| { |
| "architectures": [ |
| "LongcatFlashNgramForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_longcat_ngram.LongcatFlashNgramConfig", |
| "AutoModel": "modeling_longcat_ngram.LongcatFlashNgramModel", |
| "AutoModelForCausalLM": "modeling_longcat_ngram.LongcatFlashNgramForCausalLM" |
| }, |
| "bos_token_id": 1, |
| "disable_quant_module": [], |
| "emb_neighbor_num": 4, |
| "emb_split_num": 4, |
| "eos_token_id": 2, |
| "expert_ffn_hidden_size": 1024, |
| "ffn_hidden_size": 6144, |
| "hidden_size": 3072, |
| "kv_lora_rank": 512, |
| "max_position_embeddings": 327680, |
| "mla_scale_kv_lora": true, |
| "mla_scale_q_lora": true, |
| "moe_topk": 12, |
| "n_routed_experts": 256, |
| "ngram_vocab_size_ratio": 78, |
| "num_attention_heads": 32, |
| "num_layers": 14, |
| "q_lora_rank": 1536, |
| "qk_nope_head_dim": 128, |
| "qk_rope_head_dim": 64, |
| "quantization_config": { |
| "activation_scheme": "dynamic", |
| "fmt": "e4m3", |
| "ignored_layers": [ |
| "lm_head", |
| "model.embed_tokens", |
| "model.layers.0.input_layernorm.0", |
| "model.layers.0.input_layernorm.1", |
| "model.layers.0.mlp.router.classifier", |
| "model.layers.0.mlp.router.e_score_correction_bias", |
| "model.layers.0.post_attention_layernorm.0", |
| "model.layers.0.post_attention_layernorm.1", |
| "model.layers.0.self_attn.0.kv_a_layernorm", |
| "model.layers.0.self_attn.0.q_a_layernorm", |
| "model.layers.0.self_attn.1.kv_a_layernorm", |
| "model.layers.0.self_attn.1.q_a_layernorm", |
| "model.layers.1.input_layernorm.0", |
| "model.layers.1.input_layernorm.1", |
| "model.layers.1.mlp.router.classifier", |
| "model.layers.1.mlp.router.e_score_correction_bias", |
| "model.layers.1.post_attention_layernorm.0", |
| "model.layers.1.post_attention_layernorm.1", |
| "model.layers.1.self_attn.0.kv_a_layernorm", |
| "model.layers.1.self_attn.0.q_a_layernorm", |
| "model.layers.1.self_attn.1.kv_a_layernorm", |
| "model.layers.1.self_attn.1.q_a_layernorm", |
| "model.layers.10.input_layernorm.0", |
| "model.layers.10.input_layernorm.1", |
| "model.layers.10.mlp.router.classifier", |
| "model.layers.10.mlp.router.e_score_correction_bias", |
| "model.layers.10.post_attention_layernorm.0", |
| "model.layers.10.post_attention_layernorm.1", |
| "model.layers.10.self_attn.0.kv_a_layernorm", |
| "model.layers.10.self_attn.0.q_a_layernorm", |
| "model.layers.10.self_attn.1.kv_a_layernorm", |
| "model.layers.10.self_attn.1.q_a_layernorm", |
| "model.layers.11.input_layernorm.0", |
| "model.layers.11.input_layernorm.1", |
| "model.layers.11.mlp.router.classifier", |
| "model.layers.11.mlp.router.e_score_correction_bias", |
| "model.layers.11.post_attention_layernorm.0", |
| "model.layers.11.post_attention_layernorm.1", |
| "model.layers.11.self_attn.0.kv_a_layernorm", |
| "model.layers.11.self_attn.0.q_a_layernorm", |
| "model.layers.11.self_attn.1.kv_a_layernorm", |
| "model.layers.11.self_attn.1.q_a_layernorm", |
| "model.layers.12.input_layernorm.0", |
| "model.layers.12.input_layernorm.1", |
| "model.layers.12.mlp.router.classifier", |
| "model.layers.12.mlp.router.e_score_correction_bias", |
| "model.layers.12.post_attention_layernorm.0", |
| "model.layers.12.post_attention_layernorm.1", |
