Upload 15 files

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,197 @@
+{
+  "_commit_hash": null,
+  "_name_or_path": "/nfs/dataset-ofs-perception/tracking/marui/Code/llava-qw/outputs/LlavaQw_finetune_model_checkpoints/epoch_1",
+  "architectures": [
+    "LlavaQwModel"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_llavaqw.LlavaQwConfig",
+    "AutoModel": "modeling_llavaqw.LlavaQwModel",
+    "AutoModelForCausalLM": "modeling_llavaqw.LlavaQwModel"
+  },
+  "downsample_ratio": 0.5,
+  "dynamic_image_size": true,
+  "force_image_size": 448,
+  "llm_config": {
+    "_name_or_path": "/nfs/dataset-ofs-perception/tracking/marui/models/Qwen2.5-7B-Instruct",
+    "add_cross_attention": false,
+    "architectures": [
+      "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 151643,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 151645,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 3584,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 18944,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 28,
+    "min_length": 0,
+    "model_type": "qwen2",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 28,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 1000000.0,
+    "sep_token_id": null,
+    "sliding_window": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "transformers_version": "4.45.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 152064
+  },
+  "max_dynamic_patch": 6,
+  "min_dynamic_patch": 1,
+  "model_type": "LlavaQw",
+  "ps_version": "v2",
+  "select_layer": -1,
+  "template": "chatml",
+  "torch_dtype": "bfloat16",
+  "transformers_version": null,
+  "use_backbone_lora": 0,
+  "use_llm_lora": 0,
+  "use_thumbnail": true,
+  "vision_config": {
+    "_name_or_path": "",
+    "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": 0.1,
+    "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": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 448,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "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": "layer_norm",
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "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": false,
+    "qkv_bias": true,
+    "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": "4.45.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_flash_attn": true
+  }
+}

configuration_intern_vit.py

@@ -0,0 +1,119 @@
+# --------------------------------------------------------
+# InternVL
+# Copyright (c) 2023 OpenGVLab
+# Licensed under The MIT License [see LICENSE for details]
+# --------------------------------------------------------
+import os
+from typing import Union
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+
+class InternVisionConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`InternVisionModel`]. It is used to
+    instantiate a vision encoder according to the specified arguments, defining the model architecture.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+    Args:
+        num_channels (`int`, *optional*, defaults to 3):
+            Number of color channels in the input images (e.g., 3 for RGB).
+        patch_size (`int`, *optional*, defaults to 14):
+            The size (resolution) of each patch.
+        image_size (`int`, *optional*, defaults to 224):
+            The size (resolution) of each image.
+        qkv_bias (`bool`, *optional*, defaults to `False`):
+            Whether to add a bias to the queries and values in the self-attention layers.
+        hidden_size (`int`, *optional*, defaults to 3200):
+            Dimensionality of the encoder layers and the pooler layer.
+        num_attention_heads (`int`, *optional*, defaults to 25):
+            Number of attention heads for each attention layer in the Transformer encoder.
+        intermediate_size (`int`, *optional*, defaults to 12800):
+            Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
+        qk_normalization (`bool`, *optional*, defaults to `True`):
+            Whether to normalize the queries and keys in the self-attention layers.
+        num_hidden_layers (`int`, *optional*, defaults to 48):
+            Number of hidden layers in the Transformer encoder.
+        use_flash_attn (`bool`, *optional*, defaults to `True`):
+            Whether to use flash attention mechanism.
+        hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`):
+            The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
+            `"relu"`, `"selu"` and `"gelu_new"` ``"gelu"` are supported.
+        layer_norm_eps (`float`, *optional*, defaults to 1e-6):
+            The epsilon used by the layer normalization layers.
+        dropout (`float`, *optional*, defaults to 0.0):
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
+        drop_path_rate (`float`, *optional*, defaults to 0.0):
+            Dropout rate for stochastic depth.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        initializer_factor (`float`, *optional*, defaults to 0.1):
+            A factor for layer scale.
+    """
+
+    model_type = 'intern_vit_6b'
+
+    def __init__(
+            self,
+            num_channels=3,
+            patch_size=14,
+            image_size=224,
+            qkv_bias=False,
+            hidden_size=3200,
+            num_attention_heads=25,
+            intermediate_size=12800,
+            qk_normalization=True,
+            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,
+            attention_dropout=0.0,
+            initializer_range=0.02,
+            initializer_factor=0.1,
+            **kwargs,
+    ):
+        super().__init__(**kwargs)
+
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.dropout = dropout
+        self.drop_path_rate = drop_path_rate
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.num_channels = num_channels
+        self.patch_size = patch_size
+        self.image_size = image_size
+        self.initializer_range = initializer_range
+        self.initializer_factor = initializer_factor
+        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
+
+    @classmethod
+    def from_pretrained(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs) -> 'PretrainedConfig':
+        config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)
+
+        if 'vision_config' in config_dict:
+            config_dict = config_dict['vision_config']
+
+        if 'model_type' in config_dict and hasattr(cls, 'model_type') and config_dict['model_type'] != cls.model_type:
+            logger.warning(
+                f"You are using a model of type {config_dict['model_type']} to instantiate a model of type "
+                f'{cls.model_type}. This is not supported for all configurations of models and can yield errors.'
+            )
+
+        return cls.from_dict(config_dict, **kwargs)

configuration_llavaqw.py

@@ -0,0 +1,99 @@
+# --------------------------------------------------------
+# Adapted from https://huggingface.co/OpenGVLab/InternVL2-Llama3-76B under MIT License
+#     LICENSE is in incl_licenses directory.
+# --------------------------------------------------------
+
+import copy
+
+from transformers import AutoConfig, Qwen2Config
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+from .configuration_intern_vit import InternVisionConfig
+
+logger = logging.get_logger(__name__)
+
+
+class LlavaQwConfig(PretrainedConfig):
+    model_type = 'LlavaQw'
+    is_composition = True
+
+    def __init__(
+            self,
+            vision_config=None,
+            llm_config=None,
+            use_backbone_lora=0,
+            use_llm_lora=0,
+            select_layer=-1,
+            force_image_size=None,
+            downsample_ratio=0.5,
+            template=None,
+            dynamic_image_size=False,
+            use_thumbnail=False,
+            ps_version='v1',
+            min_dynamic_patch=1,
+            max_dynamic_patch=6,
+            **kwargs
+    ):
+        super().__init__(**kwargs)
+
+        if vision_config is None:
+            vision_config = {'architectures': ['InternVisionModel']}
+            logger.info('vision_config is None. Initializing InternVisionConfig with default values.')
+
+        # Handle llm_config initialization
+        if llm_config is None:
+            llm_config = {'architectures': ['Qwen2ForCausalLM']}
+            logger.info('llm_config is None. Initializing LLM Config with default values.')
+
+        self.vision_config = InternVisionConfig(**vision_config)
+
+        # Check for supported architecture
+        if llm_config.get('architectures', [None])[0] == 'Qwen2ForCausalLM':
+            self.llm_config = Qwen2Config(**llm_config)
+        else:
+            raise ValueError(f"Unsupported architecture: {llm_config.get('architectures', [None])[0]}")
+
+        # Assign configuration values
+        self.use_backbone_lora = use_backbone_lora
+        self.use_llm_lora = use_llm_lora
+        self.select_layer = select_layer
+        self.force_image_size = force_image_size
+        self.downsample_ratio = downsample_ratio
+        self.template = template
+        self.dynamic_image_size = dynamic_image_size
+        self.use_thumbnail = use_thumbnail
+        self.ps_version = ps_version  # Pixel shuffle version
+        self.min_dynamic_patch = min_dynamic_patch
+        self.max_dynamic_patch = max_dynamic_patch
+
+        # Log important parameters
+        logger.info(f'vision_select_layer: {self.select_layer}')
+        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}')
+
+    def to_dict(self):
+        """
+        Serializes this instance to a Python dictionary. Overrides the default `PretrainedConfig.to_dict`.
+
+        Returns:
+            Dict[str, Any]: Dictionary of all the attributes that make up this configuration instance.
+        """
+        output = copy.deepcopy(self.__dict__)
+        output['vision_config'] = self.vision_config.to_dict()
+        output['llm_config'] = self.llm_config.to_dict()
+        output['model_type'] = self.model_type
+        output['use_backbone_lora'] = self.use_backbone_lora
+        output['use_llm_lora'] = self.use_llm_lora
+        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['dynamic_image_size'] = self.dynamic_image_size
+        output['use_thumbnail'] = self.use_thumbnail
+        output['ps_version'] = self.ps_version
+        output['min_dynamic_patch'] = self.min_dynamic_patch
+        output['max_dynamic_patch'] = self.max_dynamic_patch
+
+        return output

