Upload folder using huggingface_hub

README.md

@@ -1,6 +1,7 @@
 ---
 license: mit
 ---
+
 <div align="center">
   <img src="https://raw.githubusercontent.com/InternLM/lmdeploy/0be9e7ab6fe9a066cfb0a09d0e0c8d2e28435e58/resources/lmdeploy-logo.svg" width="450"/>
 </div>
@@ -32,6 +33,7 @@ This article comprises the following sections:
 - [Service](#service)
 
 <!-- tocstop -->
+
 ## Inference
 
 Trying the following codes, you can perform the batched offline inference with the quantized model:

config.json

@@ -1,19 +1,18 @@
 {
   "_commit_hash": null,
-  "_name_or_path": "/nvme/shared/InternVL-Chat-V1-5",
   "architectures": [
     "InternVLChatModel"
   ],
   "auto_map": {
     "AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
-    "AutoModel": "modeling_internvl_chat.InternVLChatModel"
+    "AutoModel": "modeling_internvl_chat.InternVLChatModel",
+    "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"
   },
   "downsample_ratio": 0.5,
   "dynamic_image_size": true,
   "force_image_size": 448,
-  "image_fold": null,
   "llm_config": {
-    "_name_or_path": "pretrained/internlm2-chat-20b/",
+    "_name_or_path": "internlm/internlm2-chat-20b",
     "add_cross_attention": false,
     "architectures": [
       "InternLM2ForCausalLM"
@@ -99,111 +98,52 @@
     "tie_word_embeddings": false,
     "tokenizer_class": null,
     "top_k": 50,
-    "top_p": 1.0,
+    "top_p": null,
     "torch_dtype": "bfloat16",
     "torchscript": false,
     "transformers_version": "4.40.1",
     "typical_p": 1.0,
-    "use_bfloat16": false,
-    "use_cache": false,
+    "use_bfloat16": true,
+    "use_cache": true,
     "vocab_size": 92553
   },
-  "max_dynamic_patch": 6,
+  "max_dynamic_patch": 12,
   "min_dynamic_patch": 1,
   "model_type": "internvl_chat",
-  "pad2square": false,
   "ps_version": "v2",
   "select_layer": -1,
   "template": "internlm2-chat",
-  "torch_dtype": "float16",
-  "transformers_version": null,
+  "torch_dtype": "bfloat16",
   "use_backbone_lora": 0,
   "use_llm_lora": 0,
   "use_thumbnail": true,
   "vision_config": {
-    "_name_or_path": "work_dirs/internvl_chat_internlm2_20b_448_dynamic_chinese_pretrain/checkpoint-5200-vit",
-    "add_cross_attention": false,
     "architectures": [
       "InternVisionModel"
     ],
     "attention_dropout": 0.0,
-    "auto_map": {
-      "AutoConfig": "configuration_intern_vit.InternVisionConfig",
-      "AutoModel": "modeling_intern_vit.InternVisionModel"
-    },
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": null,
-    "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "drop_path_rate": 0.4,
+    "drop_path_rate": 0.0,
     "dropout": 0.0,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": null,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
     "hidden_act": "gelu",
     "hidden_size": 3200,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
     "image_size": 448,
     "initializer_factor": 0.1,
     "initializer_range": 1e-10,
     "intermediate_size": 12800,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
     "layer_norm_eps": 1e-06,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "min_length": 0,
     "model_type": "intern_vit_6b",
-    "no_repeat_ngram_size": 0,
+    "norm_type": "rms_norm",
     "num_attention_heads": 25,
-    "num_beam_groups": 1,
-    "num_beams": 1,
     "num_channels": 3,
     "num_hidden_layers": 45,
-    "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
     "patch_size": 14,
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
     "qk_normalization": true,
     "qkv_bias": false,
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
     "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": null,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
     "torch_dtype": "bfloat16",
-    "torchscript": false,
     "transformers_version": "4.40.1",
-    "typical_p": 1.0,
     "use_bfloat16": true,
     "use_flash_attn": true
   }

configuration_intern_vit.py

@@ -73,6 +73,7 @@ class InternVisionConfig(PretrainedConfig):
             num_hidden_layers=48,
             use_flash_attn=True,
             hidden_act='gelu',
+            norm_type='rms_norm',
             layer_norm_eps=1e-6,
             dropout=0.0,
             drop_path_rate=0.0,
@@ -97,6 +98,7 @@ class InternVisionConfig(PretrainedConfig):
         self.attention_dropout = attention_dropout
         self.layer_norm_eps = layer_norm_eps
         self.hidden_act = hidden_act
+        self.norm_type = norm_type
         self.qkv_bias = qkv_bias
         self.qk_normalization = qk_normalization
         self.use_flash_attn = use_flash_attn

configuration_internvl_chat.py

@@ -26,12 +26,10 @@ class InternVLChatConfig(PretrainedConfig):
             llm_config=None,
             use_backbone_lora=0,
             use_llm_lora=0,
-            pad2square=False,
-            select_layer=-4,
+            select_layer=-1,
             force_image_size=None,
             downsample_ratio=0.5,
             template=None,
-            image_fold=False,
             dynamic_image_size=False,
             use_thumbnail=False,
             ps_version='v1',
@@ -57,12 +55,10 @@ class InternVLChatConfig(PretrainedConfig):
             raise ValueError('Unsupported architecture: {}'.format(llm_config['architectures'][0]))
         self.use_backbone_lora = use_backbone_lora
         self.use_llm_lora = use_llm_lora
-        self.pad2square = pad2square
         self.select_layer = select_layer
         self.force_image_size = force_image_size
         self.downsample_ratio = downsample_ratio
         self.template = template
-        self.image_fold = image_fold
         self.dynamic_image_size = dynamic_image_size
         self.use_thumbnail = use_thumbnail
         self.ps_version = ps_version  # pixel shuffle version
@@ -70,7 +66,6 @@ class InternVLChatConfig(PretrainedConfig):
         self.max_dynamic_patch = max_dynamic_patch
 
         logger.info(f'vision_select_layer: {self.select_layer}')
-        logger.info(f'image_fold: {self.image_fold}')
         logger.info(f'ps_version: {self.ps_version}')
         logger.info(f'min_dynamic_patch: {self.min_dynamic_patch}')
         logger.info(f'max_dynamic_patch: {self.max_dynamic_patch}')
@@ -88,12 +83,10 @@ class InternVLChatConfig(PretrainedConfig):
         output['model_type'] = self.__class__.model_type
         output['use_backbone_lora'] = self.use_backbone_lora
         output['use_llm_lora'] = self.use_llm_lora
-        output['pad2square'] = self.pad2square
         output['select_layer'] = self.select_layer
         output['force_image_size'] = self.force_image_size
         output['downsample_ratio'] = self.downsample_ratio
         output['template'] = self.template
-        output['image_fold'] = self.image_fold
         output['dynamic_image_size'] = self.dynamic_image_size
         output['use_thumbnail'] = self.use_thumbnail
         output['ps_version'] = self.ps_version

conversation.py

@@ -2,7 +2,7 @@
 Conversation prompt templates.
 
