{ "architectures": [ "KimiK25ForConditionalGeneration" ], "auto_map": { "AutoConfig": "configuration_kimi_k25.KimiK25Config", "AutoModel": "modeling_kimi_k25.KimiK25ForConditionalGeneration", "AutoModelForCausalLM": "modeling_kimi_k25.KimiK25ForConditionalGeneration" }, "bos_token_id": 163584, "dtype": "bfloat16", "eos_token_id": 163586, "ignore_index": -100, "media_placeholder_token_id": 163605, "model_type": "kimi_k25", "pad_token_id": 163839, "quantization_config": { "config_groups": { "group_0": { "input_activations": { "dynamic": false, "num_bits": 4, "type": "float", "group_size": 16 }, "weights": { "dynamic": false, "num_bits": 4, "type": "float", "group_size": 16 }, "targets": [ "Linear" ] } }, "ignore": [ "language_model.lm_head", "language_model.model.layers.0*", "language_model.model.layers.1.mlp.shared_experts*", "language_model.model.layers.1.self_attn*", "language_model.model.layers.10.mlp.shared_experts*", "language_model.model.layers.10.self_attn*", "language_model.model.layers.11.mlp.shared_experts*", "language_model.model.layers.11.self_attn*", "language_model.model.layers.12.mlp.shared_experts*", "language_model.model.layers.12.self_attn*", "language_model.model.layers.13.mlp.shared_experts*", "language_model.model.layers.13.self_attn*", "language_model.model.layers.14.mlp.shared_experts*", "language_model.model.layers.14.self_attn*", "language_model.model.layers.15.mlp.shared_experts*", "language_model.model.layers.15.self_attn*", "language_model.model.layers.16.mlp.shared_experts*", "language_model.model.layers.16.self_attn*", "language_model.model.layers.17.mlp.shared_experts*", "language_model.model.layers.17.self_attn*", "language_model.model.layers.18.mlp.shared_experts*", "language_model.model.layers.18.self_attn*", "language_model.model.layers.19.mlp.shared_experts*", "language_model.model.layers.19.self_attn*", "language_model.model.layers.2.mlp.shared_experts*", "language_model.model.layers.2.self_attn*", "language_model.model.layers.20.mlp.shared_experts*", "language_model.model.layers.20.self_attn*", "language_model.model.layers.21.mlp.shared_experts*", "language_model.model.layers.21.self_attn*", "language_model.model.layers.22.mlp.shared_experts*", "language_model.model.layers.22.self_attn*", "language_model.model.layers.23.mlp.shared_experts*", "language_model.model.layers.23.self_attn*", "language_model.model.layers.24.mlp.shared_experts*", "language_model.model.layers.24.self_attn*", "language_model.model.layers.25.mlp.shared_experts*", "language_model.model.layers.25.self_attn*", "language_model.model.layers.26.mlp.shared_experts*", "language_model.model.layers.26.self_attn*", "language_model.model.layers.27.mlp.shared_experts*", "language_model.model.layers.27.self_attn*", "language_model.model.layers.28.mlp.shared_experts*", "language_model.model.layers.28.self_attn*", "language_model.model.layers.29.mlp.shared_experts*", "language_model.model.layers.29.self_attn*", "language_model.model.layers.3.mlp.shared_experts*", "language_model.model.layers.3.self_attn*", "language_model.model.layers.30.mlp.shared_experts*", "language_model.model.layers.30.self_attn*", "language_model.model.layers.31.mlp.shared_experts*", "language_model.model.layers.31.self_attn*", "language_model.model.layers.32.mlp.shared_experts*", "language_model.model.layers.32.self_attn*", "language_model.model.layers.33.mlp.shared_experts*", "language_model.model.layers.33.self_attn*", "language_model.model.layers.34.mlp.shared_experts*", "language_model.model.layers.34.self_attn*", "language_model.model.layers.35.mlp.shared_experts*", "language_model.model.layers.35.self_attn*", "language_model.model.layers.36.mlp.shared_experts*", "language_model.model.layers.36.self_attn*", "language_model.model.layers.37.mlp.shared_experts*", "language_model.model.layers.37.self_attn*", "language_model.model.layers.38.mlp.shared_experts*", "language_model.model.layers.38.self_attn*", "language_model.model.layers.39.mlp.shared_experts*", "language_model.model.layers.39.self_attn*", "language_model.model.layers.4.mlp.shared_experts*", "language_model.model.layers.4.self_attn*", "language_model.model.layers.40.mlp.shared_experts*", "language_model.model.layers.40.self_attn*", "language_model.model.layers.41.mlp.shared_experts*", "language_model.model.layers.41.self_attn*", "language_model.model.layers.42.mlp.shared_experts*", "language_model.model.layers.42.self_attn*", "language_model.model.layers.43.mlp.shared_experts*", "language_model.model.layers.43.self_attn*", "language_model.model.layers.44.mlp.shared_experts*", "language_model.model.layers.44.self_attn*", "language_model.model.layers.45.mlp.shared_experts*", "language_model.model.layers.45.self_attn*", "language_model.model.layers.46.mlp.shared_experts*", "language_model.model.layers.46.self_attn*", "language