CoolFace
Modelpublic

ChesterProgrammer/Qwen3.5-9B-ConsistentChat-100steps

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face
0likes4downloads
config.json113 linesDownload Raw Back to root
1{2    "architectures": [3        "Qwen3_5ForConditionalGeneration"4    ],5    "torch_dtype": "bfloat16",6    "image_token_id": 248056,7    "model_name": "unsloth/Qwen3.5-9B",8    "model_type": "qwen3_5",9    "mtp_num_hidden_layers": 1,10    "pad_token_id": 248055,11    "text_config": {12        "attention_bias": false,13        "attention_dropout": 0.0,14        "attn_output_gate": true,15        "bos_token_id": null,16        "torch_dtype": "bfloat16",17        "eos_token_id": 248044,18        "full_attention_interval": 4,19        "head_dim": 256,20        "hidden_act": "silu",21        "hidden_size": 4096,22        "initializer_range": 0.02,23        "intermediate_size": 12288,24        "layer_types": [25            "linear_attention",26            "linear_attention",27            "linear_attention",28            "full_attention",29            "linear_attention",30            "linear_attention",31            "linear_attention",32            "full_attention",33            "linear_attention",34            "linear_attention",35            "linear_attention",36            "full_attention",37            "linear_attention",38            "linear_attention",39            "linear_attention",40            "full_attention",41            "linear_attention",42            "linear_attention",43            "linear_attention",44            "full_attention",45            "linear_attention",46            "linear_attention",47            "linear_attention",48            "full_attention",49            "linear_attention",50            "linear_attention",51            "linear_attention",52            "full_attention",53            "linear_attention",54            "linear_attention",55            "linear_attention",56            "full_attention"57        ],58        "linear_conv_kernel_dim": 4,59        "linear_key_head_dim": 128,60        "linear_num_key_heads": 16,61        "linear_num_value_heads": 32,62        "linear_value_head_dim": 128,63        "mamba_ssm_dtype": "float32",64        "max_position_embeddings": 262144,65        "mlp_only_layers": [],66        "model_type": "qwen3_5_text",67        "mtp_num_hidden_layers": 1,68        "mtp_use_dedicated_embeddings": false,69        "num_attention_heads": 16,70        "num_hidden_layers": 32,71        "num_key_value_heads": 4,72        "pad_token_id": null,73        "partial_rotary_factor": 0.25,74        "rms_norm_eps": 1e-06,75        "rope_parameters": {76            "mrope_interleaved": true,77            "mrope_section": [78                11,79                11,80                1081            ],82            "partial_rotary_factor": 0.25,83            "rope_theta": 10000000,84            "rope_type": "default"85        },86        "tie_word_embeddings": false,87        "use_cache": false,88        "vocab_size": 24832089    },90    "tie_word_embeddings": false,91    "unsloth_fixed_mtp": true,92    "unsloth_version": "2026.7.3",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",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}