enosislabs/aether-2b-cyber
011
1{2 "architectures": [3 "Qwen3_5ForConditionalGeneration"4 ],5 "torch_dtype": "bfloat16",6 "eos_token_id": 248044,7 "image_token_id": 248056,8 "model_name": "Qwen/Qwen3.5-2B-Base",9 "model_type": "qwen3_5",10 "pad_token_id": 248044,11 "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": 2048,22 "initializer_range": 0.02,23 "intermediate_size": 6144,24 "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 ],50 "linear_conv_kernel_dim": 4,51 "linear_key_head_dim": 128,52 "linear_num_key_heads": 16,53 "linear_num_value_heads": 16,54 "linear_value_head_dim": 128,55 "mamba_ssm_dtype": "float32",56 "max_position_embeddings": 262144,57 "mlp_only_layers": [],58 "model_type": "qwen3_5_text",59 "mtp_num_hidden_layers": 1,60 "mtp_use_dedicated_embeddings": false,61 "num_attention_heads": 8,62 "num_hidden_layers": 24,63 "num_key_value_heads": 2,64 "pad_token_id": null,65 "partial_rotary_factor": 0.25,66 "rms_norm_eps": 1e-06,67 "rope_parameters": {68 "mrope_interleaved": true,69 "mrope_section": [70 11,71 11,72 1073 ],74 "partial_rotary_factor": 0.25,75 "rope_theta": 10000000,76 "rope_type": "default"77 },78 "tie_word_embeddings": true,79 "use_cache": true,80 "vocab_size": 24832081 },82 "tie_word_embeddings": true,83 "unsloth_version": "2026.6.8",84 "use_cache": false,85 "video_token_id": 248057,86 "vision_config": {87 "deepstack_visual_indexes": [],88 "depth": 24,89 "torch_dtype": "bfloat16",90 "hidden_act": "gelu_pytorch_tanh",91 "hidden_size": 1024,92 "in_channels": 3,93 "initializer_range": 0.02,94 "intermediate_size": 4096,95 "model_type": "qwen3_5",96 "num_heads": 16,97 "num_position_embeddings": 2304,98 "out_hidden_size": 2048,99 "patch_size": 16,100 "spatial_merge_size": 2,101 "temporal_patch_size": 2102 },103 "vision_end_token_id": 248054,104 "vision_start_token_id": 248053105}