CoolFace
Modelpublic

UnionStreet/Helios-Rabbit-1.0

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face
0likes44downloads
config.json106 linesDownload Raw Back to root
1{2    "architectures": [3        "Qwen3_5MoeForConditionalGeneration"4    ],5    "image_token_id": 248056,6    "model_name": "/root/.cache/kagglehub/models/jackjirong2/qwen3.6-35b-a3b/transformers/default/1",7    "model_type": "qwen3_5_moe",8    "pad_token_id": 248044,9    "text_config": {10        "attention_bias": false,11        "attention_dropout": 0.0,12        "attn_output_gate": true,13        "bos_token_id": 248044,14        "torch_dtype": "bfloat16",15        "eos_token_id": 248044,16        "full_attention_interval": 4,17        "head_dim": 256,18        "hidden_act": "silu",19        "hidden_size": 2048,20        "initializer_range": 0.02,21        "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        ],63        "linear_conv_kernel_dim": 4,64        "linear_key_head_dim": 128,65        "linear_num_key_heads": 16,66        "linear_num_value_heads": 32,67        "linear_value_head_dim": 128,68        "mamba_ssm_dtype": "float32",69        "max_position_embeddings": 262144,70        "model_type": "qwen3_5_moe_text",71        "moe_intermediate_size": 512,72        "mtp_num_hidden_layers": 1,73        "mtp_use_dedicated_embeddings": false,74        "num_attention_heads": 16,75        "num_experts": 256,76        "num_experts_per_tok": 8,77        "num_hidden_layers": 40,78        "num_key_value_heads": 2,79        "output_router_logits": false,80        "pad_token_id": null,81        "partial_rotary_factor": 0.25,82        "rms_norm_eps": 1e-06,83        "rope_parameters": {84            "mrope_interleaved": true,85            "mrope_section": [86                11,87                11,88                1089            ],90            "partial_rotary_factor": 0.25,91            "rope_theta": 10000000,92            "type": "default"93        },94        "router_aux_loss_coef": 0.001,95        "shared_expert_intermediate_size": 512,96        "tie_word_embeddings": false,97        "use_cache": true,98        "vocab_size": 24832099    },100    "tie_word_embeddings": false,101    "torch_dtype": "bfloat16",102    "unsloth_version": "2026.4.8",103    "video_token_id": 248057,104    "vision_end_token_id": 248054,105    "vision_start_token_id": 248053106}