conversation.py

@@ -0,0 +1,358 @@
+"""
+Adapted from https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py under the Apache License 2.0.
+     LICENSE is in incl_licenses directory.
+
+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.
+"""
+
+import dataclasses
+from enum import IntEnum, auto
+from typing import Any, Dict, List, Tuple, Union
+
+
+class SeparatorStyle(IntEnum):
+    """Separator styles."""
+
+    ADD_COLON_SINGLE = auto()
+    ADD_COLON_TWO = auto()
+    ADD_COLON_SPACE_SINGLE = auto()
+    NO_COLON_SINGLE = auto()
+    NO_COLON_TWO = auto()
+    ADD_NEW_LINE_SINGLE = auto()
+    LLAMA2 = auto()
+    CHATGLM = auto()
+    CHATML = auto()
+    CHATINTERN = auto()
+    DOLLY = auto()
+    RWKV = auto()
+    PHOENIX = auto()
+    ROBIN = auto()
+    FALCON_CHAT = auto()
+    CHATGLM3 = auto()
+    INTERNVL_ZH = auto()
+    MPT = auto()
+
+
+@dataclasses.dataclass
+class Conversation:
+    """A class that manages prompt templates and keeps all conversation history."""
+
+    # The name of this template
+    name: str
+    # The template of the system prompt
+    system_template: str = '{system_message}'
+    # The system message
+    system_message: str = ''
+    # The names of two roles
+    roles: Tuple[str] = ('USER', 'ASSISTANT')
+    # All messages. Each item is (role, message).
+    messages: List[List[str]] = ()
+    # The number of few shot examples
+    offset: int = 0
+    # The separator style and configurations
+    sep_style: SeparatorStyle = SeparatorStyle.ADD_COLON_SINGLE
+    sep: str = '\n'
+    sep2: str = None
+    # Stop criteria (the default one is EOS token)
+    stop_str: Union[str, List[str]] = None
+    # Stops generation if meeting any token in this list
+    stop_token_ids: List[int] = None
+
+    def get_prompt(self) -> str:
+        """Get the prompt for generation."""
+        system_prompt = self.system_template.format(system_message=self.system_message)
+        if self.sep_style == SeparatorStyle.ADD_COLON_SINGLE:
+            ret = system_prompt + self.sep
+            for role, message in self.messages:
+                if message:
+                    ret += role + ': ' + message + self.sep
+                else:
+                    ret += role + ':'
+            return ret
+        elif self.sep_style == SeparatorStyle.ADD_COLON_TWO:
+            seps = [self.sep, self.sep2]
+            ret = system_prompt + seps[0]
+            for i, (role, message) in enumerate(self.messages):
+                if message:
+                    ret += role + ': ' + message + seps[i % 2]
+                else:
+                    ret += role + ':'
+            return ret
+        elif self.sep_style == SeparatorStyle.ADD_COLON_SPACE_SINGLE:
+            ret = system_prompt + self.sep
+            for role, message in self.messages:
+                if message:
+                    ret += role + ': ' + message + self.sep
+                else:
+                    ret += role + ': '  # must be end with a space
+            return ret
+        elif self.sep_style == SeparatorStyle.ADD_NEW_LINE_SINGLE:
+            ret = '' if system_prompt == '' else system_prompt + self.sep
+            for role, message in self.messages:
+                if message:
+                    ret += role + '\n' + message + self.sep
+                else:
+                    ret += role + '\n'
+            return ret
+        elif self.sep_style == SeparatorStyle.NO_COLON_SINGLE:
+            ret = system_prompt
+            for role, message in self.messages:
+                if message:
+                    ret += role + message + self.sep
+                else:
+                    ret += role
+            return ret
+        elif self.sep_style == SeparatorStyle.NO_COLON_TWO:
+            seps = [self.sep, self.sep2]
+            ret = system_prompt
+            for i, (role, message) in enumerate(self.messages):
+                if message:
+                    ret += role + message + seps[i % 2]
+                else:
+                    ret += role
+            return ret
+        elif self.sep_style == SeparatorStyle.RWKV:
+            ret = system_prompt
+            for i, (role, message) in enumerate(self.messages):
+                if message:
+                    ret += (
+                        role
+                        + ': '
+                        + message.replace('\r\n', '\n').replace('\n\n', '\n')
+                    )
+                    ret += '\n\n'
+                else:
+                    ret += role + ':'
+            return ret
+        elif self.sep_style == SeparatorStyle.LLAMA2:
+            seps = [self.sep, self.sep2]
+            if self.system_message:
+                ret = system_prompt
+            else:
+                ret = '[INST] '
+            for i, (role, message) in enumerate(self.messages):
+                tag = self.roles[i % 2]
+                if message:
+                    if i == 0:
+                        ret += message + ' '
+                    else:
+                        ret += tag + ' ' + message + seps[i % 2]
+                else:
+                    ret += tag
+            return ret
+        elif self.sep_style == SeparatorStyle.CHATGLM:
+            # source: https://huggingface.co/THUDM/chatglm-6b/blob/1d240ba371910e9282298d4592532d7f0f3e9f3e/modeling_chatglm.py#L1302-L1308
+            # source2: https://huggingface.co/THUDM/chatglm2-6b/blob/e186c891cf64310ac66ef10a87e6635fa6c2a579/modeling_chatglm.py#L926
+            round_add_n = 1 if self.name == 'chatglm2' else 0
+            if system_prompt:
+                ret = system_prompt + self.sep
+            else:
+                ret = ''
+
+            for i, (role, message) in enumerate(self.messages):
+                if i % 2 == 0:
+                    ret += f'[Round {i//2 + round_add_n}]{self.sep}'
+
+                if message:
+                    ret += f'{role}：{message}{self.sep}'
+                else:
+                    ret += f'{role}：'
+            return ret
+        elif self.sep_style == SeparatorStyle.CHATML:
+            ret = '' if system_prompt == '' else system_prompt + self.sep + '\n'
+            for role, message in self.messages:
+                if message:
+                    ret += role + '\n' + message + self.sep + '\n'
+                else:
+                    ret += role + '\n'
+            return ret
+        elif self.sep_style == SeparatorStyle.CHATGLM3:
+            ret = ''
+            if self.system_message:
+                ret += system_prompt
+            for role, message in self.messages:
+                if message:
