| { |
| "architectures": [ |
| "D1OmniModel" |
| ], |
| "auto_map": { |
| "AutoConfig": "modeling_d1.D1OmniConfig", |
| "AutoModel": "modeling_d1.D1OmniModel" |
| }, |
| "model_type": "d1_omni", |
| "dtype": "float32", |
| "max_length": 16384, |
| "image_text_length": 896, |
| "audio_text_length": 15360, |
| "head_layers": 2, |
| "projector_hidden_size": 2048, |
| "temperatures": { |
| "choice:11+": 1.372515082359314, |
| "choice:2": 1.7465145587921143, |
| "choice:3-5": 1.3998981714248657, |
| "choice:6-10": 1.1751071214675903, |
| "noul:2": 1.6663223505020142, |
| "score:3-5": 1.7301132678985596, |
| "score:6-10": 1.0, |
| "choice": 1.0, |
| "score": 1.0, |
| "noul": 1.0 |
| }, |
| "bos_token_id": 1, |
| "pad_token_id": 0, |
| "text_config": { |
| "vocab_size": 65536, |
| "hidden_size": 1024, |
| "intermediate_size": 6656, |
| "num_hidden_layers": 16, |
| "num_attention_heads": 16, |
| "num_key_value_heads": 8, |
| "layer_types": [ |
| "conv", |
| "conv", |
| "full_attention", |
| "conv", |
| "conv", |
| "full_attention", |
| "conv", |
| "conv", |
| "full_attention", |
| "conv", |
| "full_attention", |
| "conv", |
| "full_attention", |
| "conv", |
| "full_attention", |
| "conv" |
| ], |
| "norm_eps": 1e-05, |
| "conv_L_cache": 3, |
| "block_ffn_dim_multiplier": 1.0, |
| "block_multiple_of": 256, |
| "max_position_embeddings": 128000, |
| "rope_theta": 1000000.0 |
| }, |
| "vision_config": { |
| "attention_dropout": 0.0, |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_size": 768, |
| "intermediate_size": 3072, |
| "layer_norm_eps": 1e-06, |
| "model_type": "siglip2_vision_model", |
| "num_attention_heads": 12, |
| "num_channels": 3, |
| "num_hidden_layers": 12, |
| "num_patches": 256, |
| "patch_size": 16, |
| "vision_use_head": false |
| }, |
| "audio_config": { |
| "feat_in": 128, |
| "n_layers": 17, |
| "d_model": 512, |
| "subsampling_conv_channels": 256, |
| "ff_expansion_factor": 4, |
| "n_heads": 8, |
| "conv_kernel_size": 9, |
| "residual_width": 512 |
| } |
| } |
|
|