| "model.layers.12.self_attn.0.kv_a_layernorm", |
| "model.layers.12.self_attn.0.q_a_layernorm", |
| "model.layers.12.self_attn.1.kv_a_layernorm", |
| "model.layers.12.self_attn.1.q_a_layernorm", |
| "model.layers.13.input_layernorm.0", |
| "model.layers.13.input_layernorm.1", |
| "model.layers.13.mlp.router.classifier", |
| "model.layers.13.mlp.router.e_score_correction_bias", |
| "model.layers.13.post_attention_layernorm.0", |
| "model.layers.13.post_attention_layernorm.1", |
| "model.layers.13.self_attn.0.kv_a_layernorm", |
| "model.layers.13.self_attn.0.q_a_layernorm", |
| "model.layers.13.self_attn.1.kv_a_layernorm", |
| "model.layers.13.self_attn.1.q_a_layernorm", |
| "model.layers.2.input_layernorm.0", |
| "model.layers.2.input_layernorm.1", |
| "model.layers.2.mlp.router.classifier", |
| "model.layers.2.mlp.router.e_score_correction_bias", |
| "model.layers.2.post_attention_layernorm.0", |
| "model.layers.2.post_attention_layernorm.1", |
| "model.layers.2.self_attn.0.kv_a_layernorm", |
| "model.layers.2.self_attn.0.q_a_layernorm", |
| "model.layers.2.self_attn.1.kv_a_layernorm", |
| "model.layers.2.self_attn.1.q_a_layernorm", |
| "model.layers.3.input_layernorm.0", |
| "model.layers.3.input_layernorm.1", |
| "model.layers.3.mlp.router.classifier", |
| "model.layers.3.mlp.router.e_score_correction_bias", |
| "model.layers.3.post_attention_layernorm.0", |
| "model.layers.3.post_attention_layernorm.1", |
| "model.layers.3.self_attn.0.kv_a_layernorm", |
| "model.layers.3.self_attn.0.q_a_layernorm", |
| "model.layers.3.self_attn.1.kv_a_layernorm", |
| "model.layers.3.self_attn.1.q_a_layernorm", |
| "model.layers.4.input_layernorm.0", |
| "model.layers.4.input_layernorm.1", |
| "model.layers.4.mlp.router.classifier", |
| "model.layers.4.mlp.router.e_score_correction_bias", |
| "model.layers.4.post_attention_layernorm.0", |
| "model.layers.4.post_attention_layernorm.1", |
| "model.layers.4.self_attn.0.kv_a_layernorm", |
| "model.layers.4.self_attn.0.q_a_layernorm", |
| "model.layers.4.self_attn.1.kv_a_layernorm", |
| "model.layers.4.self_attn.1.q_a_layernorm", |
| "model.layers.5.input_layernorm.0", |
| "model.layers.5.input_layernorm.1", |
| "model.layers.5.mlp.router.classifier", |
| "model.layers.5.mlp.router.e_score_correction_bias", |
| "model.layers.5.post_attention_layernorm.0", |
| "model.layers.5.post_attention_layernorm.1", |
| "model.layers.5.self_attn.0.kv_a_layernorm", |
| "model.layers.5.self_attn.0.q_a_layernorm", |
| "model.layers.5.self_attn.1.kv_a_layernorm", |
| "model.layers.5.self_attn.1.q_a_layernorm", |
| "model.layers.6.input_layernorm.0", |
| "model.layers.6.input_layernorm.1", |
| "model.layers.6.mlp.router.classifier", |
| "model.layers.6.mlp.router.e_score_correction_bias", |
| "model.layers.6.post_attention_layernorm.0", |
| "model.layers.6.post_attention_layernorm.1", |
| "model.layers.6.self_attn.0.kv_a_layernorm", |
| "model.layers.6.self_attn.0.q_a_layernorm", |
| "model.layers.6.self_attn.1.kv_a_layernorm", |
| "model.layers.6.self_attn.1.q_a_layernorm", |
| "model.layers.7.input_layernorm.0", |
| "model.layers.7.input_layernorm.1", |
| "model.layers.7.mlp.router.classifier", |
| "model.layers.7.mlp.router.e_score_correction_bias", |