+                    ret += role + '\n' + ' ' + message
+                else:
+                    ret += role
+            return ret
+        elif self.sep_style == SeparatorStyle.CHATINTERN:
+            # source: https://huggingface.co/internlm/internlm-chat-7b-8k/blob/bd546fa984b4b0b86958f56bf37f94aa75ab8831/modeling_internlm.py#L771
+            seps = [self.sep, self.sep2]
+            ret = system_prompt
+            for i, (role, message) in enumerate(self.messages):
+                # if i % 2 == 0:
+                #     ret += "<s>"
+                if message:
+                    ret += role + ':' + message + seps[i % 2] + '\n'
+                else:
+                    ret += role + ':'
+            return ret
+        elif self.sep_style == SeparatorStyle.DOLLY:
+            seps = [self.sep, self.sep2]
+            ret = system_prompt
+            for i, (role, message) in enumerate(self.messages):
+                if message:
+                    ret += role + ':\n' + message + seps[i % 2]
+                    if i % 2 == 1:
+                        ret += '\n\n'
+                else:
+                    ret += role + ':\n'
+            return ret
+        elif self.sep_style == SeparatorStyle.PHOENIX:
+            ret = system_prompt
+            for role, message in self.messages:
+                if message:
+                    ret += role + ': ' + '<s>' + message + '</s>'
+                else:
+                    ret += role + ': ' + '<s>'
+            return ret
+        elif self.sep_style == SeparatorStyle.ROBIN:
+            ret = system_prompt + self.sep
+            for role, message in self.messages:
+                if message:
+                    ret += role + ':\n' + message + self.sep
+                else:
+                    ret += role + ':\n'
+            return ret
+        elif self.sep_style == SeparatorStyle.FALCON_CHAT:
+            ret = ''
+            if self.system_message:
+                ret += system_prompt + self.sep
+            for role, message in self.messages:
+                if message:
+                    ret += role + ': ' + message + self.sep
+                else:
+                    ret += role + ':'
+
+            return ret
+        elif self.sep_style == SeparatorStyle.INTERNVL_ZH:
+            seps = [self.sep, self.sep2]
+            ret = self.system_message + seps[0]
+            for i, (role, message) in enumerate(self.messages):
+                if message:
+                    ret += role + ': ' + message + seps[i % 2]
+                else:
+                    ret += role + ':'
+            return ret
+        elif self.sep_style == SeparatorStyle.MPT:
+            ret = ''
+            for role, message in self.messages:
+                if message:
+                    if type(message) is tuple:
+                        message, _, _ = message
+                    ret += role + message + self.sep
+                else:
+                    ret += role
+            return ret
+        else:
+            raise ValueError(f'Invalid style: {self.sep_style}')
+
+    def set_system_message(self, system_message: str):
+        """Set the system message."""
+        self.system_message = system_message
+
+    def append_message(self, role: str, message: str):
+        """Append a new message."""
+        self.messages.append([role, message])
+
+    def update_last_message(self, message: str):
+        """Update the last output.
+
+        The last message is typically set to be None when constructing the prompt,
+        so we need to update it in-place after getting the response from a model.
+        """
+        self.messages[-1][1] = message
+
+    def to_gradio_chatbot(self):
+        """Convert the conversation to gradio chatbot format."""
+        ret = []
+        for i, (role, msg) in enumerate(self.messages[self.offset :]):
+            if i % 2 == 0:
+                ret.append([msg, None])
+            else:
+                ret[-1][-1] = msg
+        return ret
+
+    def to_openai_api_messages(self):
+        """Convert the conversation to OpenAI chat completion format."""
+        ret = [{'role': 'system', 'content': self.system_message}]
+
+        for i, (_, msg) in enumerate(self.messages[self.offset :]):
+            if i % 2 == 0:
+                ret.append({'role': 'user', 'content': msg})
+            else:
+                if msg is not None:
+                    ret.append({'role': 'assistant', 'content': msg})
+        return ret
+
+    def copy(self):
+        return Conversation(
+            name=self.name,
+            system_template=self.system_template,
+            system_message=self.system_message,
+            roles=self.roles,
+            messages=[[x, y] for x, y in self.messages],
+            offset=self.offset,
+            sep_style=self.sep_style,
+            sep=self.sep,
+            sep2=self.sep2,
+            stop_str=self.stop_str,
+            stop_token_ids=self.stop_token_ids,
+        )
+
+    def dict(self):
+        return {
+            'template_name': self.name,
+            'system_message': self.system_message,
+            'roles': self.roles,
+            'messages': self.messages,
+            'offset': self.offset,
+        }
+
+
+# A global registry for all conversation templates
+conv_templates: Dict[str, Conversation] = {}
+
+
+def register_conv_template(template: Conversation, override: bool = False):
+    """Register a new conversation template."""
+    if not override:
+        assert (
+            template.name not in conv_templates
+        ), f'{template.name} has been registered.'
+
+    conv_templates[template.name] = template
+
+
+def get_conv_template(name: str) -> Conversation:
+    """Get a conversation template."""
+    return conv_templates[name].copy()
+
+
+# Both Hermes-2 and internlm2-chat are chatml-format conversation templates. The difference
+# is that during training, the preprocessing function for the Hermes-2 template doesn't add
+# <s> at the beginning of the tokenized sequence, while the internlm2-chat template does.
+# Therefore, they are completely equivalent during inference.
+
+register_conv_template(
+    Conversation(
+        name='chatml',
+        system_template='<|im_start|>system\n{system_message}',
+        # note: The new system prompt was not used here to avoid changes in benchmark performance.
+        system_message='Answer the questions.',
+        roles=('<|im_start|>user\n', '<|im_start|>assistant\n'),
+        sep_style=SeparatorStyle.MPT,
+        sep='<|im_end|>',
+        stop_token_ids=[
+            2,
+            92543,
+            92542
+        ]
+    )
+)
+
+

