| { |
| "architectures": [ |
| "KimiK3ForConditionalGeneration" |
| ], |
| "auto_map": { |
| "AutoConfig": "configuration_kimi_k3.KimiK3Config", |
| "AutoModel": "modeling_kimi_k3.KimiK3ForConditionalGeneration", |
| "AutoModelForCausalLM": "modeling_kimi_k3.KimiK3ForConditionalGeneration" |
| }, |
| "bos_token_id": 163584, |
| "dtype": "bfloat16", |
| "eos_token_id": 163586, |
| "ignore_index": -100, |
| "image_placeholder": "<|kimi_image_placeholder|>", |
| "media_placeholder_token_id": 163605, |
| "model_type": "kimi_k3", |
| "pad_token_id": 163839, |
| "text_config": { |
| "_name_or_path": "", |
| "activation_situ_beta": 4.0, |
| "activation_situ_linear_beta": 25.0, |
| "add_cross_attention": false, |
| "architectures": [ |
| "KimiLinearForCausalLM" |
| ], |
| "attn_res_block_size": 8, |
| "auto_map": { |
| "AutoConfig": "configuration_kimi_k3.KimiLinearConfig", |
| "AutoModel": "modeling_kimi_linear.KimiLinearModel", |
| "AutoModelForCausalLM": "modeling_kimi_linear.KimiLinearForCausalLM" |
| }, |
| "bos_token_id": 163584, |
| "chunk_size_feed_forward": 0, |
| "cross_attention_hidden_size": null, |
| "decoder_start_token_id": null, |
| "dtype": "bfloat16", |
| "eos_token_id": 163586, |
| "finetuning_task": null, |
| "first_k_dense_replace": 1, |
| "head_dim": 1, |
| "hidden_act": "situ", |
| "hidden_size": 8, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 32, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "kv_lora_rank": 512, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "latent_moe_use_norm": true, |
| "linear_attn_config": { |
| "full_attn_layers": [ |
| 4, |
| 8, |
| 12, |
| 16, |
| 17 |
| ], |
| "gate_lower_bound": -5.0, |
| "head_dim": 128, |
| "kda_layers": [ |
| 1, |
| 2, |
| 3, |
| 5, |
| 6, |
| 7, |
| 9, |
| 10, |
| 11, |
| 13, |
| 14, |
| 15 |
| ], |
| "num_heads": 8, |
| "short_conv_kernel_size": 4, |
| "use_full_rank_gate": true |
| }, |
| "max_position_embeddings": 1048576, |
| "mla_use_nope": true, |
| "mla_use_output_gate": true, |
| "model_type": "kimi_linear", |
| "moe_intermediate_size": 32, |
| "moe_layer_freq": 1, |
| "moe_renormalize": true, |
| "moe_router_activation_func": "sigmoid", |
| "num_attention_heads": 8, |
| "num_expert_group": 1, |
| "num_experts": 64, |
| "num_experts_per_token": 16, |
| "num_hidden_layers": 17, |
| "num_key_value_heads": 8, |
| "num_nextn_predict_layers": 0, |
| "num_shared_experts": 2, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "pad_token_id": 163839, |
| "prefix": null, |
| "problem_type": null, |
| "pruned_heads": {}, |
| "q_lora_rank": 256, |
| "qk_nope_head_dim": 128, |
| "qk_rope_head_dim": 64, |
| "return_dict": true, |
| "rms_norm_eps": 1e-05, |
| "rope_parameters": { |
| "rope_theta": 10000.0, |
| "rope_type": "default" |
| }, |
| "rope_theta": 10000.0, |
| "routed_expert_hidden_size": 32, |
| "routed_scaling_factor": 1.0, |
| "sep_token_id": null, |
| "task_specific_params": null, |
| "tf_legacy_loss": false, |
| "tie_encoder_decoder": false, |
| "tie_word_embeddings": false, |
| "tokenizer_class": null, |
| "topk_group": 1, |
| "topk_method": "noaux_tc", |
| "torchscript": false, |
| "use_bfloat16": false, |
| "use_cache": true, |
| "use_grouped_topk": true, |
| "v_head_dim": 128, |
| "vocab_size": 163840 |
| }, |
| "tie_word_embeddings": false, |
| "transformers_version": "5.15.0.dev0", |
| "vision_config": { |
| "_name_or_path": "", |
| "activation_func": "gelu_pytorch_tanh", |
| "architectures": null, |
| "attn_bias": false, |
| "chunk_size_feed_forward": 0, |
| "dtype": null, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "init_pos_emb_height": 8, |
| "init_pos_emb_time": 4, |
| "init_pos_emb_width": 8, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "linear_bias": false, |
| "merge_kernel_size": [ |
| 2, |
| 2 |
| ], |
| "merge_type": "sd2_tpool", |
| "mlp_type": "mlp2", |
| "mm_hidden_size": 64, |
| "mm_projector_type": "patchmergerv2", |
| "model_type": "", |
| "norm_type": "rmsnorm", |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "patch_embed_proj_bias": false, |
| "patch_size": 14, |
| "pos_emb_interpolation_mode": "bilinear", |
| "pos_emb_type": "divided_fixed", |
| "problem_type": null, |
| "projector_hidden_act": "gelu", |
| "projector_ln_eps": 1e-05, |
| "qkv_hidden_size": 64, |
| "return_dict": true, |
| "text_hidden_size": 8, |
| "vt_hidden_size": 64, |
| "vt_intermediate_size": 128, |
| "vt_num_attention_heads": 2, |
| "vt_num_hidden_layers": 2 |
| } |
| } |
|
|
