| { | |
| "architectures": [ | |
| "LongcatFlashForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attention_method": "MLA", | |
| "auto_map": { | |
| "AutoConfig": "configuration_longcat_flash.LongcatFlashConfig", | |
| "AutoModel": "modeling_longcat_flash.LongcatFlashModel", | |
| "AutoModelForCausalLM": "modeling_longcat_flash.LongcatFlashForCausalLM" | |
| }, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "expert_ffn_hidden_size": 64, | |
| "ffn_hidden_size": 64, | |
| "head_dim": 192, | |
| "hidden_act": "silu", | |
| "hidden_size": 8, | |
| "initializer_range": 0.006, | |
| "kv_lora_rank": 384, | |
| "max_position_embeddings": 131072, | |
| "mla_scale_kv_lora": true, | |
| "mla_scale_q_lora": true, | |
| "model_type": "longcat_flash", | |
| "moe_topk": 12, | |
| "n_routed_experts": 32, | |
| "norm_topk_prob": false, | |
| "num_attention_heads": 4, | |
| "num_key_value_heads": 4, | |
| "num_layers": 2, | |
| "q_lora_rank": 32, | |
| "qk_head_dim": 256, | |
| "qk_nope_head_dim": 64, | |
| "qk_rope_head_dim": 192, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000000.0, | |
| "routed_scaling_factor": 6.0, | |
| "router_bias": false, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.56.0.dev0", | |
| "use_cache": true, | |
| "v_head_dim": 64, | |
| "vocab_size": 131072, | |
| "zero_expert_num": 16, | |
| "zero_expert_type": "identity" | |
| } |