# Glm4vMoe ## Overview The GLM-V model was proposed in [GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning](https://huggingface.co/papers/2507.01006v6). The abstract from the paper is the following: > *We present GLM-4.1V-Thinking, GLM-4.5V, and GLM-4.6V, a family of vision-language models (VLMs) designed to advance general-purpose multimodal understanding and reasoning. In this report, we share our key findings in the development of the reasoning-centric training framework. We first develop a capable vision foundation model with significant potential through large-scale pre-training, which arguably sets the upper bound for the final performance. We then propose Reinforcement Learning with Curriculum Sampling (RLCS) to unlock the full potential of the model, leading to comprehensive capability enhancement across a diverse range of tasks, including STEM problem solving, video understanding, content recognition, coding, grounding, GUI-based agents, and long document interpretation. In a comprehensive evaluation across 42 public benchmarks, GLM-4.5V achieves state-of-the-art performance on nearly all tasks among open-source models of similar size, and demonstrates competitive or even superior results compared to closed-source models such as Gemini-2.5-Flash on challenging tasks including Coding and GUI Agents. Meanwhile, the smaller GLM-4.1V-9B-Thinking remains highly competitive-achieving superior results to the much larger Qwen2.5-VL-72B on 29 benchmarks. We open-source both GLM-4.1V-9B-Thinking and GLM-4.5V. We further introduce the GLM-4.6V series, open-source multimodal models with native tool use and a 128K context window. A brief overview is available at this https URL. Code, models and more information are released at https://github.com/zai-org/GLM-V* ## Support Model This Model type support these model of zai-org: + [GLM-4.5V](https://huggingface.co/zai-org/GLM-4.5V) + [GLM-4.6V](https://huggingface.co/zai-org/GLM-4.6V) This model was contributed by [Raushan Turganbay](https://huggingface.co/RaushanTurganbay) and [Yuxuan Zhang](https://huggingface.co/ZHANGYUXUAN-zR). ## Glm4vMoeConfig[[transformers.Glm4vMoeConfig]] #### transformers.Glm4vMoeConfig[[transformers.Glm4vMoeConfig]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/glm4v_moe/configuration_glm4v_moe.py#L153) This is the configuration class to store the configuration of a Glm4vMoeModel. It is used to instantiate a Glm4V Moe model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the [zai-org/GLM-4.5V](https://huggingface.co/zai-org/GLM-4.5V) Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.8.0/en/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the documentation from [PreTrainedConfig](/docs/transformers/v5.8.0/en/main_classes/configuration#transformers.PreTrainedConfig) for more information. ```python >>> from transformers import Glm4vMoeForConditionalGeneration, Glm4vMoeConfig >>> # Initializing a GLM-4.5V style configuration >>> configuration = Glm4vMoeConfig() >>> # Initializing a model from the GLM-4.5V style configuration >>> model = Glm4vMoeForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` **Parameters:** text_config (`Union[dict, ~configuration_utils.PreTrainedConfig]`, *optional*) : The config object or dictionary of the text backbone. vision_config (`Union[dict, ~configuration_utils.PreTrainedConfig]`, *optional*) : The config object or dictionary of the vision backbone. image_token_id (`int`, *optional*, defaults to `151363`) : The image token index used as a placeholder for input images. video_token_id (`int`, *optional*, defaults to `151364`) : The video token index used as a placeholder for input videos. image_start_token_id (`int`, *optional*, defaults to 151339) : The image start token index to encode the start of image. image_end_token_id (`int`, *optional*, defaults to 151340) : The image end token index to encode the end of image. video_start_token_id (`int`, *optional*, defaults to 151341) : The video start token index to encode the start of video. video_end_token_id (`int`, *optional*, defaults to 151342) : The video end token index to encode the end of video. tie_word_embeddings (`bool`, *optional*, defaults to `False`) : Whether to tie weight embeddings according to model's `tied_weights_keys` mapping. ## Glm4vMoeVisionConfig[[transformers.Glm4vMoeVisionConfig]] #### transformers.Glm4vMoeVisionConfig[[transformers.Glm4vMoeVisionConfig]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/glm4v_moe/configuration_glm4v_moe.py#L111) This is the configuration class to store the configuration of a Glm4vMoeModel. It is used to instantiate a Glm4V Moe model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the [zai-org/GLM-4.1V-9B-Thinking](https://huggingface.co/zai-org/GLM-4.1V-9B-Thinking) Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.8.0/en/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the documentation from [PreTrainedConfig](/docs/transformers/v5.8.0/en/main_classes/configuration#transformers.PreTrainedConfig) for more information. Example: ```python >>> from transformers import Glm4vMoeVisionConfig, Glm4vMoeVisionModel >>> # Initializing a Glm4vMoeVisionConfig GLM-4.1V-9B style configuration >>> configuration = Glm4vMoeVisionConfig() >>> # Initializing a model (with random weights) from the GLM-4.1V-9B configuration >>> model = Glm4vMoeVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` **Parameters:** depth (`int`, *optional*, defaults to `24`) : Number of Transformer layers in the vision encoder. hidden_size (`int`, *optional*, defaults to `1536`) : Dimension of the hidden representations. hidden_act (`str`, *optional*, defaults to `silu`) : The non-linear activation function (function or string) in the decoder. For example, `"gelu"`, `"relu"`, `"silu"`, etc. attention_bias (`bool`, *optional*, defaults to `False`) : Whether to use a bias in the query, key, value and output projection layers during self-attention. attention_dropout (`Union[float, int]`, *optional*, defaults to `0.0`) : The dropout ratio for the attention probabilities. num_heads (`int`, *optional*, defaults to `12`) : Number of attention heads for each attention layer in the Transformer decoder. in_channels (`int`, *optional*, defaults to `3`) : The number of input channels. image_size (`Union[int, list[int], tuple[int, int]]`, *optional*, defaults to `336`) : The size (resolution) of each image. patch_size (`Union[int, list[int], tuple[int, int]]`, *optional*, defaults to `14`) : The size (resolution) of each patch. rms_norm_eps (`float`, *optional*, defaults to `1e-05`) : The epsilon used by the rms normalization layers. spatial_merge_size (`int`, *optional*, defaults to `2`) : The size of the spatial merge window used to reduce the number of visual tokens by merging neighboring patches. temporal_patch_size (`Union[int, list[int], tuple[int, int]]`, *optional*, defaults to `2`) : Temporal patch size used in the 3D patch embedding for video inputs. out_hidden_size (`int`, *optional*, defaults to 4096) : The output hidden size of the vision model. intermediate_size (`int`, *optional*, defaults to `13696`) : Dimension of the MLP representations. initializer_range (`float`, *optional*, defaults to `0.02`) : The standard deviation of the truncated_normal_initializer for initializing all weight matrices. ## Glm4vMoeTextConfig[[transformers.Glm4vMoeTextConfig]] #### transformers.Glm4vMoeTextConfig[[transformers.Glm4vMoeTextConfig]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/glm4v_moe/configuration_glm4v_moe.py#L29) This is the configuration class to store the configuration of a Glm4vMoeModel. It is used to instantiate a Glm4V Moe model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the [zai-org/GLM-4.5V](https://huggingface.co/zai-org/GLM-4.5V) Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.8.0/en/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the documentation from [PreTrainedConfig](/docs/transformers/v5.8.0/en/main_classes/configuration#transformers.PreTrainedConfig) for more information. Example: ```python >>> from transformers import Glm4vMoeTextModel, Glm4vMoeConfig >>> # Initializing a GLM-4.5V style configuration >>> configuration = Glm4vMoeConfig() >>> # Initializing a model from the GLM-4.5V style configuration >>> model = Glm4vMoeTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` **Parameters:** vocab_size (`int`, *optional*, defaults to `151424`) : Vocabulary size of the model. Defines the number of different tokens that can be represented by the `input_ids`. hidden_size (`int`, *optional*, defaults to `4096`) : Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to `10944`) : Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to `46`) : Number of hidden layers in the Transformer decoder. num_attention_heads (`int`, *optional*, defaults to `96`) : Number of attention heads for each attention layer in the Transformer decoder. 