flash_attention.py

@@ -0,0 +1,75 @@
+import torch
+import torch.nn as nn
+from einops import rearrange
+
+try:  # v1
+    from flash_attn.flash_attn_interface import \
+        flash_attn_unpadded_qkvpacked_func
+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
+
+
+class FlashAttention(nn.Module):
+    """Implement the scaled dot product attention with softmax.
+    Arguments
+    ---------
+        softmax_scale: The temperature to use for the softmax attention.
+                      (default: 1/sqrt(d_keys) where d_keys is computed at
+                      runtime)
+        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.
+        Arguments
+        ---------
+            qkv: The tensor containing the query, key, and value. (B, S, 3, H, D) if key_padding_mask is None
+                if unpadded: (nnz, 3, h, d)
+            key_padding_mask: a bool tensor of shape (B, S)
+        """
+        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]
+            if key_padding_mask is None:
+                qkv = rearrange(qkv, 'b s ... -> (b s) ...')
+                max_s = seqlen
+                cu_seqlens = torch.arange(0, (batch_size + 1) * seqlen, step=seqlen, dtype=torch.int32,
+                                          device=qkv.device)
+                output = flash_attn_unpadded_qkvpacked_func(
+                    qkv, cu_seqlens, max_s, self.dropout_p if self.training else 0.0,
+                    softmax_scale=self.softmax_scale, causal=causal
+                )
+                output = rearrange(output, '(b s) ... -> b s ...', b=batch_size)
+            else:
+                nheads = qkv.shape[-2]
+                x = rearrange(qkv, 'b s three h d -> b s (three h d)')
+                x_unpad, indices, cu_seqlens, max_s = unpad_input(x, key_padding_mask)
+                x_unpad = rearrange(x_unpad, 'nnz (three h d) -> nnz three h d', three=3, h=nheads)
+                output_unpad = flash_attn_unpadded_qkvpacked_func(
+                    x_unpad, cu_seqlens, max_s, self.dropout_p if self.training else 0.0,
+                    softmax_scale=self.softmax_scale, causal=causal
+                )
+                output = rearrange(pad_input(rearrange(output_unpad, 'nnz h d -> nnz (h d)'),
+                                             indices, batch_size, seqlen),
+                                   'b s (h d) -> b s h d', h=nheads)
+        else:
+            assert max_s is not None
+            output = flash_attn_unpadded_qkvpacked_func(
+                qkv, cu_seqlens, max_s, self.dropout_p if self.training else 0.0,
+                softmax_scale=self.softmax_scale, causal=causal
+            )
+
+        return output, None

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.45.0"
+}

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca76e6a409549c80001b5af64a538530bbb785ce60105468a29f84f6ce2b43c0
+size 1380991480

model.safetensors.index.json

@@ -0,0 +1,690 @@
+{
+  "metadata": {
+    "total_size": 16130253824
+  },
+  "weight_map": {
+    "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.norm.weight": "model-00003-of-00004.safetensors",
+    "mlp1.0.bias": "model-00004-of-00004.safetensors",
+    "mlp1.0.weight": "model-00004-of-00004.safetensors",
+    "mlp1.1.weight": "model-00004-of-00004.safetensors",
+    "mlp1.3.weight": "model-00004-of-00004.safetensors",
+    "vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
+    "vision_model.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors",
+    "vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
+    "vision_model.embeddings.position_embedding": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.norm2.weight": "model-00001-of-00004.safetensors"
+  }
+}

