| { |
| "architectures": [ |
| "Qwen3NextForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0, |
| "bos_token_id": 151643, |
| "decoder_sparse_step": 1, |
| "dtype": "bfloat16", |
| "eos_token_id": 151645, |
| "full_attention_interval": 4, |
| "head_dim": 256, |
| "hidden_act": "silu", |
| "hidden_size": 2048, |
| "initializer_range": 0.02, |
| "intermediate_size": 5120, |
| "layer_types": [ |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention" |
| ], |
| "linear_conv_kernel_dim": 4, |
| "linear_key_head_dim": 128, |
| "linear_num_key_heads": 16, |
| "linear_num_value_heads": 32, |
| "linear_value_head_dim": 128, |
| "max_position_embeddings": 262144, |
| "mlp_only_layers": [], |
| "model_type": "qwen3_next", |
| "moe_intermediate_size": 512, |
| "norm_topk_prob": true, |
| "num_attention_heads": 16, |
| "num_experts": 512, |
| "num_experts_per_tok": 10, |
| "num_hidden_layers": 48, |
| "num_key_value_heads": 2, |
| "output_router_logits": false, |
| "pad_token_id": null, |
| "partial_rotary_factor": 0.25, |
| "quantization_config": { |
| "bits": 4, |
| "checkpoint_format": "gptq", |
| "desc_act": false, |
| "dynamic": { |
| "-:.*linear_attn\\.in_proj_qkvz": {}, |
| "-:.*linear_attn\\.out_proj": {}, |
| "-:.*shared_expert\\.down_proj": {}, |
| "-:.*shared_expert\\.gate_proj": {}, |
| "-:.*shared_expert\\.up_proj": {} |
| }, |
| "format": "gptq", |
| "group_size": 32, |
| "lm_head": false, |
| "meta": { |
| "act_group_aware": true, |
| "auto_forward_data_parallel": true, |
| "damp_auto_increment": 0.01, |
| "damp_percent": 0.05, |
| "failsafe": { |
| "smooth": { |
| "group_size_threshold": 128, |
| "k": 2.75, |
| "type": "mad" |
| }, |
| "strategy": "rtn", |
| "threshold": "0.5%" |
| }, |
| "gc_mode": "interval", |
| "gptaq": null, |
| "hessian": { |
| "chunk_bytes": null, |
| "chunk_size": null, |
| "staging_dtype": "float32" |
| }, |
| "mock_quantization": false, |
| "mse": 0.0, |
| "offload_to_disk": false, |
| "offload_to_disk_path": null, |
| "pack_impl": "cpu", |
| "quantizer": [ |
| "gptqmodel:5.7.0" |
| ], |
| "static_groups": false, |
| "true_sequential": true, |
| "uri": "https://github.com/modelcloud/gptqmodel", |
| "vram_strategy": "exclusive", |
| "wait_for_submodule_finalizers": false |
| }, |
| "pack_dtype": "int32", |
| "quant_method": "gptq", |
| "sym": true |
| }, |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "partial_rotary_factor": 0.25, |
| "rope_theta": 5000000, |
| "rope_type": "default" |
| }, |
| "router_aux_loss_coef": 0.001, |
| "shared_expert_intermediate_size": 512, |
| "tie_word_embeddings": false, |
| "transformers_version": "5.0.0", |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 151936 |
| } |
|
|
