CoolFace
Modelpublic

cfli/A-base

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face
0likes36downloads
config.json123 linesDownload Raw Back to root
1{2    "architectures": [3        "Qwen3_5MoeForConditionalGeneration"4    ],5    "image_token_id": 248056,6    "model_type": "qwen3_5_moe",7    "text_config": {8        "attention_bias": false,9        "attention_dropout": 0.0,10        "attn_output_gate": true,11        "dtype": "bfloat16",12        "eos_token_id": 248044,13        "full_attention_interval": 4,14        "head_dim": 256,15        "hidden_act": "silu",16        "hidden_size": 3072,17        "initializer_range": 0.02,18        "layer_types": [19            "linear_attention",20            "linear_attention",21            "linear_attention",22            "full_attention",23            "linear_attention",24            "linear_attention",25            "linear_attention",26            "full_attention",27            "linear_attention",28            "linear_attention",29            "linear_attention",30            "full_attention",31            "linear_attention",32            "linear_attention",33            "linear_attention",34            "full_attention",35            "linear_attention",36            "linear_attention",37            "linear_attention",38            "full_attention",39            "linear_attention",40            "linear_attention",41            "linear_attention",42            "full_attention",43            "linear_attention",44            "linear_attention",45            "linear_attention",46            "full_attention",47            "linear_attention",48            "linear_attention",49            "linear_attention",50            "full_attention",51            "linear_attention",52            "linear_attention",53            "linear_attention",54            "full_attention",55            "linear_attention",56            "linear_attention",57            "linear_attention",58            "full_attention",59            "linear_attention",60            "linear_attention",61            "linear_attention",62            "full_attention",63            "linear_attention",64            "linear_attention",65            "linear_attention",66            "full_attention"67        ],68        "linear_conv_kernel_dim": 4,69        "linear_key_head_dim": 128,70        "linear_num_key_heads": 16,71        "linear_num_value_heads": 64,72        "linear_value_head_dim": 128,73        "max_position_embeddings": 262144,74        "mlp_only_layers": [],75        "model_type": "qwen3_5_moe_text",76        "moe_intermediate_size": 1024,77        "mtp_num_hidden_layers": 1,78        "mtp_use_dedicated_embeddings": false,79        "num_attention_heads": 32,80        "num_experts": 256,81        "num_experts_per_tok": 8,82        "num_hidden_layers": 48,83        "num_key_value_heads": 2,84        "rms_norm_eps": 1e-06,85        "router_aux_loss_coef": 0.001,86        "shared_expert_intermediate_size": 1024,87        "use_cache": true,88        "vocab_size": 248320,89        "mamba_ssm_dtype": "float32",90        "rope_parameters": {91            "mrope_interleaved": true,92            "mrope_section": [93                11,94                11,95                1096            ],97            "rope_type": "default",98            "rope_theta": 10000000,99            "partial_rotary_factor": 0.25100        }101    },102    "tie_word_embeddings": false,103    "transformers_version": "4.57.0.dev0",104    "video_token_id": 248057,105    "vision_config": {106        "deepstack_visual_indexes": [],107        "depth": 27,108        "hidden_act": "gelu_pytorch_tanh",109        "hidden_size": 1152,110        "in_channels": 3,111        "initializer_range": 0.02,112        "intermediate_size": 4304,113        "model_type": "qwen3_5_moe",114        "num_heads": 16,115        "num_position_embeddings": 2304,116        "out_hidden_size": 3072,117        "patch_size": 16,118        "spatial_merge_size": 2,119        "temporal_patch_size": 2120    },121    "vision_end_token_id": 248054,122    "vision_start_token_id": 248053123}