modeling_intern_vit.py

@@ -0,0 +1,363 @@
+# --------------------------------------------------------
+# InternVL
+# Copyright (c) 2023 OpenGVLab
+# Licensed under The MIT License [see LICENSE for details]
+# --------------------------------------------------------
+from typing import Optional, Tuple, Union
+
+import torch
+import torch.nn.functional as F
+import torch.utils.checkpoint
+from einops import rearrange
+from timm.models.layers import DropPath
+from torch import nn
+from transformers.activations import ACT2FN
+from transformers.modeling_outputs import (BaseModelOutput,
+                                           BaseModelOutputWithPooling)
+from transformers.modeling_utils import PreTrainedModel
+from transformers.utils import logging
+
+from .configuration_intern_vit import InternVisionConfig
+
+try:
+    from .flash_attention import FlashAttention
+    has_flash_attn = True
+except:
+    print('FlashAttention is not installed.')
+    has_flash_attn = False
+
+
+logger = logging.get_logger(__name__)
+
+
+class InternRMSNorm(nn.Module):
+    def __init__(self, hidden_size, eps=1e-6):
+        super().__init__()
+        self.weight = nn.Parameter(torch.ones(hidden_size))
+        self.variance_epsilon = eps
+
+    def forward(self, hidden_states):
+        input_dtype = hidden_states.dtype
+        hidden_states = hidden_states.to(torch.float32)
+        variance = hidden_states.pow(2).mean(-1, keepdim=True)
+        hidden_states = hidden_states * torch.rsqrt(variance + self.variance_epsilon)
+        return self.weight * hidden_states.to(input_dtype)
+
+
+try:
+    from apex.normalization import FusedRMSNorm
+
+    InternRMSNorm = FusedRMSNorm  # noqa
+
+    logger.info('Discovered apex.normalization.FusedRMSNorm - will use it instead of InternRMSNorm')
+except ImportError:
+    # using the normal InternRMSNorm
+    pass
+except Exception:
+    logger.warning('discovered apex but it failed to load, falling back to InternRMSNorm')
+    pass
+
+
+NORM2FN = {
+    'rms_norm': InternRMSNorm,
+    'layer_norm': nn.LayerNorm,
+}
+
+
+class InternVisionEmbeddings(nn.Module):
+    def __init__(self, config: InternVisionConfig):
+        super().__init__()
+        self.config = config
+        self.embed_dim = config.hidden_size
+        self.image_size = config.image_size
+        self.patch_size = config.patch_size
+
+        self.class_embedding = nn.Parameter(
+            torch.randn(1, 1, self.embed_dim),
+        )
+
+        self.patch_embedding = nn.Conv2d(
+            in_channels=3, out_channels=self.embed_dim, kernel_size=self.patch_size, stride=self.patch_size
+        )
+
+        self.num_patches = (self.image_size // self.patch_size) ** 2
+        self.num_positions = self.num_patches + 1
+
+        self.position_embedding = nn.Parameter(torch.randn(1, self.num_positions, self.embed_dim))
+
+    def _get_pos_embed(self, pos_embed, H, W):
+        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).\
+            reshape(1, -1, H * W).permute(0, 2, 1).to(target_dtype)
+        return pos_embed
+
+    def forward(self, pixel_values: torch.FloatTensor) -> torch.Tensor:
+        target_dtype = self.patch_embedding.weight.dtype
+        patch_embeds = self.patch_embedding(pixel_values)  # shape = [*, channel, width, height]
+        batch_size, _, height, width = patch_embeds.shape
+        patch_embeds = patch_embeds.flatten(2).transpose(1, 2)
+        class_embeds = self.class_embedding.expand(batch_size, 1, -1).to(target_dtype)
+        embeddings = torch.cat([class_embeds, patch_embeds], dim=1)
+        position_embedding = torch.cat([
+            self.position_embedding[:, :1, :],
+            self._get_pos_embed(self.position_embedding[:, 1:, :], height, width)
+        ], dim=1)
+        embeddings = embeddings + position_embedding.to(target_dtype)
+        return embeddings
+
+
+class InternAttention(nn.Module):
+    """Multi-headed attention from 'Attention Is All You Need' paper"""
+
+    def __init__(self, config: InternVisionConfig):
+        super().__init__()
+        self.config = config
+        self.embed_dim = config.hidden_size
+        self.num_heads = config.num_attention_heads
+        self.use_flash_attn = config.use_flash_attn and has_flash_attn
+        if config.use_flash_attn and not has_flash_attn:
+            print('Warning: Flash Attention is not available, use_flash_attn is set to False.')
+        self.head_dim = self.embed_dim // self.num_heads
+        if self.head_dim * self.num_heads != self.embed_dim:
+            raise ValueError(
+                f'embed_dim must be divisible by num_heads (got `embed_dim`: {self.embed_dim} and `num_heads`:'
+                f' {self.num_heads}).'
+            )
+
+        self.scale = self.head_dim ** -0.5
+        self.qkv = nn.Linear(self.embed_dim, 3 * self.embed_dim, bias=config.qkv_bias)
+        self.attn_drop = nn.Dropout(config.attention_dropout)
+        self.proj_drop = nn.Dropout(config.dropout)
+
+        self.qk_normalization = config.qk_normalization
+
+        if self.qk_normalization:
+            self.q_norm = InternRMSNorm(self.embed_dim, eps=config.layer_norm_eps)
+            self.k_norm = InternRMSNorm(self.embed_dim, eps=config.layer_norm_eps)
+
+        if self.use_flash_attn:
+            self.inner_attn = FlashAttention(attention_dropout=config.attention_dropout)
+        self.proj = nn.Linear(self.embed_dim, self.embed_dim)
+
+    def _naive_attn(self, x):
+        B, N, C = x.shape
+        qkv = self.qkv(x).reshape(B, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
+        q, k, v = qkv.unbind(0)  # make torchscript happy (cannot use tensor as tuple)
+
+        if self.qk_normalization:
+            B_, H_, N_, D_ = q.shape
+            q = self.q_norm(q.transpose(1, 2).flatten(-2, -1)).view(B_, N_, H_, D_).transpose(1, 2)
+            k = self.k_norm(k.transpose(1, 2).flatten(-2, -1)).view(B_, N_, H_, D_).transpose(1, 2)
+
+        attn = ((q * self.scale) @ k.transpose(-2, -1))
+        attn = attn.softmax(dim=-1)
+        attn = self.attn_drop(attn)
+
+        x = (attn @ v).transpose(1, 2).reshape(B, N, C)
+        x = self.proj(x)
+        x = self.proj_drop(x)
+        return x
+
+    def _flash_attn(self, x, key_padding_mask=None, need_weights=False):
+        qkv = self.qkv(x)
+        qkv = rearrange(qkv, 'b s (three h d) -> b s three h d', three=3, h=self.num_heads)
+
+        if self.qk_normalization:
+            q, k, v = qkv.unbind(2)
+            q = self.q_norm(q.flatten(-2, -1)).view(q.shape)
+            k = self.k_norm(k.flatten(-2, -1)).view(k.shape)
+            qkv = torch.stack([q, k, v], dim=2)
+
+        context, _ = self.inner_attn(
+            qkv, key_padding_mask=key_padding_mask, need_weights=need_weights, causal=False
+        )
+        outs = self.proj(rearrange(context, 'b s h d -> b s (h d)'))
+        outs = self.proj_drop(outs)
+        return outs
+
+    def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
+        x = self._naive_attn(hidden_states) if not self.use_flash_attn else self._flash_attn(hidden_states)
+        return x
+
+
