Upload modeling_internvl_chat.py with huggingface_hub

modeling_internvl_chat.py

@@ -12,7 +12,7 @@ import transformers
 from torch import nn
 from torch.nn import CrossEntropyLoss
 from transformers import (AutoModel, GenerationConfig, LlamaForCausalLM,
-                          LlamaTokenizer)
+                          Qwen2ForCausalLM)
 from transformers.modeling_outputs import CausalLMOutputWithPast
 from transformers.modeling_utils import PreTrainedModel
 from transformers.utils import ModelOutput, logging
@@ -20,7 +20,6 @@ from transformers.utils import ModelOutput, logging
 from .configuration_internvl_chat import InternVLChatConfig
 from .conversation import get_conv_template
 from .modeling_intern_vit import InternVisionModel, has_flash_attn
-from .modeling_internlm2 import InternLM2ForCausalLM
 
 logger = logging.get_logger(__name__)
 
@@ -39,7 +38,7 @@ class InternVLChatModel(PreTrainedModel):
     base_model_prefix = 'language_model'
     _supports_flash_attn_2 = True
     supports_gradient_checkpointing = True
-    _no_split_modules = ['InternVisionModel', 'LlamaDecoderLayer', 'InternLM2DecoderLayer']
+    _no_split_modules = ['InternVisionModel', 'LlamaDecoderLayer', 'Qwen2DecoderLayer']
 
     def __init__(self, config: InternVLChatConfig, vision_model=None, language_model=None, use_flash_attn=True):
         super().__init__(config)
@@ -55,7 +54,7 @@ class InternVLChatModel(PreTrainedModel):
         self.ps_version = config.ps_version
         use_flash_attn = use_flash_attn if has_flash_attn else False
         config.vision_config.use_flash_attn = True if use_flash_attn else False
-        config.llm_config.attn_implementation = 'flash_attention_2' if use_flash_attn else 'eager'
+        config.llm_config._attn_implementation = 'flash_attention_2' if use_flash_attn else 'eager'
 
         logger.info(f'num_image_token: {self.num_image_token}')
         logger.info(f'ps_version: {self.ps_version}')
@@ -68,8 +67,8 @@ class InternVLChatModel(PreTrainedModel):
         else:
             if config.llm_config.architectures[0] == 'LlamaForCausalLM':
                 self.language_model = LlamaForCausalLM(config.llm_config)
-            elif config.llm_config.architectures[0] == 'InternLM2ForCausalLM':
-                self.language_model = InternLM2ForCausalLM(config.llm_config)
+            elif config.llm_config.architectures[0] == 'Qwen2ForCausalLM':
+                self.language_model = Qwen2ForCausalLM(config.llm_config)
             else:
                 raise NotImplementedError(f'{config.llm_config.architectures[0]} is not implemented.')