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 `num_attention_heads`. hidden_act (`str`, *optional*, defaults to `silu`) : The non-linear activation function (function or string) in the decoder. For example, `"gelu"`, `"relu"`, `"silu"`, etc. max_position_embeddings (`int`, *optional*, defaults to `65536`) : 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` or when the model is a decoder-only generative model. tie_word_embeddings (`bool`, *optional*, defaults to `False`) : Whether to tie weight embeddings according to model's `tied_weights_keys` mapping. rope_parameters (`Union[~modeling_rope_utils.RopeParameters, dict]`, *optional*) : Dictionary containing the configuration parameters for the RoPE embeddings. The dictionary should contain a value for `rope_theta` and optionally parameters used for scaling in case you want to use RoPE with longer `max_position_embeddings`. attention_bias (`bool`, *optional*, defaults to `True`) : Whether to use a bias in the query, key, value and output projection layers during self-attention. attention_dropout (`Union[float, int]`, *optional*, defaults to `0.0`) : The dropout ratio for the attention probabilities. moe_intermediate_size (`int`, *optional*, defaults to `1408`) : Intermediate size of the routed expert MLPs. num_experts_per_tok (`int`, *optional*, defaults to `8`) : Number of experts to route each token to. This is the top-k value for the token-choice routing. n_shared_experts (`int`, *optional*, defaults to `1`) : Number of shared experts. n_routed_experts (`int`, *optional*, defaults to `128`) : Number of routed experts. routed_scaling_factor (`float`, *optional*, defaults to `1.0`) : Scaling factor or routed experts. n_group (`int`, *optional*, defaults to 1) : Number of groups for routed experts. topk_group (`int`, *optional*, defaults to `1`) : Number of selected groups for each token (for each token, ensuring the selected experts is only within `topk_group` groups). first_k_dense_replace (`int`, *optional*, defaults to 1) : Number of dense layers in shallow layers(embed->dense->dense->...->dense->moe->moe...->lm_head). \--k dense layers--/ norm_topk_prob (`bool`, *optional*, defaults to `True`) : Whether to normalize the weights of the routed experts. bos_token_id (`int`, *optional*) : Token id used for beginning-of-stream in the vocabulary. eos_token_id (`Union[int, list[int]]`, *optional*) : Token id used for end-of-stream in the vocabulary. pad_token_id (`int`, *optional*) : Token id used for padding in the vocabulary. router_aux_loss_coef (`float`, *optional*, defaults to `0.0001`) : Auxiliary load balancing loss coefficient. Used to penalize uneven expert routing in MoE models. ## Glm4vMoeVisionModel[[transformers.Glm4vMoeVisionModel]] #### transformers.Glm4vMoeVisionModel[[transformers.Glm4vMoeVisionModel]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/glm4v_moe/modeling_glm4v_moe.py#L757) The bare Glm4V Moe Model outputting raw hidden-states without any specific head on top. This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.) This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior. forwardtransformers.Glm4vMoeVisionModel.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/glm4v_moe/modeling_glm4v_moe.py#L823[{"name": "hidden_states", "val": ": Tensor"}, {"name": "grid_thw", "val": ": Tensor"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **hidden_states** (`torch.Tensor` of shape `(seq_len, hidden_size)`) -- The final hidden states of the model. - **grid_thw** (`torch.Tensor` of shape `(num_images_or_videos, 3)`) -- The temporal, height and width of feature shape of each image in LLM.0`torch.Tensor`hidden_states. The [Glm4vMoeVisionModel](/docs/transformers/v5.8.0/en/model_doc/glm4v_moe#transformers.Glm4vMoeVisionModel) forward method, overrides the `__call__` special method. Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them. **Parameters:** config ([Glm4vMoeVisionModel](/docs/transformers/v5.8.0/en/model_doc/glm4v_moe#transformers.Glm4vMoeVisionModel)) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from_pretrained()](/docs/transformers/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** ``torch.Tensor`` hidden_states. ## Glm4vMoeTextModel[[transformers.Glm4vMoeTextModel]] #### transformers.Glm4vMoeTextModel[[transformers.Glm4vMoeTextModel]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/glm4v_moe/modeling_glm4v_moe.py#L964) The bare Glm4V Moe Text Model outputting raw hidden-states without any specific head on to. This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.) This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior. forwardtransformers.Glm4vMoeTextModel.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/glm4v_moe/modeling_glm4v_moe.py#L989[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.modeling_flash_attention_utils.FlashAttentionKwargs]"}]- **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/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/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/v5.8.0/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/v5.8.0/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. - **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`).0`MoeModelOutputWithPast` or `tuple(torch.FloatTensor)`A `MoeModelOutputWithPast` 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 (`None`) and inputs. The [Glm4vMoeTextModel](/docs/transformers/v5.8.0/en/model_doc/glm4v_moe#transformers.Glm4vMoeTextModel) forward method, overrides the `__call__` special method. Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them. - **last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`) -- Sequence of hidden-states at the output of the last layer of the model. - **past_key_values** (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [Cache](/docs/transformers/v5.8.0/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 and optionally if `config.is_encoder_decoder=True` in the cross-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. - **router_logits** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_router_probs=True` and `config.add_router_probs=True` is passed or when `config.output_router_probs=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, sequence_length, num_experts)`. Raw router logtis (post-softmax) that are computed by MoE routers, these terms are used to compute the auxiliary loss for Mixture of Experts models. **Parameters:** config ([Glm4vMoeTextConfig](/docs/transformers/v5.8.0/en/model_doc/glm4v_moe#transformers.Glm4vMoeTextConfig)) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from_pretrained()](/docs/transformers/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** ``MoeModelOutputWithPast` or `tuple(torch.FloatTensor)`` A `MoeModelOutputWithPast` 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 (`None`) and inputs. ## Glm4vMoeModel[[transformers.Glm4vMoeModel]] #### transformers.Glm4vMoeModel[[transformers.Glm4vMoeModel]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/glm4v_moe/modeling_glm4v_moe.py#L1097) The bare Glm4V Moe Model outputting raw hidden-states without any specific head on top. This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.) This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior. forwardtransformers.Glm4vMoeModel.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/glm4v_moe/modeling_glm4v_moe.py#L1413[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "pixel_values", "val": ": torch.Tensor | None = None"}, {"name": "pixel_values_videos", "val": ": torch.FloatTensor | None = None"}, {"name": "image_grid_thw", "val": ": torch.LongTensor | None = None"}, {"name": "video_grid_thw", "val": ": torch.LongTensor | None = None"}, {"name": "rope_deltas", "val": ": torch.LongTensor | None = None"}, {"name": "mm_token_type_ids", "val": ": torch.IntTensor | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **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/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/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/v5.8.0/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/v5.8.0/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. - **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 `image_processor_class`. See `image_processor_class.__call__` for details (`processor_class` uses `image_processor_class` 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 `video_processor_class`. See `video_processor_class.__call__` for details (`processor_class` uses `video_processor_class` 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. - **mm_token_type_ids** (`torch.IntTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of input sequence tokens matching each modality. For example text (0), image (1), video (2). Multimodal token type ids can be obtained using [AutoProcessor](/docs/transformers/v5.8.0/en/model_doc/auto#transformers.AutoProcessor). See [ProcessorMixin.__call__()](/docs/transformers/v5.8.0/en/model_doc/align#transformers.AlignProcessor.__call__) for details.0`Glm4vMoeModelOutputWithPast` or `tuple(torch.FloatTensor)`A `Glm4vMoeModelOutputWithPast` 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 (`None`) and inputs. The [Glm4vMoeModel](/docs/transformers/v5.8.0/en/model_doc/glm4v_moe#transformers.Glm4vMoeModel) forward method, overrides the `__call__` special method. Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them. - **last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*, defaults to `None`) -- Sequence of hidden-states at the output of the last layer of the model. - **past_key_values** (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [Cache](/docs/transformers/v5.8.0/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. - **router_logits** (`tuple[torch.FloatTensor]`, *optional*, returned when `output_router_logits=True` is passed or when `config.add_router_probs=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, sequence_length, num_experts)`. Router logits of the model, useful to compute the auxiliary loss for Mixture of Experts models. **Parameters:** config ([Glm4vMoeModel](/docs/transformers/v5.8.0/en/model_doc/glm4v_moe#transformers.Glm4vMoeModel)) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from_pretrained()](/docs/transformers/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** ``Glm4vMoeModelOutputWithPast` or `tuple(torch.FloatTensor)`` A `Glm4vMoeModelOutputWithPast` 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 (`None`) and inputs. #### get_video_features[[transformers.Glm4vMoeModel.get_video_features]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/glm4v_moe/modeling_glm4v_moe.py#L1269) - **last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`) -- Sequence of hidden-states at the output of the last layer of the model. - **pooler_output** (`torch.FloatTensor` of shape `(batch_size, hidden_size)`) -- Last layer hidden-state of the first token of the sequence (classification token) after further processing through the layers used for the auxiliary pretraining task. E.g. for BERT-family of models, this returns the classification token after processing through a linear layer and a tanh activation function. The linear layer weights are trained from the next sentence prediction (classification) objective during pretraining. - **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. **Parameters:** pixel_values_videos (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)`) : The tensors corresponding to the input videos. video_grid_thw (`torch.LongTensor` of shape `(num_videos, 3)`, *optional*) : The temporal, height and width of feature shape of each video in LLM. **Returns:** `[BaseModelOutputWithPooling](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`` A [BaseModelOutputWithPooling](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) 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 ([Glm4vMoeConfig](/docs/transformers/v5.8.0/en/model_doc/glm4v_moe#transformers.Glm4vMoeConfig)) and inputs. #### get_image_features[[transformers.Glm4vMoeModel.get_image_features]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/glm4v_moe/modeling_glm4v_moe.py#L1300) - **last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`) -- Sequence of hidden-states at the output of the last layer of the model. - **pooler_output** (`torch.FloatTensor` of shape `(batch_size, hidden_size)`) -- Last layer hidden-state of the first token of the sequence (classification token) after further processing through the layers used for the auxiliary pretraining task. E.g. for BERT-family of models, this returns the classification token after processing through a linear layer and a tanh activation function. The linear layer weights are trained from the next sentence prediction (classification) objective during pretraining. - **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. **Parameters:** pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)`) : The tensors corresponding to the input images. image_grid_thw (`torch.LongTensor` of shape `(num_images, 3)`, *optional*) : The temporal, height and width of feature shape of each image in LLM. **Returns:** `[BaseModelOutputWithPooling](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`` A [BaseModelOutputWithPooling](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) 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 ([Glm4vMoeConfig](/docs/transformers/v5.8.0/en/model_doc/glm4v_moe#transformers.Glm4vMoeConfig)) and inputs. ## Glm4vMoeForConditionalGeneration[[transformers.Glm4vMoeForConditionalGeneration]] #### transformers.Glm4vMoeForConditionalGeneration[[transformers.Glm4vMoeForConditionalGeneration]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/glm4v_moe/modeling_glm4v_moe.py#L1564) forwardtransformers.Glm4vMoeForConditionalGeneration.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/glm4v_moe/modeling_glm4v_moe.py#L1616[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "labels", "val": ": torch.LongTensor | None = None"}, {"name": "pixel_values", "val": ": torch.Tensor | None = None"}, {"name": "pixel_values_videos", "val": ": torch.FloatTensor | None = None"}, {"name": "image_grid_thw", "val": ": torch.LongTensor | None = None"}, {"name": "video_grid_thw", "val": ": torch.LongTensor | None = None"}, {"name": "mm_token_type_ids", "val": ": torch.IntTensor | None = None"}, {"name": "logits_to_keep", "val": ": int | torch.Tensor = 0"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **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/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/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/v5.8.0/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/v5.8.0/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]`. - **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 `image_processor_class`. See `image_processor_class.