CoolFace
Modelpublic

Kompaktion/action

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face
0likes7downloads
config.json113 linesDownload Raw Back to root
1{2    "architectures": [3        "Qwen3_5ForConditionalGeneration"4    ],5    "torch_dtype": "bfloat16",6    "eos_token_id": 248046,7    "hidden_size": 4096,8    "image_token_id": 248056,9    "model_name": "ornith-ai/Ornith-1.0-9B",10    "model_type": "qwen3_5",11    "pad_token_id": 248044,12    "text_config": {13        "attention_bias": false,14        "attention_dropout": 0.0,15        "attn_output_gate": true,16        "bos_token_id": null,17        "torch_dtype": "bfloat16",18        "eos_token_id": 248044,19        "full_attention_interval": 4,20        "head_dim": 256,21        "hidden_act": "silu",22        "hidden_size": 4096,23        "initializer_range": 0.02,24        "intermediate_size": 12288,25        "layer_types": [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        ],59        "linear_conv_kernel_dim": 4,60        "linear_key_head_dim": 128,61        "linear_num_key_heads": 16,62        "linear_num_value_heads": 32,63        "linear_value_head_dim": 128,64        "mamba_ssm_dtype": "float32",65        "max_position_embeddings": 262144,66        "mlp_only_layers": [],67        "model_type": "qwen3_5_text",68        "mtp_num_hidden_layers": 1,69        "mtp_use_dedicated_embeddings": false,70        "num_attention_heads": 16,71        "num_hidden_layers": 32,72        "num_key_value_heads": 4,73        "pad_token_id": 248044,74        "partial_rotary_factor": 0.25,75        "rms_norm_eps": 1e-06,76        "rope_parameters": {77            "mrope_interleaved": true,78            "mrope_section": [79                11,80                11,81                1082            ],83            "partial_rotary_factor": 0.25,84            "rope_theta": 10000000,85            "rope_type": "default"86        },87        "tie_word_embeddings": false,88        "use_cache": false,89        "vocab_size": 24832090    },91    "tie_word_embeddings": false,92    "unsloth_version": "2026.8.4",93    "video_token_id": 248057,94    "vision_config": {95        "deepstack_visual_indexes": [],96        "depth": 27,97        "torch_dtype": "bfloat16",98        "hidden_act": "gelu_pytorch_tanh",99        "hidden_size": 1152,100        "in_channels": 3,101        "initializer_range": 0.02,102        "intermediate_size": 4304,103        "model_type": "qwen3_5_vision",104        "num_heads": 16,105        "num_position_embeddings": 2304,106        "out_hidden_size": 4096,107        "patch_size": 16,108        "spatial_merge_size": 2,109        "temporal_patch_size": 2110    },111    "vision_end_token_id": 248054,112    "vision_start_token_id": 248053113}