diffusers-internal-dev/tiny-minimax-h3-modular-pipe
0297
1{2 "architectures": [3 "Qwen3VLForConditionalGeneration"4 ],5 "dtype": "float32",6 "image_token_id": 151655,7 "model_type": "qwen3_vl",8 "text_config": {9 "attention_bias": false,10 "attention_dropout": 0.0,11 "head_dim": 8,12 "hidden_act": "silu",13 "hidden_size": 16,14 "initializer_range": 0.02,15 "intermediate_size": 16,16 "max_position_embeddings": 128000,17 "model_type": "qwen3_vl_text",18 "num_attention_heads": 2,19 "num_hidden_layers": 51,20 "num_key_value_heads": 2,21 "pad_token_id": null,22 "rms_norm_eps": 1e-06,23 "rope_parameters": {24 "mrope_section": [25 1,26 1,27 228 ],29 "rope_theta": 500000.0,30 "rope_type": "default",31 "type": "default"32 },33 "use_cache": true,34 "vocab_size": 15193635 },36 "tie_word_embeddings": false,37 "transformers_version": "5.8.0",38 "video_token_id": 151656,39 "vision_config": {40 "deepstack_visual_indexes": [41 042 ],43 "depth": 2,44 "hidden_act": "gelu_pytorch_tanh",45 "hidden_size": 16,46 "in_channels": 3,47 "initializer_range": 0.02,48 "intermediate_size": 16,49 "model_type": "qwen3_vl_vision",50 "num_heads": 2,51 "num_position_embeddings": 64,52 "out_hidden_size": 16,53 "patch_size": 4,54 "spatial_merge_size": 2,55 "temporal_patch_size": 256 },57 "vision_end_token_id": 151653,58 "vision_start_token_id": 15165259}60 