__call__` for details (`processor_class` uses `image_processor_class` 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 `video_processor_class`. See `video_processor_class.__call__` for details (`processor_class` uses `video_processor_class` 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. - **mm_token_type_ids** (`torch.IntTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of input sequence tokens matching each modality. For example text (0), image (1), video (2). Multimodal token type ids can be obtained using [AutoProcessor](/docs/transformers/v5.8.0/en/model_doc/auto#transformers.AutoProcessor). See [ProcessorMixin.__call__()](/docs/transformers/v5.8.0/en/model_doc/align#transformers.AlignProcessor.__call__) for details. - **logits_to_keep** (`Union[int, torch.Tensor]`, *optional*, defaults to `0`) -- If an `int`, compute logits for the last `logits_to_keep` tokens. If `0`, calculate logits for all `input_ids` (special case). Only last token logits are needed for generation, and calculating them only for that token can save memory, which becomes pretty significant for long sequences or large vocabulary size. If a `torch.Tensor`, must be 1D corresponding to the indices to keep in the sequence length dimension. This is useful when using packed tensor format (single dimension for batch and sequence length).0`Glm4vMoeCausalLMOutputWithPast` or `tuple(torch.FloatTensor)`A `Glm4vMoeCausalLMOutputWithPast` 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 (`None`) and inputs. The [Glm4vMoeForConditionalGeneration](/docs/transformers/v5.8.0/en/model_doc/glm4v_moe#transformers.Glm4vMoeForConditionalGeneration) forward method, overrides the `__call__` special method. Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them. - **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/v5.8.0/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. - **router_logits** (`tuple[torch.FloatTensor]`, *optional*, returned when `output_router_logits=True` is passed or when `config.add_router_probs=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, sequence_length, num_experts)`. Router logits of the model, useful to compute the auxiliary loss for Mixture of Experts models. - **aux_loss** (`torch.FloatTensor`, *optional*, returned when `labels` is provided) -- aux_loss for the sparse modules. Example: ```python >>> from PIL import Image >>> import httpx >>> from io import BytesIO >>> from transformers import AutoProcessor, Glm4vMoeForConditionalGeneration >>> model = Glm4vMoeForConditionalGeneration.from_pretrained("zai-org/GLM-4.1V-9B-Thinking") >>> processor = AutoProcessor.from_pretrained("zai-org/GLM-4.1V-9B-Thinking") >>> messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://www.ilankelman.org/stopsigns/australia.jpg"}, {"type": "text", "text": "What is shown in this image?"}, ], }, ] >>> url = "https://www.ilankelman.org/stopsigns/australia.jpg" >>> with httpx.stream("GET", url) as response: ... image = Image.open(BytesIO(response.read())) >>> 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/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/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/v5.8.0/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/v5.8.0/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]`. 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 `image_processor_class`. See `image_processor_class.__call__` for details (`processor_class` uses `image_processor_class` 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 `video_processor_class`. See `video_processor_class.__call__` for details (`processor_class` uses `video_processor_class` 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. mm_token_type_ids (`torch.IntTensor` of shape `(batch_size, sequence_length)`, *optional*) : Indices of input sequence tokens matching each modality. For example text (0), image (1), video (2). Multimodal token type ids can be obtained using [AutoProcessor](/docs/transformers/v5.8.0/en/model_doc/auto#transformers.AutoProcessor). See [ProcessorMixin.__call__()](/docs/transformers/v5.8.0/en/model_doc/align#transformers.AlignProcessor.