# Qwen2-VL ## Overview The [Qwen2-VL](https://huggingface.co/papers/2409.12191) ([blog post](https://qwenlm.github.io/blog/qwen2-vl/)) model is a major update to [Qwen-VL](https://huggingface.co/papers/2308.12966) from the Qwen team at Alibaba Research. The abstract from the blog is the following: *This blog introduces Qwen2-VL, an advanced version of the Qwen-VL model that has undergone significant enhancements over the past year. Key improvements include enhanced image comprehension, advanced video understanding, integrated visual agent functionality, and expanded multilingual support. The model architecture has been optimized for handling arbitrary image resolutions through Naive Dynamic Resolution support and utilizes Multimodal Rotary Position Embedding (M-ROPE) to effectively process both 1D textual and multi-dimensional visual data. This updated model demonstrates competitive performance against leading AI systems like GPT-4o and Claude 3.5 Sonnet in vision-related tasks and ranks highly among open-source models in text capabilities. These advancements make Qwen2-VL a versatile tool for various applications requiring robust multimodal processing and reasoning abilities.* Qwen2-VL architecture. Taken from the blog post. This model was contributed by [simonJJJ](https://huggingface.co/simonJJJ). ## Usage example ### Single Media inference The model can accept both images and videos as input. Here's an example code for inference. ```python import torch from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor # Load the model in half-precision on the available device(s) model = Qwen2VLForConditionalGeneration.from_pretrained("Qwen/Qwen2-VL-7B-Instruct", device_map="auto") processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct") conversation = [ { "role":"user", "content":[ { "type":"image", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg" }, { "type":"text", "text":"Describe this image." } ] } ] inputs = processor.apply_chat_template( conversation, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt" ).to(model.device) # Inference: Generation of the output output_ids = model.generate(**inputs, max_new_tokens=128) generated_ids = [output_ids[len(input_ids):] for input_ids, output_ids in zip(inputs.input_ids, output_ids)] output_text = processor.batch_decode(generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True) print(output_text) # Video conversation = [ { "role": "user", "content": [ {"type": "video", "path": "/path/to/video.mp4"}, {"type": "text", "text": "What happened in the video?"}, ], } ] inputs = processor.apply_chat_template( conversation, fps=1, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt" ).to(model.device) # Inference: Generation of the output output_ids = model.generate(**inputs, max_new_tokens=128) generated_ids = [output_ids[len(input_ids):] for input_ids, output_ids in zip(inputs.input_ids, output_ids)] output_text = processor.batch_decode(generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True) print(output_text) ``` ### Batch Mixed Media Inference The model can batch inputs composed of mixed samples of various types such as images, videos, and text. Here is an example. ```python # Conversation for the first image conversation1 = [ { "role": "user", "content": [ {"type": "image", "path": "/path/to/image1.jpg"}, {"type": "text", "text": "Describe this image."} ] } ] # Conversation with two images conversation2 = [ { "role": "user", "content": [ {"type": "image", "path": "/path/to/image2.jpg"}, {"type": "image", "path": "/path/to/image3.jpg"}, {"type": "text", "text": "What is written in the pictures?"} ] } ] # Conversation with pure text conversation3 = [ { "role": "user", "content": "who are you?" } ] # Conversation with mixed midia conversation4 = [ { "role": "user", "content": [ {"type": "image", "path": "/path/to/image3.jpg"}, {"type": "image", "path": "/path/to/image4.jpg"}, {"type": "video", "path": "/path/to/video.jpg"}, {"type": "text", "text": "What are the common elements in these medias?"