| { | |
| "num_hidden_layers": 30, | |
| "vocab_size": 151936, | |
| "hidden_size": 2048, | |
| "intermediate_size": 5120, | |
| "num_attention_heads": 16, | |
| "num_key_value_heads": 4, | |
| "hidden_act": "silu", | |
| "use_qkv_bias": false, | |
| "use_bias": false, | |
| "rms_norm_eps": 1e-06, | |
| "embedding_dropout": 0.0, | |
| "attention_dropout": 0.0, | |
| "output_dropout": 0.0, | |
| "num_nextn_predict_layers": 0, | |
| "mtp_loss_scaling_factor": 0, | |
| "initializer_range": 0.02, | |
| "max_position_embeddings": 32768, | |
| "rope_theta": 600000, | |
| "use_cache": true, | |
| "max_window_layers": 20, | |
| "head_dim": 128, | |
| "rope_scaling": null, | |
| "use_qk_norm": true, | |
| "moe_router_enable_expert_bias": true, | |
| "routed_scaling_factor": 2.5, | |
| "num_experts": 224, | |
| "num_shared_experts": null, | |
| "num_experts_per_tok": 8, | |
| "n_group": 8, | |
| "topk_group": 4, | |
| "moe_intermediate_size": 512, | |
| "first_k_dense_replace": 1, | |
| "output_router_logits": true, | |
| "return_dict": true, | |
| "output_hidden_states": false, | |
| "torchscript": false, | |
| "dtype": "bfloat16", | |
| "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, | |
| "architectures": [ | |
| "BailingMoeV2ForCausalLM" | |
| ], | |
| "finetuning_task": null, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "task_specific_params": null, | |
| "problem_type": null, | |
| "tokenizer_class": null, | |
| "prefix": null, | |
| "bos_token_id": 151643, | |
| "pad_token_id": null, | |
| "eos_token_id": 151645, | |
| "sep_token_id": null, | |
| "decoder_start_token_id": null, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "num_beams": 1, | |
| "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, | |
| "num_beam_groups": 1, | |
| "diversity_penalty": 0.0, | |
| "_name_or_path": "RedMod/9kling224-fuse-heal-tokmerge-noheal-correcttok", | |
| "transformers_version": "4.57.3", | |
| "_moe_implementation": "fused", | |
| "auto_map": { | |
| "AutoConfig": "configuration_bailing_moe_v2.BailingMoeV2Config", | |
| "AutoModel": "modeling_bailing_moe_v2.BailingMoeV2Model", | |
| "AutoModelForCausalLM": "modeling_bailing_moe_v2.BailingMoeV2ForCausalLM" | |
| }, | |
| "moe_shared_expert_intermediate_size": 512, | |
| "norm_topk_prob": true, | |
| "partial_rotary_factor": 0.5, | |
| "pruning_info": { | |
| "original_experts": 256, | |
| "original_model_path": "5kling-fuse_heal", | |
| "pruned_experts": 224, | |
| "pruning_date": "2026-01-16T05:26:11.661656", | |
| "pruning_method": "MoP" | |
| }, | |
| "quantize": false, | |
| "router_dtype": "fp32", | |
| "score_function": "sigmoid", | |
| "use_rmsnorm": true, | |
| "tf_legacy_loss": false, | |
| "use_bfloat16": false, | |
| "model_type": "", | |
| "output_attentions": false | |
| } |