| { |
| "architectures": [ |
| "Qwen3_5ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attn_output_gate": true, |
| "bos_token_id": null, |
| "dtype": "bfloat16", |
| "eos_token_id": 248044, |
| "full_attention_interval": 4, |
| "head_dim": 256, |
| "hidden_act": "silu", |
| "hidden_size": 2560, |
| "initializer_range": 0.02, |
| "intermediate_size": 9216, |
| "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_conv_kernel_dim": 4, |
| "linear_key_head_dim": 128, |
| "linear_num_key_heads": 16, |
| "linear_num_value_heads": 32, |
| "linear_value_head_dim": 128, |
| "mamba_ssm_dtype": "float32", |
| "max_position_embeddings": 262144, |
| "mlp_only_layers": [], |
| "model_type": "qwen3_5_text", |
| "mtp_num_hidden_layers": 1, |
| "mtp_use_dedicated_embeddings": false, |
| "num_attention_heads": 16, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 4, |
| "pad_token_id": null, |
| "partial_rotary_factor": 0.25, |
| "quantization_config": { |
| "autoround_version": "0.14.0", |
| "bits": 4, |
| "block_name_to_quantize": [ |
| "model.language_model.layers", |
| "model.visual.blocks", |
| "mtp.layers" |
| ], |
| "data_type": "int", |
| "enable_quanted_input": false, |
| "group_size": 128, |
| "low_gpu_mem_usage": true, |
| "packing_format": "auto_round:auto_gptq", |
| "quant_method": "auto-round", |
| "sym": true, |
| "extra_config": { |
| "model.visual.merger.linear_fc1": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "mtp.fc": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.visual.merger.linear_fc2": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.visual.pos_embed": { |
| "bits": 16, |
| "data_type": "fp" |
| } |
| } |
| }, |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "mrope_interleaved": true, |
| "mrope_section": [ |
| 11, |
| 11, |
| 10 |
| ], |
| "partial_rotary_factor": 0.25, |
| "rope_theta": 10000000, |
| "rope_type": "default" |
| }, |
| "tie_word_embeddings": true, |
| "transformers_version": "5.9.0", |
| "use_cache": true, |
| "vocab_size": 248320 |
| } |