}, ], } ] conversations = [conversation1, conversation2, conversation3, conversation4] # Preparation for batch inference ipnuts = processor.apply_chat_template( conversations, fps=1, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt" ).to(model.device) # Batch Inference output_ids = model.generate(**inputs, max_new_tokens=128) generated_ids = [output_ids[len(input_ids):] for input_ids, output_ids in zip(inputs.input_ids, output_ids)] output_text = processor.batch_decode(generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True) print(output_text) ``` ### Usage Tips #### Image Resolution trade-off The model supports a wide range of resolution inputs. By default, it uses the native resolution for input, but higher resolutions can enhance performance at the cost of more computation. Users can set the minimum and maximum number of pixels to achieve an optimal configuration for their needs. ```python min_pixels = 224*224 max_pixels = 2048*2048 processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels) ``` In case of limited GPU RAM, one can reduce the resolution as follows: ```python min_pixels = 256*28*28 max_pixels = 1024*28*28 processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels) ``` This ensures each image gets encoded using a number between 256-1024 tokens. The 28 comes from the fact that the model uses a patch size of 14 and a temporal patch size of 2 (14 x 2 = 28). #### Multiple Image Inputs By default, images and video content are directly included in the conversation. When handling multiple images, it's helpful to add labels to the images and videos for better reference. Users can control this behavior with the following settings: ```python conversation = [ { "role": "user", "content": [ {"type": "image"}, {"type": "text", "text": "Hello, how are you?"} ] }, { "role": "assistant", "content": "I'm doing well, thank you for asking. How can I assist you today?" }, { "role": "user", "content": [ {"type": "text", "text": "Can you describe these images and video?"}, {"type": "image"}, {"type": "image"}, {"type": "video"}, {"type": "text", "text": "These are from my vacation."} ] }, { "role": "assistant", "content": "I'd be happy to describe the images and video for you. Could you please provide more context about your vacation?" }, { "role": "user", "content": "It was a trip to the mountains. Can you see the details in the images and video?" } ] # default: prompt_without_id = processor.apply_chat_template(conversation, add_generation_prompt=True) # Excepted output: 'system\nYou are a helpful assistant.\nuser\nHello, how are you?\nassistant\nI'm doing well, thank you for asking. How can I assist you today?\nuser\nCan you describe these images and video?These are from my vacation.\nassistant\nI'd be happy to describe the images and video for you. Could you please provide more context about your vacation?\nuser\nIt was a trip to the mountains. Can you see the details in the images and video?\nassistant\n' # add ids prompt_with_id = processor.apply_chat_template(conversation, add_generation_prompt=True, add_vision_id=True) # Excepted output: 'system\nYou are a helpful assistant.\nuser\nPicture 1: Hello, how are you?\nassistant\nI'm doing well, thank you for asking. How can I assist you today?\nuser\nCan you describe these images and video?Picture 2: Picture 3: Video 1: These are from my vacation.\nassistant\nI'd be happy to describe the images and video for you. Could you please provide more context about your vacation?\nuser\nIt was a trip to the mountains. Can you see the details in the images and video?\nassistant\n' ``` #### Flash-Attention 2 to speed up generation First, make sure to install the latest version of Flash Attention 2: ```bash pip install -U flash-attn --no-build-isolation ``` Also, you should have a hardware that is compatible with Flash-Attention 2. Read more about it in the official documentation of the [flash attention repository](https://github.com/Dao-AILab/flash-attention). FlashAttention-2 can only be used when a model is loaded in `torch.float16` or `torch.bfloat16`. To load and run a model using Flash Attention-2, simply add `attn_implementation="flash_attention_2"` when loading the model as follows: ```python from transformers import Qwen2VLForConditionalGeneration model = Qwen2VLForConditionalGeneration.from_pretrained( "Qwen/Qwen2-VL-7B-Instruct", dtype=torch.bfloat16, attn_implementation="flash_attention_2", ) ``` ## Qwen2VLConfig[[transformers.Qwen2VLConfig]] #### transformers.Qwen2VLConfig[[transformers.Qwen2VLConfig]] [Source](https://github.com/huggingface/transformers/blob/v4.57.3/src/transformers/models/qwen2_vl/configuration_qwen2_vl.py#L253) This is the configuration class to store the configuration of a [Qwen2VLModel](/docs/transformers/v4.57.3/en/model_doc/qwen2_vl#transformers.Qwen2VLModel). It is used to instantiate a Qwen2-VL