{ "_attn_implementation_autoset": false, "add_cross_attention": false, "architectures": [ "KimiVLForConditionalGeneration" ], "auto_map": { "AutoConfig": "configuration_kimi_vl.KimiVLConfig", "AutoModel": "modeling_kimi_vl.KimiVLForConditionalGeneration", "AutoModelForCausalLM": "modeling_kimi_vl.KimiVLForConditionalGeneration" }, "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, "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, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "ignore_index": -100, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "media_placeholder_token_id": 163605, "min_length": 0, "model_type": "kimi_vl", "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 0, "prefix": null, "problem_type": null, "pruned_heads": {}, "quantization": { "group_size": 64, "bits": 8 }, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "text_config": { "vocab_size": 163840, "max_position_embeddings": 131072, "hidden_size": 2048, "intermediate_size": 11264, "moe_intermediate_size": 1408, "num_hidden_layers": 27, "num_nextn_predict_layers": 1, "num_attention_heads": 16, "n_shared_experts": 2, "n_routed_experts": 64, "ep_size": 1, "routed_scaling_factor": 2.446, "kv_lora_rank": 512, "q_lora_rank": null, "qk_rope_head_dim": 64, "v_head_dim": 128, "qk_nope_head_dim": 128, "topk_method": "noaux_tc", "n_group": 1, "topk_group": 1, "num_experts_per_tok": 6, "moe_layer_freq": 1, "first_k_dense_replace": 1, "norm_topk_prob": true, "scoring_func": "sigmoid", "aux_loss_alpha": 0.001, "seq_aux": true, "num_key_value_heads": 16, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 800000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": "bfloat16", "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": null, "finetuning_task": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "tokenizer_class": null, "prefix": null, "bos_token_id": 163584, "pad_token_id": 163839, "eos_token_id": 163585, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "model_type": "deepseek_v3" }, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": false, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torchscript": false, "transformers_version": "4.52.0.dev0", "typical_p": 1.0, "use_bfloat16": false, "vision_config": { "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": "bfloat16", "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": true, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": null, "finetuning_task": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "tokenizer_class": null, "prefix": null, "bos_token_id": null, "pad_token_id": null, "eos_token_id": null, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "model_type": "moonvit", "patch_size": 14, "init_pos_emb_height": 64, "init_pos_emb_width": 64, "num_hidden_layers": 27, "num_attention_heads": 16, "hidden_size": 1152, "intermediate_size": 4304, "merge_kernel_size": [ 2, 2 ], "skip_vision": true }, "vocab_size": 163840 }