ----------------------------  ------  -------------------
+mmlu                          -          naive_average                 gen     73.17
+cmmlu                         -          naive_average                 gen     79.21
+ceval                         -          naive_average                 gen     80.14
+agieval                       -          -                             -       -
+GaokaoBench                   -          weighted_average              gen     74.99
+triviaqa                      2121ce     score                         gen     62.03
+triviaqa_wiki_1shot           -          -                             -       -
+nq                            3dcea1     score                         gen     28.12
+C3                            8c358f     accuracy                      gen     94.19
+race-high                     9a54b6     accuracy                      gen     90.82
+flores_100                    -          -                             -       -
+winogrande                    b36770     accuracy                      gen     85.87
+hellaswag                     e42710     accuracy                      gen     94.91
+bbh                           -          naive_average                 gen     72.67
+gsm8k                         1d7fe4     accuracy                      gen     75.59
+math                          393424     accuracy                      gen     39.50
+TheoremQA                     6f0af8     score                         gen     15.62
+MathBench                     -          -                             -       -
+openai_humaneval              8e312c     humaneval_pass@1              gen     69.51
+humanevalx                    -          -                             -       -
+sanitized_mbpp                a447ff     score                         gen     58.75
+mbpp_cn                       6fb572     score                         gen     48.20
+leval                         -          -                             -       -
+leval_closed                  -          -                             -       -
+leval_open                    -          -                             -       -
+longbench                     -          -                             -       -
+longbench_single-document-qa  -          -                             -       -
+longbench_multi-document-qa   -          -                             -       -
+longbench_summarization       -          -                             -       -
+longbench_few-shot-learning   -          -                             -       -
+longbench_synthetic-tasks     -          -                             -       -
+longbench_code-completion     -          -                             -       -
+teval                         -          -                             -       -
+teval_zh                      -          -                             -       -
+IFEval                        3321a3     Prompt-level-strict-accuracy  gen     52.31
+IFEval                        3321a3     Inst-level-strict-accuracy    gen     62.71
+IFEval                        3321a3     Prompt-level-loose-accuracy   gen     54.90
+IFEval                        3321a3     Inst-level-loose-accuracy     gen     64.87
+09/30 19:55:16 - OpenCompass - INFO - write summary to /mnt/petrelfs/wangweiyun/workspace_cz/InternVL/internvl_chat_dev/share_internvl/InternVL2-8B/20240930_190803/summary/summary_20240930_190803.txt
+09/30 19:55:16 - OpenCompass - INFO - write csv to /mnt/petrelfs/wangweiyun/workspace_cz/InternVL/internvl_chat_dev/share_internvl/InternVL2-8B/20240930_190803/summary/summary_20240930_190803.csv

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,
         )