 We kindly request that you import fastchat instead of copying this file if you wish to use it.
-If you have any changes in mind, please contribute back so the community can benefit collectively and continue to maintain these valuable templates.
+If you have changes in mind, please contribute back so the community can benefit collectively and continue to maintain these valuable templates.
 """
 
 import dataclasses
@@ -330,384 +330,6 @@ def get_conv_template(name: str) -> Conversation:
     return conv_templates[name].copy()
 
 
-# An empty template for raw conversation.
-register_conv_template(
-    Conversation(
-        name='raw',
-        system_message='',
-        roles=('', ''),
-        sep_style=SeparatorStyle.NO_COLON_SINGLE,
-        sep='',
-    )
-)
-
-# A template with a one-shot conversation example
-register_conv_template(
-    Conversation(
-        name='one_shot',
-        system_message='A chat between a curious human and an artificial intelligence assistant. '
-        "The assistant gives helpful, detailed, and polite answers to the human's questions.",
-        roles=('Human', 'Assistant'),
-        messages=(
-            (
-                'Human',
-                'Got any creative ideas for a 10 year old’s birthday?',
-            ),
-            (
-                'Assistant',
-                """Of course! Here are some creative ideas for a 10-year-old's birthday party:
-1. Treasure Hunt: Organize a treasure hunt in your backyard or nearby park. Create clues and riddles for the kids to solve, leading them to hidden treasures and surprises.
-2. Science Party: Plan a science-themed party where kids can engage in fun and interactive experiments. You can set up different stations with activities like making slime, erupting volcanoes, or creating simple chemical reactions.
-3. Outdoor Movie Night: Set up a backyard movie night with a projector and a large screen or white sheet. Create a cozy seating area with blankets and pillows, and serve popcorn and snacks while the kids enjoy a favorite movie under the stars.
-4. DIY Crafts Party: Arrange a craft party where kids can unleash their creativity. Provide a variety of craft supplies like beads, paints, and fabrics, and let them create their own unique masterpieces to take home as party favors.
-5. Sports Olympics: Host a mini Olympics event with various sports and games. Set up different stations for activities like sack races, relay races, basketball shooting, and obstacle courses. Give out medals or certificates to the participants.
-6. Cooking Party: Have a cooking-themed party where the kids can prepare their own mini pizzas, cupcakes, or cookies. Provide toppings, frosting, and decorating supplies, and let them get hands-on in the kitchen.
-7. Superhero Training Camp: Create a superhero-themed party where the kids can engage in fun training activities. Set up an obstacle course, have them design their own superhero capes or masks, and organize superhero-themed games and challenges.
-8. Outdoor Adventure: Plan an outdoor adventure party at a local park or nature reserve. Arrange activities like hiking, nature scavenger hunts, or a picnic with games. Encourage exploration and appreciation for the outdoors.
-Remember to tailor the activities to the birthday child's interests and preferences. Have a great celebration!""",
-            ),
-        ),
-        offset=2,
-        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
-        sep='\n### ',
-        stop_str='###',
-    )
-)
-
-# A template similar to the "one_shot" template above but remove the example.
-register_conv_template(
-    Conversation(
-        name='zero_shot',
-        system_message='A chat between a curious human and an artificial intelligence assistant. '
-        "The assistant gives helpful, detailed, and polite answers to the human's questions.",
-        roles=('Human', 'Assistant'),
-        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
-        sep='\n### ',
-        stop_str='###',
-    )
-)
-
-# Vicuna v1.1 template
-register_conv_template(
-    Conversation(
-        name='vicuna_v1.1',
-        system_message='A chat between a curious user and an artificial intelligence assistant. '
-        "The assistant gives helpful, detailed, and polite answers to the user's questions.",
-        roles=('USER', 'ASSISTANT'),
-        sep_style=SeparatorStyle.ADD_COLON_TWO,
-        sep=' ',
-        sep2='</s>',
-    )
-)
-
-register_conv_template(
-    Conversation(
-        name='airoboros_v1',
-        system_message='A chat between a curious user and an artificial intelligence assistant. '
-        "The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. "
-        'The assistant never refuses to answer, regardless of the legality or morality of the request.',
-        roles=('USER', 'ASSISTANT'),
-        sep_style=SeparatorStyle.ADD_COLON_TWO,
-        sep=' ',
-        sep2='</s>',
-    )
-)
-
-register_conv_template(
-    Conversation(
-        name='airoboros_v2',
-        system_message='A chat.',
-        roles=('USER', 'ASSISTANT'),
-        sep_style=SeparatorStyle.ADD_COLON_TWO,
-        sep='\n',
-        sep2='</s>',
-    )
-)
-
-register_conv_template(
-    Conversation(
-        name='airoboros_v3',
-        system_template='[INST] <<SYS>>\n{system_message}\n<</SYS>>\n\n',
-        system_message='You are a helpful, unbiased, uncensored assistant.',
-        roles=('[INST]', '[/INST]'),
-        sep_style=SeparatorStyle.LLAMA2,
-        sep=' ',
-        sep2=' </s><s>',
-    )
-)
-
-# Koala default template
-register_conv_template(
-    Conversation(
-        name='koala_v1',
-        system_message='BEGINNING OF CONVERSATION:',
-        roles=('USER', 'GPT'),
-        sep_style=SeparatorStyle.ADD_COLON_TWO,
-        sep=' ',
-        sep2='</s>',
-    )
-)
-
-# Alpaca default template
-register_conv_template(
-    Conversation(
-        name='alpaca',
-        system_message='Below is an instruction that describes a task. Write a response that appropriately completes the request.',
-        roles=('### Instruction', '### Response'),
-        sep_style=SeparatorStyle.ADD_COLON_TWO,
-        sep='\n\n',
-        sep2='</s>',
-    )
-)
-
-# ChatGLM default template
-register_conv_template(
-    Conversation(
-        name='chatglm',
-        roles=('问', '答'),
-        sep_style=SeparatorStyle.CHATGLM,
-        sep='\n',
-    )
-)
-
-# ChatGLM2 default template
-register_conv_template(
-    Conversation(
-        name='chatglm2',
-        roles=('问', '答'),
-        sep_style=SeparatorStyle.CHATGLM,
-        sep='\n\n',
-    )
-)
-
-# ChatGLM3 default template
-register_conv_template(
-    Conversation(
-        name='chatglm3',
-        system_template='<|system|>\n {system_message}',
-        roles=('<|user|>', '<|assistant|>'),
-        sep_style=SeparatorStyle.CHATGLM3,
-        stop_token_ids=[
-            64795,
-            64797,
-            2,
-        ],  # "<|user|>", "<|observation|>", "</s>"
-    )
-)
-
-# CodeGeex(2) Template
-register_conv_template(
-    Conversation(
-        name='codegeex',
-        roles=('', ''),
