| { |
| "architectures": [ |
| "Qwen3_5MoeForConditionalGeneration" |
| ], |
| "dtype": "bfloat16", |
| "hidden_size": 2048, |
| "image_token_id": 248056, |
| "model_type": "qwen3_5_moe", |
| "text_config": { |
| "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": 2048, |
| "initializer_range": 0.02, |
| "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_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_moe_text", |
| "moe_intermediate_size": 512, |
| "mtp_num_hidden_layers": 1, |
| "mtp_use_dedicated_embeddings": false, |
| "num_attention_heads": 16, |
| "num_experts": 256, |
| "num_experts_per_tok": 8, |
| "num_hidden_layers": 40, |
| "num_key_value_heads": 2, |
| "output_router_logits": false, |
| "pad_token_id": null, |
| "partial_rotary_factor": 0.25, |
| "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" |
| }, |
| "router_aux_loss_coef": 0.001, |
| "shared_expert_intermediate_size": 512, |
| "tie_word_embeddings": false, |
| "use_cache": true, |
| "vocab_size": 248320 |
| }, |
| "tie_word_embeddings": false, |
| "transformers_version": "5.2.0", |
| "video_token_id": 248057, |
| "vision_config": { |
| "deepstack_visual_indexes": [], |
| "depth": 27, |
| "dtype": "bfloat16", |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_size": 1152, |
| "in_channels": 3, |
| "initializer_range": 0.02, |
| "intermediate_size": 4304, |
| "model_type": "qwen3_5_moe", |
| "num_heads": 16, |
| "num_position_embeddings": 2304, |
| "out_hidden_size": 2048, |
| "patch_size": 16, |
| "spatial_merge_size": 2, |
| "temporal_patch_size": 2 |
| }, |
| "vision_end_token_id": 248054, |
| "vision_start_token_id": 248053, |
| "quantization_config": { |
| "quant_method": "compressed-tensors", |
| "format": "pack-quantized", |
| "quantization_status": "compressed", |
| "ignore": [ |
| "re:.*layers[.]0[.](?:self_attn|linear_attn|mlp[.]shared_expert)[.].*", |
| "re:.*layers[.][0-9]+[.]mlp[.]gate$", |
| "re:.*layers[.][0-9]+[.]mlp[.]shared_expert_gate$", |
| "re:.*layers[.][0-9]+[.]linear_attn[.](?:in_proj_a|in_proj_b|in_proj_ba|conv1d)$", |
| "re:.*layers[.][0-9]+[.]self_attn[.](?:q_norm|k_norm)$", |
| "re:.*embed_tokens$", |
| "lm_head", |
| "re:.*lm_head$", |
| "re:.*visual[.].*" |
| ], |
| "config_groups": { |
| "w4a16_experts": { |
| "targets": [ |
| "re:.*layers[.][0-9]+[.]mlp[.]experts[.][0-9]+[.](?:gate_proj|up_proj|down_proj)$" |
| ], |
| "input_activations": null, |
| "output_activations": null, |
| "weights": { |
| "num_bits": 4, |
| "type": "int", |
| "symmetric": true, |
| "strategy": "group", |
| "group_size": 128, |
| "dynamic": false, |
| "actorder": null, |
| "observer": "minmax" |
| } |
| }, |
| "w8a16_linears": { |
| "targets": [ |
| "re:.*layers[.](?:[1-9][0-9]*)[.](?:self_attn[.](?:q_proj|k_proj|v_proj|o_proj)|linear_attn[.](?:in_proj_qkv|in_proj_z|out_proj)|mlp[.]shared_expert[.](?:gate_proj|up_proj|down_proj))$" |
| ], |
| "input_activations": null, |
| "output_activations": null, |
| "weights": { |
| "num_bits": 8, |
| "type": "int", |
| "symmetric": true, |
| "strategy": "group", |
| "group_size": 128, |
| "dynamic": false, |
| "actorder": null, |
| "observer": "minmax" |
| } |
| } |
| }, |
| "packed_modules_mapping": { |
| "qkv_proj": [ |
| "q_proj", |
| "k_proj", |
| "v_proj" |
| ], |
| "gate_up_proj": [ |
| "gate_proj", |
| "up_proj" |
| ], |
| "in_proj_qkvz": [ |
| "in_proj_qkv", |
| "in_proj_z" |
| ], |
| "in_proj_ba": [ |
| "in_proj_a", |
| "in_proj_b" |
| ] |
| }, |
| "kv_cache_scheme": null, |
| "global_compression_ratio": null, |
| "sparsity_config": {} |
| } |
| } |
