| { | |
| "architectures": [ | |
| "Qwen3MoeForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "decoder_sparse_step": 1, | |
| "eos_token_id": 151645, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 6144, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 262144, | |
| "max_window_layers": 28, | |
| "mlp_only_layers": [], | |
| "model_type": "qwen3_moe", | |
| "moe_intermediate_size": 2560, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 96, | |
| "num_experts": 160, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 62, | |
| "num_key_value_heads": 8, | |
| "output_router_logits": false, | |
| "qkv_bias": false, | |
| "quantization_config": { | |
| "activation_scheme": "dynamic", | |
| "modules_to_not_convert": [ | |
| "lm_head", | |
| "model.layers.0.input_layernorm", | |
| "model.layers.0.mlp.gate", | |
| "model.layers.0.post_attention_layernorm", | |
| "model.layers.1.input_layernorm", | |
| "model.layers.1.mlp.gate", | |
| "model.layers.1.post_attention_layernorm", | |
| "model.layers.2.input_layernorm", | |
| "model.layers.2.mlp.gate", | |
| "model.layers.2.post_attention_layernorm", | |
| "model.layers.3.input_layernorm", | |
| "model.layers.3.mlp.gate", | |
| "model.layers.3.post_attention_layernorm", | |
| "model.layers.4.input_layernorm", | |
| "model.layers.4.mlp.gate", | |
| "model.layers.4.post_attention_layernorm", | |
| "model.layers.5.input_layernorm", | |
| "model.layers.5.mlp.gate", | |
| "model.layers.5.post_attention_layernorm", | |
| "model.layers.6.input_layernorm", | |
| "model.layers.6.mlp.gate", | |
| "model.layers.6.post_attention_layernorm", | |
| "model.layers.7.input_layernorm", | |
| "model.layers.7.mlp.gate", | |
| "model.layers.7.post_attention_layernorm", | |
| "model.layers.8.input_layernorm", | |
| "model.layers.8.mlp.gate", | |
| "model.layers.8.post_attention_layernorm", | |
| "model.layers.9.input_layernorm", | |
| "model.layers.9.mlp.gate", | |
| "model.layers.9.post_attention_layernorm", | |
| "model.layers.10.input_layernorm", | |
| "model.layers.10.mlp.gate", | |
| "model.layers.10.post_attention_layernorm", | |
| "model.layers.11.input_layernorm", | |
| "model.layers.11.mlp.gate", | |
| "model.layers.11.post_attention_layernorm", | |
| "model.layers.12.input_layernorm", | |
| "model.layers.12.mlp.gate", | |
| "model.layers.12.post_attention_layernorm", | |
| "model.layers.13.input_layernorm", | |
| "model.layers.13.mlp.gate", | |
| "model.layers.13.post_attention_layernorm", | |
| "model.layers.14.input_layernorm", | |
| "model.layers.14.mlp.gate", | |
| "model.layers.14.post_attention_layernorm", | |
| "model.layers.15.input_layernorm", | |
| "model.layers.15.mlp.gate", | |
| "model.layers.15.post_attention_layernorm", | |
| "model.layers.16.input_layernorm", | |
| "model.layers.16.mlp.gate", | |
| "model.layers.16.post_attention_layernorm", | |
| "model.layers.17.input_layernorm", | |
| "model.layers.17.mlp.gate", | |
| "model.layers.17.post_attention_layernorm", | |
| "model.layers.18.input_layernorm", | |
| "model.layers.18.mlp.gate", | |
| "model.layers.18.post_attention_layernorm", | |
| "model.layers.19.input_layernorm", | |
| "model.layers.19.mlp.gate", | |
| "model.layers.19.post_attention_layernorm", | |
| "model.layers.20.input_layernorm", | |
| "model.layers.20.mlp.gate", | |
| "model.layers.20.post_attention_layernorm", | |
| "model.layers.21.input_layernorm", | |
| "model.layers.21.mlp.gate", | |
| "model.layers.21.post_attention_layernorm", | |
| "model.layers.22.input_layernorm", | |
| "model.layers.22.mlp.gate", | |
| "model.layers.22.post_attention_layernorm", | |
| "model.layers.23.input_layernorm", | |
| "model.layers.23.mlp.gate", | |
| "model.layers.23.post_attention_layernorm", | |
| "model.layers.24.input_layernorm", | |
| "model.layers.24.mlp.gate", | |
| "model.layers.24.post_attention_layernorm", | |
| "model.layers.25.input_layernorm", | |
| "model.layers.25.mlp.gate", | |
| "model.layers.25.post_attention_layernorm", | |
| "model.layers.26.input_layernorm", | |
| "model.layers.26.mlp.gate", | |
| "model.layers.26.post_attention_layernorm", | |
| "model.layers.27.input_layernorm", | |
| "model.layers.27.mlp.gate", | |
| "model.layers.27.post_attention_layernorm", | |
| "model.layers.28.input_layernorm", | |
| "model.layers.28.mlp.gate", | |
| "model.layers.28.post_attention_layernorm", | |
| "model.layers.29.input_layernorm", | |
| "model.layers.29.mlp.gate", | |