__call__) for details. logits_to_keep (`Union[int, torch.Tensor]`, *optional*, defaults to `0`) : If an `int`, compute logits for the last `logits_to_keep` tokens. If `0`, calculate logits for all `input_ids` (special case). Only last token logits are needed for generation, and calculating them only for that token can save memory, which becomes pretty significant for long sequences or large vocabulary size. If a `torch.Tensor`, must be 1D corresponding to the indices to keep in the sequence length dimension. This is useful when using packed tensor format (single dimension for batch and sequence length). **Returns:** ``Glm4vMoeCausalLMOutputWithPast` or `tuple(torch.FloatTensor)`` A `Glm4vMoeCausalLMOutputWithPast` 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 (`None`) and inputs. #### get_video_features[[transformers.Glm4vMoeForConditionalGeneration.get_video_features]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/glm4v_moe/modeling_glm4v_moe.py#L1584) - **last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`) -- Sequence of hidden-states at the output of the last layer of the model. - **pooler_output** (`torch.FloatTensor` of shape `(batch_size, hidden_size)`) -- Last layer hidden-state of the first token of the sequence (classification token) after further processing through the layers used for the auxiliary pretraining task. E.g. for BERT-family of models, this returns the classification token after processing through a linear layer and a tanh activation function. The linear layer weights are trained from the next sentence prediction (classification) objective during pretraining. - **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. Example: ```python >>> from PIL import Image >>> from transformers import AutoProcessor, Glm4vMoeForConditionalGeneration >>> model = Glm4vMoeForConditionalGeneration.from_pretrained("zai-org/GLM-4.5V") >>> processor = AutoProcessor.from_pretrained("zai-org/GLM-4.5V") >>> messages = [ ... { ... "role": "user", "content": [ ... {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"}, ... {"type": "text", "text": "Where is the cat standing?"}, ... ] ... }, ... ] >>> inputs = processor.apply_chat_template( ... messages, ... tokenize=True, ... return_dict=True, ... return_tensors="pt", ... add_generation_prompt=True ... ) >>> # Generate >>> generate_ids = model.generate(**inputs) >>> processor.batch_decode(generate_ids, skip_special_tokens=True)[0] ``` **Parameters:** pixel_values_videos (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)`) : The tensors corresponding to the input videos. video_grid_thw (`torch.LongTensor` of shape `(num_videos, 3)`, *optional*) : The temporal, height and width of feature shape of each video in LLM. **Returns:** `[BaseModelOutputWithPooling](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`` A [BaseModelOutputWithPooling](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) 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 ([Glm4vMoeConfig](/docs/transformers/v5.8.0/en/model_doc/glm4v_moe#transformers.Glm4vMoeConfig)) and inputs. #### get_image_features[[transformers.Glm4vMoeForConditionalGeneration.get_image_features]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/glm4v_moe/modeling_glm4v_moe.py#L1601) - **last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`) -- Sequence of hidden-states at the output of the last layer of the model. - **pooler_output** (`torch.FloatTensor` of shape `(batch_size, hidden_size)`) -- Last layer hidden-state of the first token of the sequence (classification token) after further processing through the layers used for the auxiliary pretraining task. E.g. for BERT-family of models, this returns the classification token after processing through a linear layer and a tanh activation function. The linear layer weights are trained from the next sentence prediction (classification) objective during pretraining. - **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. Example: ```python >>> from PIL import Image >>> from transformers import AutoProcessor, Glm4vMoeForConditionalGeneration >>> model = Glm4vMoeForConditionalGeneration.from_pretrained("zai-org/GLM-4.5V") >>> processor = AutoProcessor.from_pretrained("zai-org/GLM-4.5V") >>> messages = [ ... { ... "role": "user", "content": [ ... {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"}, ... {"type": "text", "text": "Where is the cat standing?"}, ... ] ... }, ... ] >>> inputs = processor.apply_chat_template( ... messages, ... tokenize=True, ... return_dict=True, ... return_tensors="pt", ... add_generation_prompt=True ... ) >>> # Generate >>> generate_ids = model.generate(**inputs) >>> processor.batch_decode(generate_ids, skip_special_tokens=True)[0] ``` **Parameters:** pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)`) : The tensors corresponding to the input images. image_grid_thw (`torch.LongTensor` of shape `(num_images, 3)`, *optional*) : The temporal, height and width of feature shape of each image in LLM. **Returns:** `[BaseModelOutputWithPooling](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`` A [BaseModelOutputWithPooling](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) 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 ([Glm4vMoeConfig](/docs/transformers/v5.8.0/en/model_doc/glm4v_moe#transformers.Glm4vMoeConfig)) and inputs.