8F-ai/Verus-R1
321
1{2 "architectures": [3 "Qwen3_5ForConditionalGeneration"4 ],5 "dtype": "bfloat16",6 "image_token_id": 248056,7 "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": null,13 "dtype": "bfloat16",14 "eos_token_id": 248044,15 "full_attention_interval": 4,16 "head_dim": 256,17 "hidden_act": "silu",18 "hidden_size": 2048,19 "initializer_range": 0.02,20 "intermediate_size": 6144,21 "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 ],47 "linear_conv_kernel_dim": 4,48 "linear_key_head_dim": 128,49 "linear_num_key_heads": 16,50 "linear_num_value_heads": 16,51 "linear_value_head_dim": 128,52 "mamba_ssm_dtype": "float32",53 "max_position_embeddings": 262144,54 "mlp_only_layers": [],55 "model_type": "qwen3_5_text",56 "mtp_num_hidden_layers": 1,57 "mtp_use_dedicated_embeddings": false,58 "num_attention_heads": 8,59 "num_hidden_layers": 24,60 "num_key_value_heads": 2,61 "pad_token_id": null,62 "partial_rotary_factor": 0.25,63 "rms_norm_eps": 1e-06,64 "rope_parameters": {65 "mrope_interleaved": true,66 "mrope_section": [67 11,68 11,69 1070 ],71 "partial_rotary_factor": 0.25,72 "rope_theta": 10000000,73 "rope_type": "default"74 },75 "tie_word_embeddings": true,76 "use_cache": true,77 "vocab_size": 24832078 },79 "tie_word_embeddings": true,80 "transformers_version": "5.8.0.dev0",81 "use_cache": true,82 "video_token_id": 248057,83 "vision_config": {84 "deepstack_visual_indexes": [],85 "depth": 24,86 "dtype": "bfloat16",87 "hidden_act": "gelu_pytorch_tanh",88 "hidden_size": 1024,89 "in_channels": 3,90 "initializer_range": 0.02,91 "intermediate_size": 4096,92 "model_type": "qwen3_5_vision",93 "num_heads": 16,94 "num_position_embeddings": 2304,95 "out_hidden_size": 2048,96 "patch_size": 16,97 "spatial_merge_size": 2,98 "temporal_patch_size": 299 },100 "vision_end_token_id": 248054,101 "vision_start_token_id": 248053102}103 