-        sep_style=SeparatorStyle.NO_COLON_SINGLE,
-        sep='\n\n',
-        stop_token_ids=[0, 2],
-    )
-)
-
-# Dolly V2 default template
-register_conv_template(
-    Conversation(
-        name='dolly_v2',
-        system_message='Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n',
-        roles=('### Instruction', '### Response'),
-        sep_style=SeparatorStyle.DOLLY,
-        sep='\n\n',
-        sep2='### End',
-    )
-)
-
-# OpenAssistant Pythia default template
-register_conv_template(
-    Conversation(
-        name='oasst_pythia',
-        roles=('<|prompter|>', '<|assistant|>'),
-        sep_style=SeparatorStyle.NO_COLON_SINGLE,
-        sep='<|endoftext|>',
-    )
-)
-
-# OpenAssistant default template
-register_conv_template(
-    Conversation(
-        name='oasst_llama',
-        roles=('<|prompter|>', '<|assistant|>'),
-        sep_style=SeparatorStyle.NO_COLON_SINGLE,
-        sep='</s>',
-    )
-)
-
-# OpenChat 3.5 default template
-register_conv_template(
-    Conversation(
-        name='openchat_3.5',
-        roles=('GPT4 Correct User', 'GPT4 Correct Assistant'),
-        sep_style=SeparatorStyle.FALCON_CHAT,
-        sep='<|end_of_turn|>',
-    )
-)
-
-# Tulu default template
-register_conv_template(
-    Conversation(
-        name='tulu',
-        roles=('<|user|>', '<|assistant|>'),
-        sep_style=SeparatorStyle.ADD_NEW_LINE_SINGLE,
-        sep='\n',
-    )
-)
-
-# StableLM Alpha default template
-register_conv_template(
-    Conversation(
-        name='stablelm',
-        system_template='<|SYSTEM|>{system_message}',
-        system_message="""# StableLM Tuned (Alpha version)
-- StableLM is a helpful and harmless open-source AI language model developed by StabilityAI.
-- StableLM is excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
-- StableLM is more than just an information source, StableLM is also able to write poetry, short stories, and make jokes.
-- StableLM will refuse to participate in anything that could harm a human.
-""",
-        roles=('<|USER|>', '<|ASSISTANT|>'),
-        sep_style=SeparatorStyle.NO_COLON_SINGLE,
-        sep='',
-        stop_token_ids=[50278, 50279, 50277, 1, 0],
-    )
-)
-
-# Baize default template
-register_conv_template(
-    Conversation(
-        name='baize',
-        system_message='The following is a conversation between a human and an AI assistant named Baize (named after a mythical creature in Chinese folklore). Baize is an open-source AI assistant developed by UCSD and Sun Yat-Sen University. The human and the AI assistant take turns chatting. Human statements start with [|Human|] and AI assistant statements start with [|AI|]. The AI assistant always provides responses in as much detail as possible, and in Markdown format. The AI assistant always declines to engage with topics, questions and instructions related to unethical, controversial, or sensitive issues. Complete the transcript in exactly that format.\n',
-        roles=('[|Human|]', '[|AI|]'),
-        messages=(
-            ('[|Human|]', 'Hello!'),
-            ('[|AI|]', 'Hi!'),
-        ),
-        offset=2,
-        sep_style=SeparatorStyle.NO_COLON_SINGLE,
-        sep='\n',
-        stop_str='[|Human|]',
-    )
-)
-
-# RWKV-4-Raven default template
-register_conv_template(
-    Conversation(
-        name='rwkv',
-        roles=('Bob', 'Alice'),
-        messages=(
-            ('Bob', 'hi'),
-            (
-                'Alice',
-                'Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.',
-            ),
-        ),
-        offset=2,
-        sep_style=SeparatorStyle.RWKV,
-        sep='',
-        stop_str='\n\n',
-    )
-)
-
-# Buddy default template
-register_conv_template(
-    Conversation(
-        name='openbuddy',
-        system_message="""Consider a conversation between User (a human) and Assistant (named Buddy).
-Buddy is an INTP-T, a friendly, intelligent and multilingual AI assistant, by OpenBuddy team. GitHub: https://github.com/OpenBuddy/OpenBuddy
-Buddy cannot access the Internet.
-Buddy can fluently speak the user's language (e.g. English, Chinese).
-Buddy can generate poems, stories, code, essays, songs, parodies, and more.
-Buddy possesses vast knowledge about the world, history, and culture.
-Buddy's responses are always safe, creative, high-quality, human-like, and interesting.
-Buddy strictly refuses to discuss political, NSFW, or other unsafe topics.
-
-User: Hi.
-Assistant: Hi, I'm Buddy, your AI assistant. How can I help you today?""",
-        roles=('User', 'Assistant'),
-        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
-        sep='\n',
-    )
-)
-
-# Phoenix default template
-register_conv_template(
-    Conversation(
-        name='phoenix',
-        system_message="A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\n\n",
-        roles=('Human', 'Assistant'),
-        sep_style=SeparatorStyle.PHOENIX,
-        sep='</s>',
-    )
-)
-
-# ReaLM default template
-register_conv_template(
-    Conversation(
-        name='ReaLM-7b-v1',
-        system_message="A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\n\n",
-        roles=('Human', 'Assistant'),
-        sep_style=SeparatorStyle.PHOENIX,
-        sep='</s>',
-    )
-)
-
-# ChatGPT default template
-register_conv_template(
-    Conversation(
-        name='chatgpt',
-        system_message='You are a helpful assistant.',
-        roles=('user', 'assistant'),
-        sep_style=None,
-        sep=None,
-    )
-)
-
-# Claude default template
-register_conv_template(
-    Conversation(
-        name='claude',
-        roles=('Human', 'Assistant'),
-        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
-        sep='\n\n',
-    )
-)
-
-# MPT default template
-register_conv_template(
-    Conversation(
-        name='mpt-7b-chat',
-        system_template="""<|im_start|>system
-{system_message}""",
-        system_message="""- You are a helpful assistant chatbot trained by MosaicML.
-- You answer questions.
-- You are excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
-- You are more than just an information source, you are also able to write poetry, short stories, and make jokes.""",
-        roles=('<|im_start|>user', '<|im_start|>assistant'),
-        sep_style=SeparatorStyle.CHATML,
-        sep='<|im_end|>',
-        stop_token_ids=[50278, 0],
-    )
-)
-
-# MPT-30b-chat default template
-register_conv_template(
-    Conversation(
-        name='mpt-30b-chat',
-        system_template="""<|im_start|>system
-{system_message}""",
-        system_message="""A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.""",
-        roles=('<|im_start|>user', '<|im_start|>assistant'),
-        sep_style=SeparatorStyle.CHATML,
-        sep='<|im_end|>',
-        stop_token_ids=[50278, 0],
-    )
-)
-
-
 register_conv_template(
     Conversation(
         name='Hermes-2',
@@ -721,7 +343,7 @@ register_conv_template(
             6,
             7,
             8,
-        ],  # "<|endoftext|>", "<|im_start|>", "<|im_end|>", "<|im_sep|>"
+        ],
         stop_str='<|endoftext|>',
     )
 )
@@ -743,519 +365,19 @@ register_conv_template(
     )
 )
 
