CoolFace
Modelpublic

abacusai/Smaug-Mini

sourceHugging Faceapache-2.0updated 15d agoView on Hugging Face
8likes18kdownloads
config.json140 linesDownload Raw Back to root
1{2    "architectures": [3        "Qwen3_5ForConditionalGeneration"4    ],5    "image_token_id": 248056,6    "language_model_only": false,7    "model_type": "qwen3_5",8    "text_config": {9        "attention_bias": false,10        "attention_dropout": 0.0,11        "attn_output_gate": true,12        "bos_token_id": 248044,13        "dtype": "bfloat16",14        "eos_token_id": 248044,15        "full_attention_interval": 4,16        "head_dim": 256,17        "hidden_act": "silu",18        "hidden_size": 5120,19        "initializer_range": 0.02,20        "intermediate_size": 17408,21        "layer_types": [22            "linear_attention",23            "linear_attention",24            "linear_attention",25            "full_attention",26            "linear_attention",27            "linear_attention",28            "linear_attention",29            "full_attention",30            "linear_attention",31            "linear_attention",32            "linear_attention",33            "full_attention",34            "linear_attention",35            "linear_attention",36            "linear_attention",37            "full_attention",38            "linear_attention",39            "linear_attention",40            "linear_attention",41            "full_attention",42            "linear_attention",43            "linear_attention",44            "linear_attention",45            "full_attention",46            "linear_attention",47            "linear_attention",48            "linear_attention",49            "full_attention",50            "linear_attention",51            "linear_attention",52            "linear_attention",53            "full_attention",54            "linear_attention",55            "linear_attention",56            "linear_attention",57            "full_attention",58            "linear_attention",59            "linear_attention",60            "linear_attention",61            "full_attention",62            "linear_attention",63            "linear_attention",64            "linear_attention",65            "full_attention",66            "linear_attention",67            "linear_attention",68            "linear_attention",69            "full_attention",70            "linear_attention",71            "linear_attention",72            "linear_attention",73            "full_attention",74            "linear_attention",75            "linear_attention",76            "linear_attention",77            "full_attention",78            "linear_attention",79            "linear_attention",80            "linear_attention",81            "full_attention",82            "linear_attention",83            "linear_attention",84            "linear_attention",85            "full_attention"86        ],87        "linear_conv_kernel_dim": 4,88        "linear_key_head_dim": 128,89        "linear_num_key_heads": 16,90        "linear_num_value_heads": 48,91        "linear_value_head_dim": 128,92        "mamba_ssm_dtype": "float32",93        "max_position_embeddings": 262144,94        "model_type": "qwen3_5_text",95        "mtp_num_hidden_layers": 1,96        "mtp_use_dedicated_embeddings": false,97        "num_attention_heads": 24,98        "num_hidden_layers": 64,99        "num_key_value_heads": 4,100        "output_gate_type": "swish",101        "pad_token_id": null,102        "partial_rotary_factor": 0.25,103        "rms_norm_eps": 1e-06,104        "rope_parameters": {105            "mrope_interleaved": true,106            "mrope_section": [107                11,108                11,109                10110            ],111            "partial_rotary_factor": 0.25,112            "rope_theta": 10000000,113            "rope_type": "default"114        },115        "tie_word_embeddings": false,116        "use_cache": true,117        "vocab_size": 248320118    },119    "tie_word_embeddings": false,120    "transformers_version": "5.8.0.dev0",121    "video_token_id": 248057,122    "vision_config": {123        "deepstack_visual_indexes": [],124        "depth": 27,125        "hidden_act": "gelu_pytorch_tanh",126        "hidden_size": 1152,127        "in_channels": 3,128        "initializer_range": 0.02,129        "intermediate_size": 4304,130        "model_type": "qwen3_5",131        "num_heads": 16,132        "num_position_embeddings": 2304,133        "out_hidden_size": 5120,134        "patch_size": 16,135        "spatial_merge_size": 2,136        "temporal_patch_size": 2137    },138    "vision_end_token_id": 248054,139    "vision_start_token_id": 248053140}