+class InternMLP(nn.Module):
+    def __init__(self, config: InternVisionConfig):
+        super().__init__()
+        self.config = config
+        self.act = ACT2FN[config.hidden_act]
+        self.fc1 = nn.Linear(config.hidden_size, config.intermediate_size)
+        self.fc2 = nn.Linear(config.intermediate_size, config.hidden_size)
+
+    def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
+        hidden_states = self.fc1(hidden_states)
+        hidden_states = self.act(hidden_states)
+        hidden_states = self.fc2(hidden_states)
+        return hidden_states
+
+
+class InternVisionEncoderLayer(nn.Module):
+    def __init__(self, config: InternVisionConfig, drop_path_rate: float):
+        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 = 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))
+        self.drop_path1 = DropPath(drop_path_rate) if drop_path_rate > 0. else nn.Identity()
+        self.drop_path2 = DropPath(drop_path_rate) if drop_path_rate > 0. else nn.Identity()
+
+    def forward(
+            self,
+            hidden_states: torch.Tensor,
+    ) -> Tuple[torch.FloatTensor, Optional[torch.FloatTensor], Optional[Tuple[torch.FloatTensor]]]:
+        """
+        Args:
+            hidden_states (`Tuple[torch.FloatTensor, Optional[torch.FloatTensor]]`): input to the layer of shape `(batch, seq_len, embed_dim)`
+        """
+        hidden_states = hidden_states + self.drop_path1(self.attn(self.norm1(hidden_states)) * self.ls1)
+
+        hidden_states = hidden_states + self.drop_path2(self.mlp(self.norm2(hidden_states)) * self.ls2)
+
+        return hidden_states
+
+
+class InternVisionEncoder(nn.Module):
+    """
+    Transformer encoder consisting of `config.num_hidden_layers` self attention layers. Each layer is a
+    [`InternEncoderLayer`].
+
+    Args:
+        config (`InternConfig`):
+            The corresponding vision configuration for the `InternEncoder`.
+    """
+
+    def __init__(self, config: InternVisionConfig):
+        super().__init__()
+        self.config = config
+        # stochastic depth decay rule
+        dpr = [x.item() for x in torch.linspace(0, config.drop_path_rate, config.num_hidden_layers)]
+        self.layers = nn.ModuleList([
+            InternVisionEncoderLayer(config, dpr[idx]) for idx in range(config.num_hidden_layers)])
+        self.gradient_checkpointing = True
+
+    def forward(
+            self,
+            inputs_embeds,
+            output_hidden_states: Optional[bool] = None,
+            return_dict: Optional[bool] = None,
+    ) -> Union[Tuple, BaseModelOutput]:
+        r"""
+        Args:
+            inputs_embeds (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`):
+                Embedded representation of the inputs. Should be float, not int tokens.
+            output_hidden_states (`bool`, *optional*):
+                Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors
+                for more detail.
+            return_dict (`bool`, *optional*):
+                Whether or not to return a [`~utils.ModelOutput`] instead of a plain tuple.
+        """
+        output_hidden_states = (
+            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
+        )
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+
+        encoder_states = () if output_hidden_states else None
+        hidden_states = inputs_embeds
+
+        for idx, encoder_layer in enumerate(self.layers):
+            if output_hidden_states:
+                encoder_states = encoder_states + (hidden_states,)
+            if self.gradient_checkpointing and self.training:
+                layer_outputs = torch.utils.checkpoint.checkpoint(
+                    encoder_layer,
+                    hidden_states)
+            else:
+                layer_outputs = encoder_layer(
+                    hidden_states,
+                )
+            hidden_states = layer_outputs
+
+        if output_hidden_states:
+            encoder_states = encoder_states + (hidden_states,)
+
+        if not return_dict:
+            return tuple(v for v in [hidden_states, encoder_states] if v is not None)
+        return BaseModelOutput(
+            last_hidden_state=hidden_states, hidden_states=encoder_states
+        )
+
+
+class InternVisionModel(PreTrainedModel):
+    main_input_name = 'pixel_values'
+    config_class = InternVisionConfig
+    _no_split_modules = ['InternVisionEncoderLayer']
+
+    def __init__(self, config: InternVisionConfig):
+        super().__init__(config)
+        self.config = config
+
+        self.embeddings = InternVisionEmbeddings(config)
+        self.encoder = InternVisionEncoder(config)
+
+    def resize_pos_embeddings(self, old_size, new_size, patch_size):
+        pos_emb = self.embeddings.position_embedding
+        _, num_positions, embed_dim = pos_emb.shape
+        cls_emb = pos_emb[:, :1, :]
+        pos_emb = pos_emb[:, 1:, :].reshape(1, old_size // patch_size, old_size // patch_size, -1).permute(0, 3, 1, 2)
+        pos_emb = F.interpolate(pos_emb.float(), size=new_size // patch_size, mode='bicubic', align_corners=False)
+        pos_emb = pos_emb.to(cls_emb.dtype).reshape(1, embed_dim, -1).permute(0, 2, 1)
+        pos_emb = torch.cat([cls_emb, pos_emb], dim=1)
+        self.embeddings.position_embedding = nn.Parameter(pos_emb)
+        self.embeddings.image_size = new_size
+        logger.info('Resized position embeddings from {} to {}'.format(old_size, new_size))
+
+    def get_input_embeddings(self):
+        return self.embeddings
+
+    def forward(
+            self,
+            pixel_values: Optional[torch.FloatTensor] = None,
+            output_hidden_states: Optional[bool] = None,
+            return_dict: Optional[bool] = None,
+            pixel_embeds: Optional[torch.FloatTensor] = None,
+    ) -> Union[Tuple, BaseModelOutputWithPooling]:
+        output_hidden_states = (
+            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
+        )
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+
+        if pixel_values is None and pixel_embeds is None:
+            raise ValueError('You have to specify pixel_values or pixel_embeds')
+
+        if pixel_embeds is not None:
+            hidden_states = pixel_embeds
+        else:
+            if len(pixel_values.shape) == 4:
+                hidden_states = self.embeddings(pixel_values)
+            else:
+                raise ValueError(f'wrong pixel_values size: {pixel_values.shape}')
+        encoder_outputs = self.encoder(
+            inputs_embeds=hidden_states,
+            output_hidden_states=output_hidden_states,
+            return_dict=return_dict,
+        )
+        last_hidden_state = encoder_outputs.last_hidden_state
+        pooled_output = last_hidden_state[:, 0, :]
+
+        if not return_dict:
+            return (last_hidden_state, pooled_output) + encoder_outputs[1:]
+
+        return BaseModelOutputWithPooling(
+            last_hidden_state=last_hidden_state,
+            pooler_output=pooled_output,
+            hidden_states=encoder_outputs.hidden_states,
+            attentions=encoder_outputs.attentions,
+        )