model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of Qwen2-VL-7B-Instruct [Qwen/Qwen2-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct). Configuration objects inherit from [PretrainedConfig](/docs/transformers/v4.57.3/en/main_classes/configuration#transformers.PretrainedConfig) and can be used to control the model outputs. Read the documentation from [PretrainedConfig](/docs/transformers/v4.57.3/en/main_classes/configuration#transformers.PretrainedConfig) for more information. ```python >>> from transformers import Qwen2VLForConditionalGeneration, Qwen2VLConfig >>> # Initializing a Qwen2VL style configuration >>> configuration = Qwen2VLConfig() >>> # Initializing a model from the Qwen2-VL-7B style configuration >>> model = Qwen2VLForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` **Parameters:** text_config (`Union[PreTrainedConfig, dict]`, *optional*, defaults to `Qwen2VLTextConfig`) : The config object or dictionary of the text backbone. vision_config (`Union[PreTrainedConfig, dict]`, *optional*, defaults to `Qwen2VLVisionConfig`) : The config object or dictionary of the vision backbone. image_token_id (`int`, *optional*, defaults to 151655) : The image token index to encode the image prompt. video_token_id (`int`, *optional*, defaults to 151656) : The video token index to encode the image prompt. vision_start_token_id (`int`, *optional*, defaults to 151652) : The token index to denote start of vision input. vision_end_token_id (`int`, *optional*, defaults to 151653) : The token index to denote end of vision input. ## Qwen2VLTextConfig[[transformers.Qwen2VLTextConfig]] #### transformers.Qwen2VLTextConfig[[transformers.Qwen2VLTextConfig]] [Source](https://github.com/huggingface/transformers/blob/v4.57.3/src/transformers/models/qwen2_vl/configuration_qwen2_vl.py#L59) This is the configuration class to store the configuration of a [Qwen2VLTextModel](/docs/transformers/v4.57.3/en/model_doc/qwen2_vl#transformers.Qwen2VLTextModel). It is used to instantiate a Qwen2-VL model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of Qwen2-VL-7B-Instruct [Qwen/Qwen2-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct). Configuration objects inherit from [PretrainedConfig](/docs/transformers/v4.57.3/en/main_classes/configuration#transformers.PretrainedConfig) and can be used to control the model outputs. Read the documentation from [PretrainedConfig](/docs/transformers/v4.57.3/en/main_classes/configuration#transformers.PretrainedConfig) for more information. ```python >>> from transformers import Qwen2VLTextModel, Qwen2VLConfig >>> # Initializing a Qwen2VL style configuration >>> configuration = Qwen2VLConfig() >>> # Initializing a model from the Qwen2-VL-7B style configuration >>> model = Qwen2VLTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` **Parameters:** vocab_size (`int`, *optional*, defaults to 152064) : Vocabulary size of the Qwen2VL model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [Qwen2VLModel](/docs/transformers/v4.57.3/en/model_doc/qwen2_vl#transformers.Qwen2VLModel) hidden_size (`int`, *optional*, defaults to 8192) : Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 29568) : Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 80) : Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 64) : Number of attention heads for each attention layer in the Transformer encoder. num_key_value_heads (`int`, *optional*, defaults to 8) : This is the number of key_value heads that should be used to implement Grouped Query Attention. If `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if `num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed by meanpooling all the original heads within that group. For more details, check out [this paper](https://huggingface.co/papers/2305.13245). If it is not specified, will default to `32`. hidden_act (`str` or `function`, *optional*, defaults to `"silu"`) : The non-linear activation function (function or string) in the decoder. max_position_embeddings (`int`, *optional*, defaults to 32768) : The maximum sequence length that this model might ever be used with. initializer_range (`float`, *optional*, defaults to 0.02) : The standard deviation of the truncated_normal_initializer for initializing all weight matrices. rms_norm_eps (`float`, *optional*, defaults to 1e-05) : The epsilon used by the rms normalization layers. use_cache (`bool`, *optional*, defaults to `True`) : Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if `config.is_decoder=True`. tie_word_embeddings (`bool`, *optional*, defaults to `False`) : Whether the model's input and output word embeddings should be tied. rope_theta (`float`, *optional*, defaults to 1000000.0) : The base period of the RoPE embeddings. use_sliding_window (`bool`, *optional*, defaults to `False`) : Whether to use sliding window attention. sliding_window (`int`, *optional*, defaults to 4096) : Sliding window attention (SWA) window size. If not specified, will default to `4096`. max_window_layers (`int`, *optional*, defaults to 80) : The number of layers using full attention. The first `max_window_layers` layers will use full attention, while any additional layer afterwards will use SWA (Sliding Window Attention). layer_types (`list`, *optional*) : Attention pattern for each layer. attention_dropout (`float`, *optional*, defaults to 0.0) : The dropout ratio for the attention probabilities. rope_scaling (`Dict`, *optional*) : Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value accordingly. Expected contents: `rope_type` (`str`): The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope', 'llama3'], with 'default' being the original RoPE implementation. `factor` (`float`, *optional*): Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In most scaling types, a `factor` of x will enable the model to handle sequences of length x * original maximum pre-trained length. `original_max_position_embeddings` (`int`, *optional*): Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during pretraining. `attention_factor` (`float`, *optional*): Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention computation. If unspecified, it defaults to value recommended by the implementation, using the `factor` field to infer the suggested value. `beta_fast` (`float`, *optional*): Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear ramp function. If unspecified, it defaults to 32. `beta_slow` (`float`, *optional*): Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear ramp function. If unspecified, it defaults to 1. `short_factor` (`list[float]`, *optional*): Only used with 'longrope'. The scaling factor to be applied to short contexts (>> from PIL import Image >>> import requests >>> from transformers import AutoProcessor, Qwen2VLForConditionalGeneration >>> model = Qwen2VLForConditionalGeneration.from_pretrained("Qwen/Qwen2-VL-7B-Instruct") >>> processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct") >>> messages = [ { "role": "user", "content": [ {"type": "image"}, {"type": "text", "text": "What is shown in this image?"}, ], }, ] >>> url = "https://www.ilankelman.org/stopsigns/australia.jpg" >>> image = Image.open(requests.get(url, stream=True).raw) >>> text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) >>> inputs = processor(text=[text], images=[image], vision_infos=[vision_infos]) >>> # Generate >>> generate_ids = model.generate(inputs.input_ids, max_length=30) >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0] "The image shows a street scene with a red stop sign in the foreground. In the background, there is a large red gate with Chinese characters ..." ``` **Parameters:** input_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) : Indices of input sequence tokens in the vocabulary. Padding will be ignored by default. Indices can be obtained using [AutoTokenizer](/docs/transformers/v4.57.3/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v4.57.3/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v4.57.3/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) attention_mask (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) : Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. [What are attention masks?](../glossary#attention-mask) position_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) : Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.n_positions - 1]`. [What are position IDs?](../glossary#position-ids) past_key_values (`~cache_utils.Cache`, *optional*) : Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used to speed up sequential decoding. This typically consists in the `past_key_values` returned by the model at a previous stage of decoding, when `use_cache=True` or `config.use_cache=True`. Only [Cache](/docs/transformers/v4.57.3/en/internal/generation_utils#transformers.Cache) instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). If no `past_key_values` are passed, [DynamicCache](/docs/transformers/v4.57.3/en/internal/generation_utils#transformers.DynamicCache) will