CoolFace
Modelpublic

Rishu11277/Qwopus3.5-9B-Coder-mlx-4Bit

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face
0likes40downloads
config.json106 linesDownload Raw Back to root
1{2    "architectures": [3        "Qwen3_5ForConditionalGeneration"4    ],5    "eos_token_id": 248046,6    "image_token_id": 248056,7    "model_name": "Jackrong/Qwopus3.5-9B-v3.5",8    "model_type": "qwen3_5",9    "pad_token_id": 248055,10    "quantization": {11        "group_size": 64,12        "bits": 4,13        "mode": "affine"14    },15    "quantization_config": {16        "group_size": 64,17        "bits": 4,18        "mode": "affine"19    },20    "text_config": {21        "attention_bias": false,22        "attention_dropout": 0.0,23        "attn_output_gate": true,24        "bos_token_id": null,25        "torch_dtype": "bfloat16",26        "eos_token_id": 248044,27        "full_attention_interval": 4,28        "head_dim": 256,29        "hidden_act": "silu",30        "hidden_size": 4096,31        "initializer_range": 0.02,32        "intermediate_size": 12288,33        "layer_types": [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        ],67        "linear_conv_kernel_dim": 4,68        "linear_key_head_dim": 128,69        "linear_num_key_heads": 16,70        "linear_num_value_heads": 32,71        "linear_value_head_dim": 128,72        "mamba_ssm_dtype": "float32",73        "max_position_embeddings": 262144,74        "mlp_only_layers": [],75        "model_type": "qwen3_5_text",76        "mtp_num_hidden_layers": 1,77        "mtp_use_dedicated_embeddings": false,78        "num_attention_heads": 16,79        "num_hidden_layers": 32,80        "num_key_value_heads": 4,81        "pad_token_id": null,82        "partial_rotary_factor": 0.25,83        "rms_norm_eps": 1e-06,84        "rope_parameters": {85            "mrope_interleaved": true,86            "mrope_section": [87                11,88                11,89                1090            ],91            "partial_rotary_factor": 0.25,92            "rope_theta": 10000000,93            "type": "default"94        },95        "tie_word_embeddings": false,96        "use_cache": true,97        "vocab_size": 24832098    },99    "tie_word_embeddings": false,100    "torch_dtype": "bfloat16",101    "unsloth_fixed": true,102    "unsloth_version": "2026.5.2",103    "video_token_id": 248057,104    "vision_end_token_id": 248054,105    "vision_start_token_id": 248053106}