modeling_llavaqw.py

@@ -0,0 +1,573 @@
+import warnings
+from typing import Any, List, Optional, Tuple, Union
+import torch.utils.checkpoint
+import transformers
+from torch import nn
+from torch.nn import CrossEntropyLoss
+from transformers import GenerationConfig
+from transformers import Qwen2ForCausalLM
+from transformers.modeling_outputs import CausalLMOutputWithPast
+from transformers.modeling_utils import PreTrainedModel
+from transformers.utils import ModelOutput, logging
+import torch.nn.functional as F
+
+from .configuration_llavaqw import LlavaQwConfig
+from .conversation import get_conv_template
+from .modeling_intern_vit import InternVisionModel, has_flash_attn
+
+logger = logging.get_logger(__name__)
+
+
+def version_cmp(v1, v2, op='eq'):
+    import operator
+
+    from packaging import version
+    op_func = getattr(operator, op)
+    return op_func(version.parse(v1), version.parse(v2))
+
+
+class LlavaQwModel(PreTrainedModel):
+    config_class = LlavaQwConfig
+    main_input_name = 'pixel_values'
+    _supports_flash_attn_2 = True
+    _no_split_modules = ['InternVisionModel', 'Qwen2DecoderLayer']
+
+    def __init__(self, config: LlavaQwConfig, vision_model=None, language_model=None, use_flash_attn=True):
+        super().__init__(config)
+
+        assert version_cmp(transformers.__version__, '4.44.2', '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
+        self.select_layer = config.select_layer
+        self.llm_arch_name = config.llm_config.architectures[0]
+        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.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'
+
+        logger.info(f'num_image_token: {self.num_image_token}')
+        logger.info(f'ps_version: {self.ps_version}')
+        if vision_model is not None:
+            self.vision_model = vision_model
+        else:
+            self.vision_model = InternVisionModel(config.vision_config)
+        if language_model is not None:
+            self.language_model = language_model
+        else:
+            if 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.')
+
+        vit_hidden_size = config.vision_config.hidden_size
+        llm_intermediate_size = config.llm_config.intermediate_size
+        llm_hidden_size = config.llm_config.hidden_size
+
+        self.mlp1 = nn.Sequential(
+            nn.LayerNorm(vit_hidden_size * int(1 / self.downsample_ratio) ** 2),
+            nn.Linear(vit_hidden_size * int(1 / self.downsample_ratio) ** 2, llm_intermediate_size, bias=False),
+            nn.GELU(),
+            nn.Linear(llm_intermediate_size, llm_hidden_size, bias=False)
+        )
+
+        self.img_context_token_id = 151654
+        self.conv_template = get_conv_template(self.template)
+        self.system_message = self.conv_template.system_message
+
+    def forward(
+            self,
+            pixel_values: torch.FloatTensor,
+            input_ids: torch.LongTensor = None,
+            attention_mask: Optional[torch.Tensor] = None,
+            position_ids: Optional[torch.LongTensor] = None,
+            image_flags: Optional[torch.LongTensor] = None,
+            past_key_values: Optional[List[torch.FloatTensor]] = None,
+            labels: Optional[torch.LongTensor] = None,
+            use_cache: Optional[bool] = None,
+            output_attentions: Optional[bool] = None,
+            output_hidden_states: Optional[bool] = None,
+            return_dict: Optional[bool] = None,
+    ) -> Union[Tuple, CausalLMOutputWithPast]:
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+
+        input_embeds = self.language_model.get_input_embeddings()(input_ids)
+
+        vit_embeds = self.extract_feature(pixel_values)
+        vit_batch_size = pixel_values.shape[0]
+
+        B, N, C = input_embeds.shape
+        input_embeds = input_embeds.reshape(B * N, C)
+
+        input_ids = input_ids.reshape(B * N)
+        selected = (input_ids == self.img_context_token_id)
+        try:
+            input_embeds[selected] = input_embeds[selected] * 0.0 + vit_embeds.reshape(-1, C)
+        except Exception as e:
+            vit_embeds = vit_embeds.reshape(-1, C)
+            print(f'warning: {e}, input_embeds[selected].shape={input_embeds[selected].shape}, '
+                  f'vit_embeds.shape={vit_embeds.shape}')
+            n_token = selected.sum()
+            input_embeds[selected] = input_embeds[selected] * 0.0 + vit_embeds[:n_token]
+
+        input_embeds = input_embeds.reshape(B, N, C)
+
+        outputs = self.language_model(
+            inputs_embeds=input_embeds,
+            attention_mask=attention_mask,
+            position_ids=position_ids,
+            past_key_values=past_key_values,
+            use_cache=use_cache,
+            output_attentions=output_attentions,
+            output_hidden_states=output_hidden_states,
+            return_dict=return_dict,
+        )
+        logits = outputs.logits
+
+        loss = None
+        if labels is not None:
+            # Shift so that tokens < n predict n
+            shift_logits = logits[..., :-1, :].contiguous()
+            shift_labels = labels[..., 1:].contiguous()
+            # Flatten the tokens
+            loss_fct = CrossEntropyLoss()
+            shift_logits = shift_logits.view(-1, self.language_model.config.vocab_size)
+            shift_labels = shift_labels.view(-1)
+
+            # Enable model parallelism
+            shift_labels = shift_labels.to(shift_logits.device)
+            loss = loss_fct(shift_logits, shift_labels)
+
+        if not return_dict:
+            output = (logits,) + outputs[1:]
+            return (loss,) + output if loss is not None else output
+
+        return CausalLMOutputWithPast(
+            loss=loss,
+            logits=logits,
+            past_key_values=outputs.past_key_values,
+            hidden_states=outputs.hidden_states,
+            attentions=outputs.attentions,
+        )
+
+    def pixel_shuffle(self, x, scale_factor=0.5):
+        n, w, h, c = x.size()
+        # N, W, H, C --> N, W, H * scale, C // scale
+        x = x.view(n, w, int(h * scale_factor), int(c / scale_factor))
+        # N, W, H * scale, C // scale --> N, H * scale, W, C // scale
+        x = x.permute(0, 2, 1, 3).contiguous()
+        # N, H * scale, W, C // scale --> N, H * scale, W * scale, C // (scale ** 2)
+        x = x.view(n, int(h * scale_factor), int(w * scale_factor),
+                   int(c / (scale_factor * scale_factor)))
+        if self.ps_version == 'v1':
+            warnings.warn("In ps_version 'v1', the height and width have not been swapped back, "
+                          'which results in a transposed image.')
+        else:
+            x = x.permute(0, 2, 1, 3).contiguous()
+        return x
+
+    def extract_feature(self, pixel_values):
+        if self.select_layer == -1:
+            vit_embeds = self.vision_model(
+                pixel_values=pixel_values,
+                output_hidden_states=False,
+                return_dict=True).last_hidden_state
+        else:
+            vit_embeds = self.vision_model(
+                pixel_values=pixel_values,
+                output_hidden_states=True,
+                return_dict=True).hidden_states[self.select_layer]
+        vit_embeds = vit_embeds[:, 1:, :]
+
+        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])
+        vit_embeds = self.mlp1(vit_embeds)
+        return vit_embeds
+
+    def chat(self, tokenizer, pixel_values, question, generation_config, history=None, return_history=False,
+             num_patches_list=None, IMG_START_TOKEN='<|vision_start|>', IMG_END_TOKEN='<|vision_end|>',
+             IMG_CONTEXT_TOKEN='<|vision_pad|>', verbose=False, visual_features=None):
+
+        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)
+        template.system_message = self.system_message
+        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()
+        # print('query:', query)
+
+        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:
+            tile_pos_identifiers = [f"<tile_{i}>" for i in range(1, num_patches)] + ["<tile_global_thumbnail>"]
+            image_tokens = ''
+            for tile_pos_identifier in tile_pos_identifiers:
+                image_tokens += tile_pos_identifier + IMG_CONTEXT_TOKEN * self.num_image_token
+            image_tokens = IMG_START_TOKEN + image_tokens + 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()
+        generation_config['eos_token_id'] = eos_token_id
+        generation_output = self.generate(
+            pixel_values=pixel_values,
+            visual_features=visual_features,
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            **generation_config
+        )
+        response = tokenizer.batch_decode(generation_output, skip_special_tokens=True)[0]
+        response = response.split(template.sep)[0].strip()
+        history.append((question, response))
+        if return_history:
+            return response, history
+        else:
+            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
+
+    def chat_without_sys_prompt(self, tokenizer, pixel_values, question, generation_config, history=None,
+                                return_history=False,
+                                num_patches_list=None, IMG_START_TOKEN='<|vision_start|>',
+                                IMG_END_TOKEN='<|vision_end|>',
+                                IMG_CONTEXT_TOKEN='<|vision_pad|>', verbose=False, visual_features=None):
+
+        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)
+        system_prompt = "<|im_start|>system\nYou are a helpful assistant.<|im_end|>"  # override dummy system prompt
+        template.system_message = system_prompt
+        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}')
+
+        query = query[len(system_prompt):]
+
+        for num_patches in num_patches_list:
+            tile_pos_identifiers = [f"<tile_{i}>" for i in range(1, num_patches)] + ["<tile_global_thumbnail>"]
+            image_tokens = ''
+            for tile_pos_identifier in tile_pos_identifiers:
+                image_tokens += tile_pos_identifier + IMG_CONTEXT_TOKEN * self.num_image_token