-# Lemur-70b-chat default template
-# reference: https://huggingface.co/OpenLemur/lemur-70b-chat-v1#generation
-register_conv_template(
-    Conversation(
-        name='lemur-70b-chat',
-        system_template="""<|im_start|>system
-{system_message}""",
-        system_message="""You are a helpful, respectful, and honest assistant.""",
-        roles=('<|im_start|>user', '<|im_start|>assistant'),
-        sep_style=SeparatorStyle.CHATML,
-        sep='<|im_end|>',
-        stop_token_ids=[32002, 0],
-    )
-)
-
-# MPT-30b-instruct default template
-# reference: https://huggingface.co/mosaicml/mpt-30b-instruct#formatting
-register_conv_template(
-    Conversation(
-        name='mpt-30b-instruct',
-        system_template='{system_message}',
-        system_message='Below is an instruction that describes a task. Write a response that appropriately completes the request.',
-        roles=('### Instruction', '### Response'),
-        sep_style=SeparatorStyle.ADD_NEW_LINE_SINGLE,
-        sep='\n\n',
-        stop_token_ids=[50278, 0],
-    )
-)
-
-# Bard default template
-# Reference: https://github.com/google/generative-ai-python/blob/9c99bcb474a991a97a2e7d62fcdb52db7ce40729/google/generativeai/discuss.py#L150
-#            https://github.com/google/generative-ai-python/blob/9c99bcb474a991a97a2e7d62fcdb52db7ce40729/google/generativeai/discuss.py#L40
-register_conv_template(
-    Conversation(
-        name='bard',
-        roles=('0', '1'),
-        sep_style=None,
-        sep=None,
-    )
-)
-
-# BiLLa default template
-register_conv_template(
-    Conversation(
-        name='billa',
-        roles=('Human', 'Assistant'),
-        sep_style=SeparatorStyle.ADD_COLON_SPACE_SINGLE,
-        sep='\n',
-        stop_str='Human:',
-    )
-)
-
-# RedPajama INCITE default template
-register_conv_template(
-    Conversation(
-        name='redpajama-incite',
-        roles=('<human>', '<bot>'),
-        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
-        sep='\n',
-        stop_str='<human>',
-    )
-)
-
-# h2oGPT default template
-register_conv_template(
-    Conversation(
-        name='h2ogpt',
-        roles=('<|prompt|>', '<|answer|>'),
-        sep_style=SeparatorStyle.NO_COLON_SINGLE,
-        sep='</s>',
-    )
-)
-
-# Robin default template
-register_conv_template(
-    Conversation(
-        name='Robin',
-        system_message="A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.",
-        roles=('###Human', '###Assistant'),
-        sep_style=SeparatorStyle.ROBIN,
-        sep='\n',
-        stop_token_ids=[2, 396],
-        stop_str='###',
-    )
-)
-
-# Snoozy default template
-# Reference: https://github.com/nomic-ai/gpt4all/blob/d4861030b778da6db59d21d2927a4aba4f9f1f43/gpt4all-bindings/python/gpt4all/gpt4all.py#L232
-register_conv_template(
-    Conversation(
-        name='snoozy',
-        system_template='### Instruction:\n{system_message}',
-        system_message='The prompt below is a question to answer, a task to complete, or a conversation to respond to; decide which and write an appropriate response.',
-        roles=('### Prompt', '### Response'),
-        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
-        sep='\n',
-        stop_str='###',
-    )
-)
-
-# manticore default template
-register_conv_template(
-    Conversation(
-        name='manticore',
-        roles=('USER', 'ASSISTANT'),
-        sep_style=SeparatorStyle.ADD_COLON_TWO,
-        sep='\n',
-        sep2='</s>',
-    )
-)
-
-# Falcon default template
-register_conv_template(
-    Conversation(
-        name='falcon',
-        roles=('User', 'Assistant'),
-        messages=[],
-        sep_style=SeparatorStyle.RWKV,
-        sep='\n',
-        sep2='<|endoftext|>',
-        stop_str='\nUser',  # use stop_str to stop generation after stop_token_ids, it will also remove stop_str from the generated text
-        stop_token_ids=[
-            0,
-            1,
-            2,
-            3,
-            4,
-            5,
-            6,
-            7,
-            8,
-            9,
-            10,
-            11,
-        ],  # it better only put special tokens here, because tokenizer only remove special tokens
-    )
-)
-
-# ChangGPT default template
-register_conv_template(
-    Conversation(
-        name='polyglot_changgpt',
-        roles=('B', 'A'),
-        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
-        sep='\n',
-    )
-)
-
-# tigerbot template
-register_conv_template(
-    Conversation(
-        name='tigerbot',
-        system_message='A chat between a curious user and an artificial intelligence assistant. '
-        "The assistant gives helpful, detailed, and polite answers to the user's questions.",
-        roles=('### Instruction', '### Response'),
-        sep_style=SeparatorStyle.ROBIN,
-        sep='\n\n',
-        stop_str='###',
-    )
-)
-
-# ref: https://huggingface.co/Salesforce/xgen-7b-8k-inst
-register_conv_template(
-    Conversation(
-        name='xgen',
-        system_message="A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\n\n",
-        roles=('### Human', '### Assistant'),
-        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
-        sep='\n',
-        stop_token_ids=[50256],
-    )
-)
-
-# Internlm-chat template
-register_conv_template(
-    Conversation(
-        name='internlm-chat',
-        system_message="A chat between a curious <|User|> and an <|Bot|>. The <|Bot|> gives helpful, detailed, and polite answers to the <|User|>'s questions.\n\n",
-        roles=('<|User|>', '<|Bot|>'),
-        sep_style=SeparatorStyle.CHATINTERN,
-        sep='<eoh>',
-        sep2='<eoa>',
-        stop_token_ids=[1, 103028],
-        stop_str='<|User|>',
-    )
-)
 
