{ "architectures": [ "MiniMaxM3SparseForConditionalGeneration" ], "auto_map": { "AutoConfig": "configuration_minimax_m3_vl.MiniMaxM3VLConfig" }, "torch_dtype": "bfloat16", "image_grid_pinpoints": "[(336, 336), (336, 672), (336, 1008), (336, 1344), (336, 1680), (336, 2016), (672, 336), (672, 672), (672, 1008), (672, 1344), (672, 1680), (672, 2016), (1008, 336), (1008, 672), (1008, 1008), (1008, 1344), (1008, 1680), (1008, 2016), (1344, 336), (1344, 672), (1344, 1008), (1344, 1344), (1344, 1680), (1344, 2016), (1680, 336), (1680, 672), (1680, 1008), (1680, 1344), (1680, 1680), (1680, 2016), (2016, 336), (2016, 672), (2016, 1008), (2016, 1344), (2016, 1680), (2016, 2016)]", "image_seq_length": 576, "image_token_index": 200025, "img_token_compression_config": { "image_token_compression_method": "patch_merge", "spatial_merge_size": 2, "temporal_patch_size": 2 }, "model_type": "minimax_m3_vl", "multimodal_projector_bias": true, "num_reward_heads": 0, "pad_token_id": 200000, "process_image_mode": "dynamic_res", "projector_hidden_act": "gelu", "projector_hidden_size": 6144, "text_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": [ "MiniMaxM3SparseForCausalLM" ], "attention_output_gate": false, "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, "dense_intermediate_size": 12288, "diversity_penalty": 0.0, "do_sample": false, "torch_dtype": null, "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, "head_dim": 128, "hidden_act": "swigluoai", "hidden_size": 6144, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "intermediate_size": 3072, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 1048576, "min_length": 0, "model_type": "", "moe_layer_freq": [ 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ], "n_shared_experts": 1, "no_repeat_ngram_size": 0, "num_attention_heads": 64, "num_beam_groups": 1, "num_beams": 1, "num_experts_per_tok": 4, "num_hidden_layers": 60, "num_key_value_heads": 4, "num_local_experts": 128, "num_mtp_modules": 7, "num_nextn_predict_layers": 1, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "partial_rotary_factor": 0.5, "prefix": null, "problem_type": null, "pruned_heads": {}, "qk_norm_type": "per_head", "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-06, "rope_theta": 5000000, "rotary_dim": 64, "routed_scaling_factor": 2.0, "scoring_func": "sigmoid", "sep_token_id": null, "shared_intermediate_size": 3072, "sparse_attention_config": { "sparse_attention_freq": [ 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ], "sparse_block_size": 128, "sparse_disable_index_value": [ 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ], "sparse_index_dim": 128, "sparse_init_block": 0, "sparse_local_block": 1, "sparse_num_index_heads": 4, "sparse_score_type": "max", "sparse_topk_blocks": 16, "use_sparse_attention": true }, "suppress_tokens": null, "swiglu_alpha": 1.702, "swiglu_limit": 7.0, "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, "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_gemma_norm": true, "use_qk_norm": true, "use_routing_bias": true, "vocab_size": 200064 }, "transformers_version": "4.57.6", "unsloth_fixed": true, "video_token_index": 200026, "vision_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": null, "attention_dropout": 0.0, "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, "torch_dtype": null, "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": 1280, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 2016, "img_token_compression_config": { "image_token_compression_method": "patch_merge", "spatial_merge_size": 2, "temporal_patch_size": 2 }, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 5120, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-05, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "", "no_repeat_ngram_size": 0, "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 32, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 14, "position_embedding_type": "rope", "prefix": null, "problem_type": null, "projection_dim": 6144, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rope_mode": "3d", "rope_theta": 10000.0, "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, "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "vision_segment_max_frames": 4, "vocab_size": 32000 }, "vision_feature_layer": -1, "vision_feature_select_strategy": "full" }