| "model.layers.7.post_attention_layernorm.0", |
| "model.layers.7.post_attention_layernorm.1", |
| "model.layers.7.self_attn.0.kv_a_layernorm", |
| "model.layers.7.self_attn.0.q_a_layernorm", |
| "model.layers.7.self_attn.1.kv_a_layernorm", |
| "model.layers.7.self_attn.1.q_a_layernorm", |
| "model.layers.8.input_layernorm.0", |
| "model.layers.8.input_layernorm.1", |
| "model.layers.8.mlp.router.classifier", |
| "model.layers.8.mlp.router.e_score_correction_bias", |
| "model.layers.8.post_attention_layernorm.0", |
| "model.layers.8.post_attention_layernorm.1", |
| "model.layers.8.self_attn.0.kv_a_layernorm", |
| "model.layers.8.self_attn.0.q_a_layernorm", |
| "model.layers.8.self_attn.1.kv_a_layernorm", |
| "model.layers.8.self_attn.1.q_a_layernorm", |
| "model.layers.9.input_layernorm.0", |
| "model.layers.9.input_layernorm.1", |
| "model.layers.9.mlp.router.classifier", |
| "model.layers.9.mlp.router.e_score_correction_bias", |
| "model.layers.9.post_attention_layernorm.0", |
| "model.layers.9.post_attention_layernorm.1", |
| "model.layers.9.self_attn.0.kv_a_layernorm", |
| "model.layers.9.self_attn.0.q_a_layernorm", |
| "model.layers.9.self_attn.1.kv_a_layernorm", |
| "model.layers.9.self_attn.1.q_a_layernorm", |
| "model.mtp.embed_tokens", |
| "model.mtp.layers.0.enorm.m", |
| "model.mtp.layers.0.hnorm.m", |
| "model.mtp.layers.0.input_layernorm", |
| "model.mtp.layers.0.post_attention_layernorm", |
| "model.mtp.layers.0.self_attn.kv_a_layernorm", |
| "model.mtp.layers.0.self_attn.q_a_layernorm", |
| "model.mtp.norm", |
| "model.ngram_embeddings.embedders.0", |
| "model.ngram_embeddings.embedders.1", |
| "model.ngram_embeddings.embedders.10", |
| "model.ngram_embeddings.embedders.11", |
| "model.ngram_embeddings.embedders.2", |
| "model.ngram_embeddings.embedders.3", |
| "model.ngram_embeddings.embedders.4", |
| "model.ngram_embeddings.embedders.5", |
| "model.ngram_embeddings.embedders.6", |
| "model.ngram_embeddings.embedders.7", |
| "model.ngram_embeddings.embedders.8", |
| "model.ngram_embeddings.embedders.9", |
| "model.ngram_embeddings.post_projs.0", |
| "model.ngram_embeddings.post_projs.1", |
| "model.ngram_embeddings.post_projs.10", |
| "model.ngram_embeddings.post_projs.11", |
| "model.ngram_embeddings.post_projs.2", |
| "model.ngram_embeddings.post_projs.3", |
| "model.ngram_embeddings.post_projs.4", |
| "model.ngram_embeddings.post_projs.5", |
| "model.ngram_embeddings.post_projs.6", |
| "model.ngram_embeddings.post_projs.7", |
| "model.ngram_embeddings.post_projs.8", |
| "model.ngram_embeddings.post_projs.9", |
| "model.norm" |
| ], |
| "quant_method": "fp8", |
| "weight_block_size": [ |
| 128, |
| 128 |
| ] |
| }, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": { |
| "beta_fast": 32, |
| "beta_slow": 1, |
| "factor": 10, |
| "mscale": 1, |
| "mscale_all_dim": 1, |
| "original_max_position_embeddings": 32768, |
| "rope_type": "yarn" |
| }, |
| "rope_theta": 5000000.0, |
| "routed_scaling_factor": 6.0, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.57.6", |
| "use_cache": true, |
| "v_head_dim": 128, |
| "vocab_size": 131072, |
| "zero_expert_num": 128, |
| "zero_expert_type": "identity" |
| } |