_model.model.layers.47.mlp.shared_experts*", "language_model.model.layers.47.self_attn*", "language_model.model.layers.48.mlp.shared_experts*", "language_model.model.layers.48.self_attn*", "language_model.model.layers.49.mlp.shared_experts*", "language_model.model.layers.49.self_attn*", "language_model.model.layers.5.mlp.shared_experts*", "language_model.model.layers.5.self_attn*", "language_model.model.layers.50.mlp.shared_experts*", "language_model.model.layers.50.self_attn*", "language_model.model.layers.51.mlp.shared_experts*", "language_model.model.layers.51.self_attn*", "language_model.model.layers.52.mlp.shared_experts*", "language_model.model.layers.52.self_attn*", "language_model.model.layers.53.mlp.shared_experts*", "language_model.model.layers.53.self_attn*", "language_model.model.layers.54.mlp.shared_experts*", "language_model.model.layers.54.self_attn*", "language_model.model.layers.55.mlp.shared_experts*", "language_model.model.layers.55.self_attn*", "language_model.model.layers.56.mlp.shared_experts*", "language_model.model.layers.56.self_attn*", "language_model.model.layers.57.mlp.shared_experts*", "language_model.model.layers.57.self_attn*", "language_model.model.layers.58.mlp.shared_experts*", "language_model.model.layers.58.self_attn*", "language_model.model.layers.59.mlp.shared_experts*", "language_model.model.layers.59.self_attn*", "language_model.model.layers.6.mlp.shared_experts*", "language_model.model.layers.6.self_attn*", "language_model.model.layers.60.mlp.shared_experts*", "language_model.model.layers.60.self_attn*", "language_model.model.layers.7.mlp.shared_experts*", "language_model.model.layers.7.self_attn*", "language_model.model.layers.8.mlp.shared_experts*", "language_model.model.layers.8.self_attn*", "language_model.model.layers.9.mlp.shared_experts*", "language_model.model.layers.9.self_attn*", "mm_projector*", "vision_tower*" ], "quant_algo": "NVFP4", "kv_cache_scheme": { "dynamic": false, "num_bits": 8, "type": "float" }, "producer": { "name": "modelopt", "version": "0.37.0-decart-k2.7" }, "quant_method": "modelopt" }, "text_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": [ "DeepseekV3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_deepseek.DeepseekV3Config", "AutoModel": "modeling_deepseek.DeepseekV3Model", "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM" }, "aux_loss_alpha": 0.001, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 163584, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "dtype": "bfloat16", "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 163586, "ep_size": 1, "exponential_decay_length_penalty": null, "finetuning_task": null, "first_k_dense_replace": 1, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "silu", "hidden_size": 7168, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 18432, "is_decoder": false, "is_encoder_decoder": false, "kv_lora_rank": 512, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 262144, "min_length": 0, "model_type": "deepseek_v3", "moe_intermediate_size": 2048, "moe_layer_freq": 1, "n_group": 1, "n_routed_experts": 384, "n_shared_experts": 1, "no_repeat_ngram_size": 0, "norm_topk_prob": true, "num_attention_heads": 64, "num_beam_groups": 1, "num_beams": 1, "num_experts_per_tok": 8, "num_hidden_layers": 61, "num_key_value_heads": 64, "num_nextn_predict_layers": 0, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 163839, "prefix": null, "pretraining_tp": 1, "problem_type": null, "pruned_heads": {}, "q_lora_rank": 1536, "qk_nope_head_dim": 128, "qk_rope_head_dim": 64, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-05, "rope_scaling": { "beta_fast": 32.0, "beta_slow": 1.0, "factor": 64.0, "mscale": 1.0, "mscale_all_dim": 1.0, "original_max_position_embeddings": 4096, "type": "yarn" }, "rope_theta": 50000.0, "routed_scaling_factor": 2.827, "scoring_func": "sigmoid", "sep_token_id": null, "seq_aux": true, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": false, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "topk_group": 1, "topk_method": "noaux_tc", "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "v_head_dim": 128, "vocab_size": 163840 }, "tie_word_embeddings": false, "transformers_version": "4.57.3", "use_unified_vision_chunk": true, "video_placeholder": "<|kimi_k25_video_placeholder|>", "vision_config": { "init_pos_emb_height": 64, "init_pos_emb_time": 4, "init_pos_emb_width": 64, "merge_kernel_size": [ 2, 2 ], "merge_type": "sd2_tpool", "mm_hidden_size": 1152, "mm_projector_type": "patchmerger", "model_type": "", "patch_size": 14, "pos_emb_type": "divided_fixed", "projector_hidden_act": "gelu", "projector_ln_eps": 1e-05, "text_hidden_size": 7168, "video_attn_type": "spatial_temporal", "vt_hidden_size": 1152, "vt_intermediate_size": 4304, "vt_num_attention_heads": 16, "vt_num_hidden_layers": 27 } }