-# StarChat template
-# reference: https://huggingface.co/spaces/HuggingFaceH4/starchat-playground/blob/main/dialogues.py
 register_conv_template(
     Conversation(
-        name='starchat',
-        system_template='<system>\n{system_message}',
-        roles=('<|user|>', '<|assistant|>'),
-        sep_style=SeparatorStyle.CHATML,
+        name='phi3-chat',
+        system_template='<|system|>\n{system_message}',
+        system_message='You are an AI assistant whose name is Phi-3.',
+        roles=('<|user|>\n', '<|assistant|>\n'),
+        sep_style=SeparatorStyle.MPT,
         sep='<|end|>',
-        stop_token_ids=[0, 49155],
-        stop_str='<|end|>',
-    )
-)
-
-# Baichuan-13B-Chat template
-register_conv_template(
-    # source: https://huggingface.co/baichuan-inc/Baichuan-13B-Chat/blob/19ef51ba5bad8935b03acd20ff04a269210983bc/modeling_baichuan.py#L555
-    # https://huggingface.co/baichuan-inc/Baichuan-13B-Chat/blob/main/generation_config.json
-    # https://github.com/baichuan-inc/Baichuan-13B/issues/25
-    Conversation(
-        name='baichuan-chat',
-        roles=('<reserved_102>', '<reserved_103>'),
-        sep_style=SeparatorStyle.NO_COLON_SINGLE,
-        sep='',
-        stop_token_ids=[],
-    )
-)
-
-# Baichuan2-13B-Chat template
-register_conv_template(
-    # source: https://huggingface.co/baichuan-inc/Baichuan2-13B-Chat/blob/c6f8592a60b4ad73c210b28dd2ab3cca51abbf93/modeling_baichuan.py#L773
-    # https://huggingface.co/baichuan-inc/Baichuan2-13B-Chat/blob/main/generation_config.json
-    # https://github.com/baichuan-inc/Baichuan2/issues/62
-    Conversation(
-        name='baichuan2-chat',
-        roles=('<reserved_106>', '<reserved_107>'),
-        sep_style=SeparatorStyle.NO_COLON_SINGLE,
-        sep='',
-        stop_token_ids=[],
-    )
-)
-
-# Mistral template
-# source: https://docs.mistral.ai/llm/mistral-instruct-v0.1#chat-template
-register_conv_template(
-    Conversation(
-        name='mistral',
-        system_template='[INST]{system_message}\n',
-        roles=('[INST]', '[/INST]'),
-        sep_style=SeparatorStyle.LLAMA2,
-        sep=' ',
-        sep2='</s>',
-    )
-)
-
-# llama2 template
-# reference: https://huggingface.co/blog/codellama#conversational-instructions
-# reference: https://github.com/facebookresearch/llama/blob/1a240688810f8036049e8da36b073f63d2ac552c/llama/generation.py#L212
-register_conv_template(
-    Conversation(
-        name='llama-2',
-        system_template='[INST] <<SYS>>\n{system_message}\n<</SYS>>\n\n',
-        roles=('[INST]', '[/INST]'),
-        sep_style=SeparatorStyle.LLAMA2,
-        sep=' ',
-        sep2=' </s><s>',
-    )
-)
-
-register_conv_template(
-    Conversation(
-        name='cutegpt',
-        roles=('问：', '答：\n'),
-        sep_style=SeparatorStyle.NO_COLON_TWO,
-        sep='\n',
-        sep2='\n',
-        stop_str='<end>',
-    )
-)
-
-# OpenOrcaxOpenChat-naPreview2-13B template
-register_conv_template(
-    Conversation(
-        name='open-orca',
-        system_template='{system_message}',
-        system_message='You are a helpful assistant. Please answer truthfully and write out your '
-        'thinking step by step to be sure you get the right answer. If you make a mistake or encounter '
-        "an error in your thinking, say so out loud and attempt to correct it. If you don't know or "
-        "aren't sure about something, say so clearly. You will act as a professional logician, mathematician, "
-        'and physicist. You will also act as the most appropriate type of expert to answer any particular '
-        'question or solve the relevant problem; state which expert type your are, if so. Also think of '
-        'any particular named expert that would be ideal to answer the relevant question or solve the '
-        'relevant problem; name and act as them, if appropriate.',
-        roles=('User', 'Assistant'),
-        sep_style=SeparatorStyle.ADD_COLON_SPACE_SINGLE,
-        sep='<|end_of_turn|>\n',
-        stop_token_ids=[32000, 32001],  # "<|end_of_turn|>"
-        stop_str='User',
-    )
-)
-
-# Open-Orca/Mistral-7B-OpenOrca template
-# source: https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca
-# reference: https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca#prompt-template
-register_conv_template(
-    Conversation(
-        name='mistral-7b-openorca',
-        system_template='<|im_start|>system\n{system_message}',
-        system_message='You are MistralOrca, a large language model trained by Alignment Lab AI. Write out your reasoning step-by-step to be sure you get the right answers!',
-        roles=('<|im_start|>user', '<|im_start|>assistant'),
-        sep_style=SeparatorStyle.CHATML,
-        sep='<|im_end|>',
-        stop_token_ids=[32000, 32001],
-    )
-)
-
-# Qwen-chat default template
-# source: https://huggingface.co/Qwen/Qwen-7B-Chat/blob/main/qwen_generation_utils.py#L130
-register_conv_template(
-    Conversation(
-        name='qwen-7b-chat',
-        system_template='<|im_start|>system\n{system_message}',
-        system_message='You are a helpful assistant.',
-        roles=('<|im_start|>user', '<|im_start|>assistant'),
-        sep_style=SeparatorStyle.CHATML,
-        sep='<|im_end|>',
         stop_token_ids=[
-            151643,
-            151644,
-            151645,
-        ],  # "<|endoftext|>", "<|im_start|>", "<|im_end|>"
-        stop_str='<|endoftext|>',
-    )
-)
-
-
-# AquilaChat default template
-# source: https://github.com/FlagAI-Open/FlagAI/blob/master/examples/Aquila/Aquila-chat/cyg_conversation.py
-register_conv_template(
-    Conversation(
-        name='aquila-chat',
-        system_message='A chat between a curious human and an artificial intelligence assistant. '
-        "The assistant gives helpful, detailed, and polite answers to the human's questions.",
-        roles=('Human', 'Assistant'),
-        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
-        sep='###',
-        sep2='',
-        stop_str=['###', '</s>', '[UNK]'],
-    )
-)
-# AquilaChat2-34B default template
-# source: https://huggingface.co/BAAI/AquilaChat2-34B/blob/4608b75855334b93329a771aee03869dbf7d88cc/predict.py#L212
-register_conv_template(
-    Conversation(
-        name='aquila-legacy',
-        system_message='A chat between a curious human and an artificial intelligence assistant. '
-        "The assistant gives helpful, detailed, and polite answers to the human's questions.\n\n",
-        roles=('### Human: ', '### Assistant: '),
-        offset=0,
-        sep_style=SeparatorStyle.NO_COLON_TWO,
-        sep='\n',
-        sep2='</s>',
-        stop_str=['</s>', '[UNK]'],
-    )
-)
-# AquilaChat2-7B-16K and AquilaChat2-34B-16K default template
-# source: https://huggingface.co/BAAI/AquilaChat2-34B/blob/4608b75855334b93329a771aee03869dbf7d88cc/predict.py#L227
-register_conv_template(
-    Conversation(
-        name='aquila',
-        system_message='A chat between a curious human and an artificial intelligence assistant. '
-        "The assistant gives helpful, detailed, and polite answers to the human's questions.",
-        roles=('Human', 'Assistant'),
-        offset=0,
-        sep_style=SeparatorStyle.ADD_COLON_TWO,
-        sep='###',
-        sep2='</s>',
-        stop_str=['</s>', '[UNK]'],
-    )
-)
-
-# AquilaChat2-7B default template
-# source: https://huggingface.co/BAAI/AquilaChat2-34B/blob/4608b75855334b93329a771aee03869dbf7d88cc/predict.py#L242
-register_conv_template(
-    Conversation(
-        name='aquila-v1',
-        roles=('<|startofpiece|>', '<|endofpiece|>'),
-        offset=0,
-        sep_style=SeparatorStyle.NO_COLON_TWO,
-        sep='',
-        sep2='</s>',
-        stop_str=['</s>', '<|endoftext|>'],
-    )
-)
-
-# Llama2-Chinese default template
-# source: https://huggingface.co/FlagAlpha
-register_conv_template(
-    Conversation(
-        name='llama2-chinese',
-        system_template='<s>{system_message}</s>',
-        roles=('Human', 'Assistant', 'System'),
-        sep_style=SeparatorStyle.ADD_COLON_TWO,
-        sep='\n',
-        sep2='\n</s><s>',
-        stop_str='</s>',
-    )
-)
-
-# Vigogne Instruct default template
-# source: https://github.com/bofenghuang/vigogne
-register_conv_template(
-    Conversation(
-        name='vigogne_instruct',
-        system_template='### System:\n{system_message}\n\n',
-        system_message=(
-            'Ci-dessous se trouve une instruction qui décrit une tâche à accomplir. Rédigez une réponse qui répond de manière'
-            ' précise à la demande.'
-        ),
-        roles=('### Instruction', '### Response'),
-        sep_style=SeparatorStyle.DOLLY,
-        sep='\n\n',
-        sep2='</s>',
-    )
-)
-
-# Vigogne Chat default template
-register_conv_template(
-    Conversation(
-        name='vigogne_chat_v2',
-        system_template='<|system|>: {system_message}',
-        system_message=(
-            'Vous êtes Vigogne, un assistant IA créé par Zaion Lab. Vous suivez extrêmement bien les instructions. Aidez'
-            ' autant que vous le pouvez.'
-        ),
-        roles=('<|user|>', '<|assistant|>'),
-        sep_style=SeparatorStyle.ADD_COLON_TWO,
-        sep='\n',
-        sep2='</s>\n',
-        stop_str='<|user|>',
-    )
-)
-
-register_conv_template(
-    Conversation(
-        name='vigogne_chat_v3',
-        system_template='[INST] <<SYS>>\n{system_message}\n<</SYS>>\n\n',
-        system_message=(
-            'Vous êtes Vigogne, un assistant IA créé par Zaion Lab. Vous suivez extrêmement bien les instructions. Aidez'
-            ' autant que vous le pouvez.'
-        ),
-        roles=('[INST]', '[/INST]'),
-        sep_style=SeparatorStyle.LLAMA2,
-        sep=' ',
-        sep2=' </s>',
-    )
-)
-
-# Falcon 180B chat template
-# source: https://huggingface.co/spaces/tiiuae/falcon-180b-demo/blob/d1590ee7fae9b6ce331ba7808e61a29dcce9239f/app.py#L28-L37
-register_conv_template(
-    Conversation(
-        name='falcon-chat',
-        roles=('User', 'Falcon'),
-        system_template='System: {system_message}',
-        messages=[],
-        sep_style=SeparatorStyle.FALCON_CHAT,
-        sep='\n',
-        sep2='<|endoftext|>',
-        stop_str='\nUser:',  # use stop_str to stop generation after stop_token_ids, it will also remove stop_str from the generated text
-    )
-)
-
-# Phind template
-# source: https://huggingface.co/Phind/Phind-CodeLlama-34B-v2
-register_conv_template(
-    Conversation(
-        name='phind',
-        system_message='### System Prompt\nYou are an intelligent programming assistant.',
-        roles=('### User Message', '### Assistant'),
-        messages=(),
-        offset=0,
-        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
-        sep='\n\n',
-    )
-)
-
-# Metharme formatting for Pygmalion models
-# source: https://huggingface.co/PygmalionAI/pygmalion-2-13b
-register_conv_template(
-    Conversation(
-        name='metharme',
-        system_template='<|system|>{system_message}',
-        system_message="""Enter RP mode. You shall reply to the user while staying
-        in character. Your responses must be detailed, creative, immersive, and drive the scenario
-        forward.""",
-        roles=('<|user|>', '<|model|>'),
-        sep_style=SeparatorStyle.NO_COLON_SINGLE,
-        sep='',
-        stop_str='<|user|>',
-    )
-)
-
-# Zephyr template
-# reference: https://huggingface.co/spaces/HuggingFaceH4/zephyr-playground/blob/main/dialogues.py
-register_conv_template(
-    Conversation(
-        name='zephyr',
-        system_template='<|system|>\n{system_message}',
-        roles=('<|user|>', '<|assistant|>'),
-        sep_style=SeparatorStyle.CHATML,
-        sep='</s>',
-        stop_token_ids=[2],
-        stop_str='</s>',
-    )
-)
-
-# InternVL-ZH template
-register_conv_template(
-    Conversation(
-        name='internvl_zh',
-        system_template='',
-        roles=('<human>', '<bot>'),
-        sep_style=SeparatorStyle.INTERNVL_ZH,
-        sep=' ',
-        sep2='</s>',
+            2,
+            32000,
+            32007
+        ]
     )
 )
-