| "model.layers.29.post_attention_layernorm", | |
| "model.layers.30.input_layernorm", | |
| "model.layers.30.mlp.gate", | |
| "model.layers.30.post_attention_layernorm", | |
| "model.layers.31.input_layernorm", | |
| "model.layers.31.mlp.gate", | |
| "model.layers.31.post_attention_layernorm", | |
| "model.layers.32.input_layernorm", | |
| "model.layers.32.mlp.gate", | |
| "model.layers.32.post_attention_layernorm", | |
| "model.layers.33.input_layernorm", | |
| "model.layers.33.mlp.gate", | |
| "model.layers.33.post_attention_layernorm", | |
| "model.layers.34.input_layernorm", | |
| "model.layers.34.mlp.gate", | |
| "model.layers.34.post_attention_layernorm", | |
| "model.layers.35.input_layernorm", | |
| "model.layers.35.mlp.gate", | |
| "model.layers.35.post_attention_layernorm", | |
| "model.layers.36.input_layernorm", | |
| "model.layers.36.mlp.gate", | |
| "model.layers.36.post_attention_layernorm", | |
| "model.layers.37.input_layernorm", | |
| "model.layers.37.mlp.gate", | |
| "model.layers.37.post_attention_layernorm", | |
| "model.layers.38.input_layernorm", | |
| "model.layers.38.mlp.gate", | |
| "model.layers.38.post_attention_layernorm", | |
| "model.layers.39.input_layernorm", | |
| "model.layers.39.mlp.gate", | |
| "model.layers.39.post_attention_layernorm", | |
| "model.layers.40.input_layernorm", | |
| "model.layers.40.mlp.gate", | |
| "model.layers.40.post_attention_layernorm", | |
| "model.layers.41.input_layernorm", | |
| "model.layers.41.mlp.gate", | |
| "model.layers.41.post_attention_layernorm", | |
| "model.layers.42.input_layernorm", | |
| "model.layers.42.mlp.gate", | |
| "model.layers.42.post_attention_layernorm", | |
| "model.layers.43.input_layernorm", | |
| "model.layers.43.mlp.gate", | |
| "model.layers.43.post_attention_layernorm", | |
| "model.layers.44.input_layernorm", | |
| "model.layers.44.mlp.gate", | |
| "model.layers.44.post_attention_layernorm", | |
| "model.layers.45.input_layernorm", | |
| "model.layers.45.mlp.gate", | |
| "model.layers.45.post_attention_layernorm", | |
| "model.layers.46.input_layernorm", | |
| "model.layers.46.mlp.gate", | |
| "model.layers.46.post_attention_layernorm", | |
| "model.layers.47.input_layernorm", | |
| "model.layers.47.mlp.gate", | |
| "model.layers.47.post_attention_layernorm", | |
| "model.layers.48.input_layernorm", | |
| "model.layers.48.mlp.gate", | |
| "model.layers.48.post_attention_layernorm", | |
| "model.layers.49.input_layernorm", | |
| "model.layers.49.mlp.gate", | |
| "model.layers.49.post_attention_layernorm", | |
| "model.layers.50.input_layernorm", | |
| "model.layers.50.mlp.gate", | |
| "model.layers.50.post_attention_layernorm", | |
| "model.layers.51.input_layernorm", | |
| "model.layers.51.mlp.gate", | |
| "model.layers.51.post_attention_layernorm", | |
| "model.layers.52.input_layernorm", | |
| "model.layers.52.mlp.gate", | |
| "model.layers.52.post_attention_layernorm", | |
| "model.layers.53.input_layernorm", | |
| "model.layers.53.mlp.gate", | |
| "model.layers.53.post_attention_layernorm", | |
| "model.layers.54.input_layernorm", | |
| "model.layers.54.mlp.gate", | |
| "model.layers.54.post_attention_layernorm", | |
| "model.layers.55.input_layernorm", | |
| "model.layers.55.mlp.gate", | |
| "model.layers.55.post_attention_layernorm", | |
| "model.layers.56.input_layernorm", | |
| "model.layers.56.mlp.gate", | |
| "model.layers.56.post_attention_layernorm", | |
| "model.layers.57.input_layernorm", | |
| "model.layers.57.mlp.gate", | |
| "model.layers.57.post_attention_layernorm", | |
| "model.layers.58.input_layernorm", | |
| "model.layers.58.mlp.gate", | |
| "model.layers.58.post_attention_layernorm", | |
| "model.layers.59.input_layernorm", | |
| "model.layers.59.mlp.gate", | |
| "model.layers.59.post_attention_layernorm", | |
| "model.layers.60.input_layernorm", | |
| "model.layers.60.mlp.gate", | |
| "model.layers.60.post_attention_layernorm", | |
| "model.layers.61.input_layernorm", | |
| "model.layers.61.mlp.gate", | |
| "model.layers.61.post_attention_layernorm" | |
| ], | |
| "quant_method": "fp8", | |
| "weight_block_size": [ | |
| 128, | |
| 128 | |
| ] | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000000, | |
| "router_aux_loss_coef": 0.0, | |
| "shared_expert_intermediate_size": 0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.52.4", | |
| "use_cache": true, | |
| "use_qk_norm": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| } | |