+            image_tokens = IMG_START_TOKEN + image_tokens + 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()
+        generation_config['eos_token_id'] = eos_token_id
+        generation_output = self.generate(
+            pixel_values=pixel_values,
+            visual_features=visual_features,
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            **generation_config
+        )
+        response = tokenizer.batch_decode(generation_output, skip_special_tokens=True)[0]
+        response = response.split(template.sep)[0].strip()
+        history.append((question, response))
+        if return_history:
+            return response, history
+        else:
+            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
+
+    def chat_without_chat_prompt(self, tokenizer, pixel_values, question, generation_config,
+                                 num_patches_list=None, IMG_START_TOKEN='<|vision_start|>',
+                                 IMG_END_TOKEN='<|vision_end|>',
+                                 IMG_CONTEXT_TOKEN='<|vision_pad|>', verbose=False, visual_features=None):
+
+        if 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)
+        template.system_message = self.system_message
+        eos_token_id = tokenizer.convert_tokens_to_ids(template.sep)
+
+        if verbose and pixel_values is not None:
+            image_bs = pixel_values.shape[0]
+            print(f'dynamic ViT batch size: {image_bs}')
+
+        query = question
+
+        for num_patches in num_patches_list:
+            tile_pos_identifiers = [f"<tile_{i}>" for i in range(1, num_patches)] + ["<tile_global_thumbnail>"]
+            image_tokens = ''
+            for tile_pos_identifier in tile_pos_identifiers:
+                image_tokens += tile_pos_identifier + IMG_CONTEXT_TOKEN * self.num_image_token
+            image_tokens = IMG_START_TOKEN + image_tokens + 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()
+        generation_config['eos_token_id'] = eos_token_id
+        generation_output = self.generate(
+            pixel_values=pixel_values,
+            visual_features=visual_features,
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            **generation_config
+        )
+        response = tokenizer.batch_decode(generation_output, skip_special_tokens=True)[0]
+        response = response.split(template.sep)[0].strip()
+
+        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
+
+    @torch.no_grad()
+    def generate(
+            self,
+            pixel_values: Optional[torch.FloatTensor] = None,
+            input_ids: Optional[torch.FloatTensor] = None,
+            attention_mask: Optional[torch.LongTensor] = None,
+            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:
+
+        # assert self.img_context_token_id is not None
+        if pixel_values is not None:
+            if visual_features is not None:
+                vit_embeds = visual_features.cuda()
+                vit_embeds = self.mlp1(vit_embeds)
+            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)
+
+            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).to(input_embeds.device)
+
+            input_embeds = input_embeds.reshape(B, N, C)
+        else:
+            input_embeds = self.language_model.get_input_embeddings()(input_ids)
+
+        outputs = self.language_model.generate(
+            inputs_embeds=input_embeds,
+            attention_mask=attention_mask,
+            generation_config=generation_config,
+            output_hidden_states=output_hidden_states,
+            return_dict=return_dict,
+            use_cache=True,
+            **generate_kwargs,
+        )
+
+        return outputs
+
+    def chat_batch(
+            self,
+            tokenizer,
+            pixel_values_list,
+            questions,
+            generation_config,
+            histories=None,
+            return_histories=False,
+            num_patches_lists=None,
+            IMG_START_TOKEN='<|vision_start|>',
+            IMG_END_TOKEN='<|vision_end|>',
+            IMG_CONTEXT_TOKEN='<|vision_pad|>',
+            verbose=False,
+            visual_features_list=None
+    ):
+
+        if histories is None:
+            histories = [[] for _ in questions]
+
+        img_context_token_id = tokenizer.convert_tokens_to_ids(IMG_CONTEXT_TOKEN)
+        self.img_context_token_id = img_context_token_id
+        # Get eos_token_id from the template
+        template = get_conv_template(self.template)
+        template.system_message = self.system_message
+        eos_token_id = tokenizer.convert_tokens_to_ids(template.sep)
+        generation_config['eos_token_id'] = eos_token_id
+
+        queries = []
+        input_ids_list = []
+        attention_mask_list = []
+
+        for idx in range(len(questions)):
+            question = questions[idx]
+            history = histories[idx]
+            pixel_values = pixel_values_list[idx] if pixel_values_list[idx] is not None else None
+            num_patches_list = [pixel_values.shape[0]] if pixel_values is not None else []
+
+            if not history and pixel_values is not None and '<image>' not in question:
+                question = '<image>\n' + question
+
+            template_i = get_conv_template(self.template)
+            template_i.system_message = self.system_message
+            for (old_question, old_answer) in history:
+                template_i.append_message(template_i.roles[0], old_question)
+                template_i.append_message(template_i.roles[1], old_answer)
+            template_i.append_message(template_i.roles[0], question)
+            template_i.append_message(template_i.roles[1], None)
+            query = template_i.get_prompt()
+            # Handle image tokens
+            if pixel_values is not None:
+                for num_patches in num_patches_list:
+                    tile_pos_identifiers = [f"<tile_{i}>" for i in range(1, num_patches)] + ["<tile_global_thumbnail>"]
+                    image_tokens = ''
+                    for tile_pos_identifier in tile_pos_identifiers:
+                        image_tokens += tile_pos_identifier + IMG_CONTEXT_TOKEN * self.num_image_token
+                    image_tokens = IMG_START_TOKEN + image_tokens + IMG_END_TOKEN
+                    query = query.replace('<image>', image_tokens, 1)
+
+            model_inputs = tokenizer(
+                query,
+                return_tensors='pt',
+                padding=True,
+                truncation=True
+            )
+            input_ids = model_inputs['input_ids'].cuda()
+            attention_mask = model_inputs['attention_mask'].cuda()
+            input_ids_list.append(input_ids)
+            attention_mask_list.append(attention_mask)
+
+        # Call the generate function
+        generation_output = self.generate_batch(
+            pixel_values_list=pixel_values_list,
+            input_ids_list=input_ids_list,
+            attention_mask_list=attention_mask_list,
+            **generation_config
+        )
+        responses = tokenizer.batch_decode(generation_output, skip_special_tokens=True)
+
+        outputs = []
+        for idx, response in enumerate(responses):
+            response = response.split(template.sep)[0].strip()
+            histories[idx].append((questions[idx], response))
+            outputs.append(response)
+
+        if return_histories:
+            return outputs, histories
+        else:
+            if verbose:
+                for idx, query in enumerate(queries):
+                    query_to_print = query.replace(IMG_CONTEXT_TOKEN, '')
+                    query_to_print = query_to_print.replace(f'{IMG_START_TOKEN}{IMG_END_TOKEN}', '<image>')
+                    print(query_to_print, outputs[idx])
+            return outputs
+
+    @torch.no_grad()
+    def generate_batch(
+            self,
+            pixel_values_list: Optional[List[torch.FloatTensor]] = None,
+            input_ids_list: Optional[List[torch.FloatTensor]] = None,
+            attention_mask_list: Optional[List[torch.LongTensor]] = None,
+            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:
+        input_embeds_list = []
+        attention_mask_padded_list = []
+
+        max_seq_length = max(input_ids.shape[1] for input_ids in input_ids_list)
+
+        for pixel_values, input_ids, attention_mask in zip(pixel_values_list, input_ids_list, attention_mask_list):
+            if pixel_values is not None:
+                if visual_features is not None:
+                    vit_embeds = visual_features.cuda()
+                    vit_embeds = self.mlp1(vit_embeds)
+                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)
+
+                input_ids = input_ids.reshape(B * N)
+                selected = (input_ids == self.img_context_token_id)
+                assert selected.sum() != 0, "No valid image context token IDs found."
+                input_embeds[selected] = vit_embeds.reshape(-1, C).to(input_embeds.device)
+
+                input_embeds = input_embeds.reshape(B, N, C)
+            else:
+                input_embeds = self.language_model.get_input_embeddings()(input_ids)
+
+            seq_length = input_embeds.shape[1]
+            if seq_length < max_seq_length:
+                pad_size = max_seq_length - seq_length
+                input_embeds = F.pad(input_embeds, (0, 0, 0, pad_size))
+                attention_mask = F.pad(attention_mask, (0, pad_size))
+
+            input_embeds_list.append(input_embeds)
+            attention_mask_padded_list.append(attention_mask)
+
+        input_embeds = torch.cat(input_embeds_list, dim=0)
+        attention_mask = torch.cat(attention_mask_padded_list, dim=0)
+
+        outputs = self.language_model.generate(
+            inputs_embeds=input_embeds,
+            attention_mask=attention_mask,
+            generation_config=generation_config,
+            output_hidden_states=output_hidden_states,
+            return_dict=return_dict,
+            use_cache=True,
+            **generate_kwargs,
+        )
+
+        return outputs

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}