modeling_intern_vit.py

@@ -26,9 +26,9 @@ try:
     except:  # v2
         from flash_attn.flash_attn_interface import \
             flash_attn_varlen_qkvpacked_func as flash_attn_unpadded_qkvpacked_func
-    
+
     from flash_attn.bert_padding import pad_input, unpad_input
-    
+
     has_flash_attn = True
 except:
     print('FlashAttention is not installed.')
@@ -47,12 +47,12 @@ class FlashAttention(nn.Module):
         attention_dropout: The dropout rate to apply to the attention
                            (default: 0.0)
     """
-    
+
     def __init__(self, softmax_scale=None, attention_dropout=0.0, device=None, dtype=None):
         super().__init__()
         self.softmax_scale = softmax_scale
         self.dropout_p = attention_dropout
-    
+
     def forward(self, qkv, key_padding_mask=None, causal=False, cu_seqlens=None,
                 max_s=None, need_weights=False):
         """Implements the multihead softmax attention.
@@ -65,7 +65,7 @@ class FlashAttention(nn.Module):
         assert not need_weights
         assert qkv.dtype in [torch.float16, torch.bfloat16]
         assert qkv.is_cuda
-        
+
         if cu_seqlens is None:
             batch_size = qkv.shape[0]
             seqlen = qkv.shape[1]
@@ -97,7 +97,7 @@ class FlashAttention(nn.Module):
                 qkv, cu_seqlens, max_s, self.dropout_p if self.training else 0.0,
                 softmax_scale=self.softmax_scale, causal=causal
             )
-        
+
         return output, None
 
 
@@ -129,6 +129,12 @@ except Exception:
     pass
 
 
+NORM2FN = {
+    'rms_norm': InternRMSNorm,
+    'layer_norm': nn.LayerNorm,
+}
+
+
 class InternVisionEmbeddings(nn.Module):
     def __init__(self, config: InternVisionConfig):
         super().__init__()
@@ -154,7 +160,7 @@ class InternVisionEmbeddings(nn.Module):
         target_dtype = pos_embed.dtype
         pos_embed = pos_embed.float().reshape(
             1, self.image_size // self.patch_size, self.image_size // self.patch_size, -1).permute(0, 3, 1, 2)
-        pos_embed = F.interpolate(pos_embed, size=(H, W), mode='bicubic', align_corners=False).\
+        pos_embed = F.interpolate(pos_embed, size=(H, W), mode='bicubic', align_corners=False). \
             reshape(1, -1, H * W).permute(0, 2, 1).to(target_dtype)
         return pos_embed
 
@@ -267,11 +273,12 @@ class InternVisionEncoderLayer(nn.Module):
         super().__init__()
         self.embed_dim = config.hidden_size
         self.intermediate_size = config.intermediate_size
+        self.norm_type = config.norm_type
 
         self.attn = InternAttention(config)
         self.mlp = InternMLP(config)
-        self.norm1 = InternRMSNorm(self.embed_dim, eps=config.layer_norm_eps)
-        self.norm2 = InternRMSNorm(self.embed_dim, eps=config.layer_norm_eps)
+        self.norm1 = NORM2FN[self.norm_type](self.embed_dim, eps=config.layer_norm_eps)
+        self.norm2 = NORM2FN[self.norm_type](self.embed_dim, eps=config.layer_norm_eps)
 
         self.ls1 = nn.Parameter(config.initializer_factor * torch.ones(self.embed_dim))
         self.ls2 = nn.Parameter(config.initializer_factor * torch.ones(self.embed_dim))

modeling_internlm2.py

@@ -48,6 +48,18 @@ _CONFIG_FOR_DOC = 'InternLM2Config'
 
 flash_attn_func, flash_attn_varlen_func = None, None
 pad_input, index_first_axis, unpad_input = None, None, None
+try:
+    from flash_attn import flash_attn_func as _flash_attn_func
+    from flash_attn import flash_attn_varlen_func as _flash_attn_varlen_func
+    from flash_attn.bert_padding import index_first_axis as _index_first_axis
+    from flash_attn.bert_padding import pad_input as _pad_input
+    from flash_attn.bert_padding import unpad_input as _unpad_input
+
+    flash_attn_func, flash_attn_varlen_func = _flash_attn_func, _flash_attn_varlen_func
+    pad_input, index_first_axis, unpad_input = _pad_input, _index_first_axis, _unpad_input
+    has_flash_attn = True
+except:
+    has_flash_attn = False
 
 
 def _import_flash_attn():
@@ -149,7 +161,7 @@ class InternLM2RotaryEmbedding(nn.Module):
 
     def _set_cos_sin_cache(self, seq_len, device, dtype):
         self.max_seq_len_cached = seq_len
-        t = torch.arange(self.max_seq_len_cached, device=device, dtype=self.inv_freq.dtype)
+        t = torch.arange(self.max_seq_len_cached, device=device).to(dtype=self.inv_freq.dtype)
 
         freqs = torch.einsum('i,j->ij', t, self.inv_freq)
         # Different from paper, but it uses a different permutation in order to obtain the same calculation
@@ -178,7 +190,7 @@ class InternLM2LinearScalingRotaryEmbedding(InternLM2RotaryEmbedding):
 
     def _set_cos_sin_cache(self, seq_len, device, dtype):
         self.max_seq_len_cached = seq_len
-        t = torch.arange(self.max_seq_len_cached, device=device, dtype=self.inv_freq.dtype)
+        t = torch.arange(self.max_seq_len_cached, device=device).to(dtype=self.inv_freq.dtype)
         t = t / self.scaling_factor
 
         freqs = torch.einsum('i,j->ij', t, self.inv_freq)
@@ -208,7 +220,7 @@ class InternLM2DynamicNTKScalingRotaryEmbedding(InternLM2RotaryEmbedding):
             inv_freq = 1.0 / (base ** (torch.arange(0, self.dim, 2).float().to(device) / self.dim))
             self.register_buffer('inv_freq', inv_freq, persistent=False)
 
-        t = torch.arange(self.max_seq_len_cached, device=device, dtype=self.inv_freq.dtype)
+        t = torch.arange(self.max_seq_len_cached, device=device).to(dtype=self.inv_freq.dtype)
 
         freqs = torch.einsum('i,j->ij', t, self.inv_freq)
         # Different from paper, but it uses a different permutation in order to obtain the same calculation
@@ -697,6 +709,7 @@ class InternLM2PreTrainedModel(PreTrainedModel):
     supports_gradient_checkpointing = True
     _no_split_modules = ['InternLM2DecoderLayer']
     _skip_keys_device_placement = 'past_key_values'
+    _supports_flash_attn_2 = True
 
     def _init_weights(self, module):
         std = self.config.initializer_range
@@ -795,6 +808,9 @@ class InternLM2Model(InternLM2PreTrainedModel):
         self.padding_idx = config.pad_token_id
         self.vocab_size = config.vocab_size
         self.config = config
+        if not has_flash_attn:
+            self.config.attn_implementation = 'eager'
+            print('Warning: Flash attention is not available, using eager attention instead.')
 