be initialized by default. The model will output the same cache format that is fed as input. If `past_key_values` are used, the user is expected to input only unprocessed `input_ids` (those that don't have their past key value states given to this model) of shape `(batch_size, unprocessed_length)` instead of all `input_ids` of shape `(batch_size, sequence_length)`. inputs_embeds (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) : Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model's internal embedding lookup matrix. labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) : Labels for computing the masked language modeling loss. Indices should either be in `[0, ..., config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`. use_cache (`bool`, *optional*) : If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see `past_key_values`). output_attentions (`bool`, *optional*) : Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail. 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. pixel_values (`torch.Tensor` of shape `(batch_size, num_channels, image_size, image_size)`, *optional*) : The tensors corresponding to the input images. Pixel values can be obtained using [Qwen2VLImageProcessor](/docs/transformers/v4.57.3/en/model_doc/qwen2_vl#transformers.Qwen2VLImageProcessor). See [Qwen2VLImageProcessor.__call__()](/docs/transformers/v4.57.3/en/model_doc/videomae#transformers.VideoMAEFeatureExtractor.__call__) for details ([Qwen2VLProcessor](/docs/transformers/v4.57.3/en/model_doc/qwen2_vl#transformers.Qwen2VLProcessor) uses [Qwen2VLImageProcessor](/docs/transformers/v4.57.3/en/model_doc/qwen2_vl#transformers.Qwen2VLImageProcessor) for processing images). pixel_values_videos (`torch.FloatTensor` of shape `(batch_size, num_frames, num_channels, frame_size, frame_size)`, *optional*) : The tensors corresponding to the input video. Pixel values for videos can be obtained using [Qwen2VLVideoProcessor](/docs/transformers/v4.57.3/en/model_doc/qwen2_vl#transformers.Qwen2VLVideoProcessor). See `Qwen2VLVideoProcessor.__call__()` for details ([Qwen2VLProcessor](/docs/transformers/v4.57.3/en/model_doc/qwen2_vl#transformers.Qwen2VLProcessor) uses [Qwen2VLVideoProcessor](/docs/transformers/v4.57.3/en/model_doc/qwen2_vl#transformers.Qwen2VLVideoProcessor) for processing videos). image_grid_thw (`torch.LongTensor` of shape `(num_images, 3)`, *optional*) : The temporal, height and width of feature shape of each image in LLM. video_grid_thw (`torch.LongTensor` of shape `(num_videos, 3)`, *optional*) : The temporal, height and width of feature shape of each video in LLM. rope_deltas (`torch.LongTensor` of shape `(batch_size, )`, *optional*) : The rope index difference between sequence length and multimodal rope. cache_position (`torch.LongTensor` of shape `(sequence_length)`, *optional*) : Indices depicting the position of the input sequence tokens in the sequence. Contrarily to `position_ids`, this tensor is not affected by padding. It is used to update the cache in the correct position and to infer the complete sequence length. **Returns:** ``transformers.models.qwen2_vl.modeling_qwen2_vl.Qwen2VLCausalLMOutputWithPast` or `tuple(torch.FloatTensor)`` A `transformers.models.qwen2_vl.modeling_qwen2_vl.Qwen2VLCausalLMOutputWithPast` or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([Qwen2VLConfig](/docs/transformers/v4.57.3/en/model_doc/qwen2_vl#transformers.Qwen2VLConfig)) and inputs. - **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) -- Language modeling loss (for next-token prediction). - **logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`) -- Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). - **past_key_values** (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [Cache](/docs/transformers/v4.57.3/en/internal/generation_utils#transformers.Cache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). Contains pre-computed hidden-states (key and values in the self-attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding. - **hidden_states** (`tuple[torch.FloatTensor]`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the optional initial embedding outputs. - **attentions** (`tuple[torch.FloatTensor]`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. - **rope_deltas** (`torch.LongTensor` of shape `(batch_size, )`, *optional*) -- The rope index difference between sequence length and multimodal rope.