fudan-generative-ai/WAM-Diff2
022
1{2 "architectures": [3 "WAMDiff2ForConditionalGeneration"4 ],5 "image_token_id": 151655,6 "model_type": "wam_diff2",7 "text_config": {8 "attention_bias": false,9 "attention_dropout": 0.0,10 "bos_token_id": 151643,11 "dtype": "bfloat16",12 "eos_token_id": 151645,13 "head_dim": 128,14 "hidden_act": "silu",15 "hidden_size": 2048,16 "initializer_range": 0.02,17 "intermediate_size": 6144,18 "max_position_embeddings": 262144,19 "model_type": "wam_diff2_text",20 "num_attention_heads": 16,21 "num_hidden_layers": 28,22 "num_key_value_heads": 8,23 "rms_norm_eps": 1e-06,24 "rope_scaling": {25 "mrope_interleaved": true,26 "mrope_section": [27 24,28 20,29 2030 ],31 "rope_type": "default"32 },33 "rope_theta": 5000000,34 "tie_word_embeddings": true,35 "use_cache": true,36 "vocab_size": 15193637 },38 "tie_word_embeddings": true,39 "transformers_version": "4.57.0.dev0",40 "video_token_id": 151656,41 "vision_config": {42 "deepstack_visual_indexes": [43 5,44 11,45 1746 ],47 "depth": 24,48 "hidden_act": "gelu_pytorch_tanh",49 "hidden_size": 1024,50 "in_channels": 3,51 "initializer_range": 0.02,52 "intermediate_size": 4096,53 "model_type": "wam_diff2",54 "num_heads": 16,55 "num_position_embeddings": 2304,56 "out_hidden_size": 2048,57 "patch_size": 16,58 "spatial_merge_size": 2,59 "temporal_patch_size": 260 },61 "vision_end_token_id": 151653,62 "vision_start_token_id": 15165263}64 