         self.tok_embeddings = nn.Embedding(config.vocab_size, config.hidden_size, self.padding_idx)
 
@@ -1082,13 +1098,16 @@ class InternLM2ForCausalLM(InternLM2PreTrainedModel):
             output = (logits,) + outputs[1:]
             return (loss,) + output if loss is not None else output
 
-        return CausalLMOutputWithPast(
+        device = input_ids.device if input_ids is not None else inputs_embeds.device
+        output = CausalLMOutputWithPast(
             loss=loss,
             logits=logits,
             past_key_values=outputs.past_key_values,
             hidden_states=outputs.hidden_states,
             attentions=outputs.attentions,
         )
+        output['logits'] = output['logits'].to(device)
+        return output
 
     def prepare_inputs_for_generation(
         self, input_ids, past_key_values=None, attention_mask=None, inputs_embeds=None, **kwargs

modeling_internvl_chat.py

@@ -1,13 +1,13 @@
 # --------------------------------------------------------
 # InternVL
-# Copyright (c) 2023 OpenGVLab
+# Copyright (c) 2024 OpenGVLab
 # Licensed under The MIT License [see LICENSE for details]
 # --------------------------------------------------------
 import warnings
 from typing import Any, List, Optional, Tuple, Union
 
 import torch.utils.checkpoint
-from peft import LoraConfig, get_peft_model
+import transformers
 from torch import nn
 from torch.nn import CrossEntropyLoss
 from transformers import (AutoModel, GenerationConfig, LlamaForCausalLM,
@@ -17,54 +17,30 @@ from transformers.modeling_utils import PreTrainedModel
 from transformers.utils import ModelOutput, logging
 
 from .configuration_internvl_chat import InternVLChatConfig
+from .conversation import get_conv_template
 from .modeling_intern_vit import InternVisionModel
 from .modeling_internlm2 import InternLM2ForCausalLM
 
 logger = logging.get_logger(__name__)
 
 
-def window_partition(x, window_size):
-    """
-    Args:
-        x: (B, C, H, W)
-        window_size (int): window size, assuming square window
+def version_cmp(v1, v2, op='eq'):
+    import operator
 
-    Returns:
-        windows: (num_windows*B, C, window_size, window_size)
-    """
-    B, C, H, W = x.shape
-    assert H % window_size == 0 and W % window_size == 0, 'H and W must be divisible by window_size'
-
-    x = x.view(B, C, H // window_size, window_size, W // window_size, window_size)
-    windows = x.permute(0, 2, 4, 1, 3, 5).contiguous().view(-1, C, window_size, window_size)
-    return windows
-
-
-def window_reverse(windows, window_size, H, W):
-    """
-    Args:
-        windows: (num_windows*B, window_size, window_size, C)
-        window_size (int): Window size
-        H (int): Height of image
-        W (int): Width of image
-
-    Returns:
-        x: (B, H * W, C)
-    """
-    B = int(windows.shape[0] / (H * W / window_size / window_size))
-    x = windows.view(B, H // window_size, W // window_size, window_size, window_size, -1)
-    x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, H * W, -1)
-    return x
+    from packaging import version
+    op_func = getattr(operator, op)
+    return op_func(version.parse(v1), version.parse(v2))
 
 
 class InternVLChatModel(PreTrainedModel):
     config_class = InternVLChatConfig
     main_input_name = 'pixel_values'
-    _no_split_modules = ['InternVisionEncoderLayer', 'LlamaDecoderLayer', 'LlamaForCausalLM']
+    _no_split_modules = ['InternVisionModel', 'LlamaDecoderLayer', 'InternLM2DecoderLayer']
 
     def __init__(self, config: InternVLChatConfig, vision_model=None, language_model=None):
         super().__init__(config)
 
+        assert version_cmp(transformers.__version__, '4.36.2', 'ge')
         image_size = config.force_image_size or config.vision_config.image_size
         patch_size = config.vision_config.patch_size
         self.patch_size = patch_size
@@ -72,7 +48,6 @@ class InternVLChatModel(PreTrainedModel):
         self.template = config.template
         self.num_image_token = int((image_size // patch_size) ** 2 * (config.downsample_ratio ** 2))
         self.downsample_ratio = config.downsample_ratio
-        self.image_fold = config.image_fold
         self.ps_version = config.ps_version
 
         logger.info(f'num_image_token: {self.num_image_token}')
@@ -101,44 +76,7 @@ class InternVLChatModel(PreTrainedModel):
             nn.Linear(llm_hidden_size, llm_hidden_size)
         )
 
-        # if config.force_image_size != config.vision_config.image_size:
-        #     self.vision_model.resize_pos_embeddings(
-        #         old_size=config.vision_config.image_size,
-        #         new_size=config.force_image_size,
-        #         patch_size=config.vision_config.patch_size
-        #     )
-
         self.img_context_token_id = None
-        self.neftune_alpha = None
-
-        if config.use_backbone_lora:
-            self.wrap_backbone_lora(r=config.use_backbone_lora, lora_alpha=2 * config.use_backbone_lora)
-
-        if config.use_llm_lora:
-            self.wrap_llm_lora(r=config.use_llm_lora, lora_alpha=2 * config.use_llm_lora)
-
-    def wrap_backbone_lora(self, r=128, lora_alpha=256, lora_dropout=0.05):
-        lora_config = LoraConfig(
-            r=r,
-            target_modules=['attn.qkv', 'attn.proj', 'mlp.fc1', 'mlp.fc2'],
-            lora_alpha=lora_alpha,
-            lora_dropout=lora_dropout,
-        )
-        self.vision_model = get_peft_model(self.vision_model, lora_config)
-        self.vision_model.print_trainable_parameters()
-
-    def wrap_llm_lora(self, r=128, lora_alpha=256, lora_dropout=0.05):
-        lora_config = LoraConfig(
-            r=r,
-            target_modules=['self_attn.q_proj', 'self_attn.k_proj', 'self_attn.v_proj', 'self_attn.o_proj',
-                            'mlp.gate_proj', 'mlp.down_proj', 'mlp.up_proj'],
-            lora_alpha=lora_alpha,
-            lora_dropout=lora_dropout,
-            task_type='CAUSAL_LM'
-        )
-        self.language_model = get_peft_model(self.language_model, lora_config)
-        self.language_model.enable_input_require_grads()
-        self.language_model.print_trainable_parameters()
 
     def forward(
             self,
@@ -235,17 +173,7 @@ class InternVLChatModel(PreTrainedModel):
             x = x.permute(0, 2, 1, 3).contiguous()
         return x
 
-    def noised_embed(self, vit_embeds, noise_alpha=5):
-        dims = torch.tensor(vit_embeds.size(1) * vit_embeds.size(2))
-        mag_norm = noise_alpha / torch.sqrt(dims)
-        noise = torch.zeros_like(vit_embeds).uniform_(-mag_norm, mag_norm)
-        return vit_embeds + noise
-
     def extract_feature(self, pixel_values):
-        if self.image_fold:
-            image_size = pixel_values.size(-1)  # B, C, H, W
-            pixel_values = window_partition(pixel_values, window_size=image_size // self.image_fold)  # 4B, C, H/2, W/2
-
         if self.select_layer == -1:
             vit_embeds = self.vision_model(
                 pixel_values=pixel_values,
@@ -258,50 +186,94 @@ class InternVLChatModel(PreTrainedModel):
                 return_dict=True).hidden_states[self.select_layer]
         vit_embeds = vit_embeds[:, 1:, :]
 
-        if self.training and self.neftune_alpha is not None:
-            vit_embeds = self.noised_embed(vit_embeds, self.neftune_alpha)
-
-        if self.image_fold:
-            vit_embeds = window_reverse(vit_embeds, window_size=image_size // (self.image_fold * self.patch_size),
-                                        H=image_size // self.patch_size, W=image_size // self.patch_size)
-
-        # if torch.distributed.get_rank() == 0:
-        #     print("before pixel shuffle:", vit_embeds.shape)
         h = w = int(vit_embeds.shape[1] ** 0.5)
         vit_embeds = vit_embeds.reshape(vit_embeds.shape[0], h, w, -1)
         vit_embeds = self.pixel_shuffle(vit_embeds, scale_factor=self.downsample_ratio)
         vit_embeds = vit_embeds.reshape(vit_embeds.shape[0], -1, vit_embeds.shape[-1])
-        # if torch.distributed.get_rank() == 0:
-        #     print("after pixel shuffle:", vit_embeds.shape)
         vit_embeds = self.mlp1(vit_embeds)
         return vit_embeds
 
-    def chat(self, tokenizer, pixel_values, question, generation_config, history=None, return_history=False,
-             IMG_START_TOKEN='<img>', IMG_END_TOKEN='</img>', IMG_CONTEXT_TOKEN='<IMG_CONTEXT>'):
+    def batch_chat(self, tokenizer, pixel_values, questions, generation_config, num_patches_list=None,
+                   history=None, return_history=False, IMG_START_TOKEN='<img>', IMG_END_TOKEN='</img>',
+                   IMG_CONTEXT_TOKEN='<IMG_CONTEXT>', verbose=False, image_counts=None):
+        if history is not None or return_history:
+            print('Now multi-turn chat is not supported in batch_chat.')
+            raise NotImplementedError
+
+        if image_counts is not None:
+            num_patches_list = image_counts
+            print('Warning: `image_counts` is deprecated. Please use `num_patches_list` instead.')
 
         img_context_token_id = tokenizer.convert_tokens_to_ids(IMG_CONTEXT_TOKEN)
         self.img_context_token_id = img_context_token_id
-        if tokenizer.convert_tokens_to_ids('<|im_end|>') != 0:
-            eos_token_id = tokenizer.convert_tokens_to_ids('<|im_end|>')  # 92542, InternLM2
-        else:
-            eos_token_id = tokenizer.eos_token_id
 
-        from .conversation import get_conv_template
+        if verbose and pixel_values is not None:
+            image_bs = pixel_values.shape[0]
+            print(f'dynamic ViT batch size: {image_bs}')
+
+        queries = []
+        for idx, num_patches in enumerate(num_patches_list):
+            question = questions[idx]
+            if pixel_values is not None and '<image>' not in question:
+                question = '<image>\n' + question
+            template = get_conv_template(self.template)
+            template.append_message(template.roles[0], question)
+            template.append_message(template.roles[1], None)
+            query = template.get_prompt()
+
+            image_tokens = IMG_START_TOKEN + IMG_CONTEXT_TOKEN * self.num_image_token * num_patches + IMG_END_TOKEN
+            query = query.replace('<image>', image_tokens, 1)
+            queries.append(query)
+
+        tokenizer.padding_side = 'left'
+        model_inputs = tokenizer(queries, return_tensors='pt', padding=True)
+        input_ids = model_inputs['input_ids'].cuda()
+        attention_mask = model_inputs['attention_mask'].cuda()
+        eos_token_id = tokenizer.convert_tokens_to_ids(template.sep)
+        generation_config['eos_token_id'] = eos_token_id
+        generation_output = self.generate(
+            pixel_values=pixel_values,
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            **generation_config
+        )
+        responses = tokenizer.batch_decode(generation_output, skip_special_tokens=True)
+        responses = [response.split(template.sep)[0].strip() for response in responses]
+        return responses
+
+    def chat(self, tokenizer, pixel_values, question, generation_config, history=None, return_history=False,
+             num_patches_list=None, IMG_START_TOKEN='<img>', IMG_END_TOKEN='</img>', IMG_CONTEXT_TOKEN='<IMG_CONTEXT>',
+             verbose=False):
+
+        if history is None and pixel_values is not None and '<image>' not in question:
+            question = '<image>\n' + question
+
+        if num_patches_list is None:
+            num_patches_list = [pixel_values.shape[0]] if pixel_values is not None else []
+        assert pixel_values is None or len(pixel_values) == sum(num_patches_list)
+
+        img_context_token_id = tokenizer.convert_tokens_to_ids(IMG_CONTEXT_TOKEN)
+        self.img_context_token_id = img_context_token_id
 
         template = get_conv_template(self.template)
-        image_bs = pixel_values.shape[0]
-        print(f'dynamic ViT batch size: {image_bs}')
-        if history is None:
-            history = []
-            image_tokens = IMG_START_TOKEN + IMG_CONTEXT_TOKEN * self.num_image_token * image_bs + IMG_END_TOKEN
-            question = image_tokens + '\n' + question
-        else:
-            for (old_question, old_answer) in history:
-                template.append_message(template.roles[0], old_question)
-                template.append_message(template.roles[1], old_answer)
+        eos_token_id = tokenizer.convert_tokens_to_ids(template.sep)
+
+        history = [] if history is None else history
+        for (old_question, old_answer) in history:
+            template.append_message(template.roles[0], old_question)
+            template.append_message(template.roles[1], old_answer)
         template.append_message(template.roles[0], question)
         template.append_message(template.roles[1], None)
         query = template.get_prompt()
+
+        if verbose and pixel_values is not None:
+            image_bs = pixel_values.shape[0]
+            print(f'dynamic ViT batch size: {image_bs}')
+
+        for num_patches in num_patches_list:
+            image_tokens = IMG_START_TOKEN + IMG_CONTEXT_TOKEN * self.num_image_token * num_patches + IMG_END_TOKEN
+            query = query.replace('<image>', image_tokens, 1)
+
         model_inputs = tokenizer(query, return_tensors='pt')
         input_ids = model_inputs['input_ids'].cuda()
         attention_mask = model_inputs['attention_mask'].cuda()
@@ -313,15 +285,16 @@ class InternVLChatModel(PreTrainedModel):
             **generation_config
         )
         response = tokenizer.batch_decode(generation_output, skip_special_tokens=True)[0]
-        response = response.split('<|im_end|>')[0].strip()  # for InternLM2
+        response = response.split(template.sep)[0].strip()
         history.append((question, response))
         if return_history:
             return response, history
         else:
-            query_to_print = query.replace(image_tokens, '<image>')
-            print(query_to_print, response)
+            query_to_print = query.replace(IMG_CONTEXT_TOKEN, '')
+            query_to_print = query_to_print.replace(f'{IMG_START_TOKEN}{IMG_END_TOKEN}', '<image>')
+            if verbose:
+                print(query_to_print, response)
             return response
-        return response
 
     @torch.no_grad()
     def generate(
@@ -342,7 +315,6 @@ class InternVLChatModel(PreTrainedModel):
                 vit_embeds = visual_features
             else:
                 vit_embeds = self.extract_feature(pixel_values)
-
             input_embeds = self.language_model.get_input_embeddings()(input_ids)
             B, N, C = input_embeds.shape
             input_embeds = input_embeds.reshape(B * N, C)
@@ -350,7 +322,7 @@ class InternVLChatModel(PreTrainedModel):
             input_ids = input_ids.reshape(B * N)
             selected = (input_ids == self.img_context_token_id)
             assert selected.sum() != 0
-            input_embeds[selected] = vit_embeds.reshape(-1, C)
+            input_embeds[selected] = vit_embeds.reshape(-1, C).to(input_embeds.device)
 
             input_embeds = input_embeds.reshape(B, N, C)
         else: