| Qwen2-0.5B as the Reasoner for tisrt sucsessfull multimodal-realtime inference. | |
| On a MacBook Air M1 8GB with ca. 3s latency. | |
| On RTX 4090 with ca. 800ms. | |
| encoder.modality_preprocessors.vision.cls_token torch.Size([1, 1, 1280]) | |
| encoder.modality_preprocessors.vision.rgbt_stem.proj.1.weight torch.Size([1280, 3, 2, 14, 14]) | |
| encoder.modality_preprocessors.vision.pos_embedding_helper.pos_embed torch.Size([1, 257, 1280]) | |
| encoder.modality_preprocessors.audio.cls_token torch.Size([1, 1, 768]) | |
| encoder.modality_preprocessors.audio.rgbt_stem.proj.weight torch.Size([768, 1, 16, 16]) | |
| encoder.modality_preprocessors.audio.rgbt_stem.norm_layer.weight torch.Size([768]) | |
| encoder.modality_preprocessors.audio.rgbt_stem.norm_layer.bias torch.Size([768]) | |
| encoder.modality_preprocessors.audio.pos_embedding_helper.pos_embed torch.Size([1, 229, 768]) | |
| encoder.modality_trunks.vision.pre_transformer_layer.0.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.pre_transformer_layer.0.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.0.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.0.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.0.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.0.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.0.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.0.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.0.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.0.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.0.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.0.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.0.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.0.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.1.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.1.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.1.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.1.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.1.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.1.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.1.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.1.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.1.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.1.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.1.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.1.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.2.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.2.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.2.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.2.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.2.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.2.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.2.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.2.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.2.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.2.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.2.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.2.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.3.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.3.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.3.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.3.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.3.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.3.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.3.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.3.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.3.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.3.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.3.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.3.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.4.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.4.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.4.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.4.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.4.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.4.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.4.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.4.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.4.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.4.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.4.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.4.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.5.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.5.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.5.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.5.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.5.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.5.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.5.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.5.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.5.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.5.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.5.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.5.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.6.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.6.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.6.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.6.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.6.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.6.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.6.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.6.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.6.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.6.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.6.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.6.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.7.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.7.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.7.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.7.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.7.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.7.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.7.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.7.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.7.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.7.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.7.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.7.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.8.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.8.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.8.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.8.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.8.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.8.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.8.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.8.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.8.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.8.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.8.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.8.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.9.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.9.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.9.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.9.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.9.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.9.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.9.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.9.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.9.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.9.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.9.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.9.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.10.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.10.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.10.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.10.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.10.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.10.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.10.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.10.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.10.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.10.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.10.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.10.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.11.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.11.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.11.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.11.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.11.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.11.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.11.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.11.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.11.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.11.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.11.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.11.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.12.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.12.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.12.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.12.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.12.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.12.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.12.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.12.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.12.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.12.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.12.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.12.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.13.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.13.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.13.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.13.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.13.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.13.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.13.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.13.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.13.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.13.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.13.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.13.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.14.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.14.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.14.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.14.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.14.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.14.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.14.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.14.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.14.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.14.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.14.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.14.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.15.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.15.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.15.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.15.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.15.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.15.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.15.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.15.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.15.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.15.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.15.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.15.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.16.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.16.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.16.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.16.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.16.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.16.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.16.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.16.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.16.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.16.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.16.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.16.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.17.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.17.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.17.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.17.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.17.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.17.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.17.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.17.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.17.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.17.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.17.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.17.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.18.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.18.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.18.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.18.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.18.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.18.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.18.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.18.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.18.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.18.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.18.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.18.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.19.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.19.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.19.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.19.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.19.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.19.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.19.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.19.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.19.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.19.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.19.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.19.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.20.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.20.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.20.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.20.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.20.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.20.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.20.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.20.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.20.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.20.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.20.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.20.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.21.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.21.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.21.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.21.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.21.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.21.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.21.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.21.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.21.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.21.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.21.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.21.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.22.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.22.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.22.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.22.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.22.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.22.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.22.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.22.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.22.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.22.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.22.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.22.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.23.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.23.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.23.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.23.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.23.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.23.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.23.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.23.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.23.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.23.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.23.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.23.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.24.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.24.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.24.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.24.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.24.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.24.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.24.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.24.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.24.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.24.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.24.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.24.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.25.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.25.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.25.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.25.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.25.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.25.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.25.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.25.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.25.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.25.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.25.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.25.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.26.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.26.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.26.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.26.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.26.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.26.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.26.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.26.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.26.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.26.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.26.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.26.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.27.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.27.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.27.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.27.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.27.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.27.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.27.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.27.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.27.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.27.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.27.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.27.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.28.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.28.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.28.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.28.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.28.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.28.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.28.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.28.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.28.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.28.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.28.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.28.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.29.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.29.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.29.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.29.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.29.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.29.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.29.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.29.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.29.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.29.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.29.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.29.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.30.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.30.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.30.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.30.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.30.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.30.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.30.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.30.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.30.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.30.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.30.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.30.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.31.attn.in_proj_weight torch.Size([3840, 1280]) | |
| encoder.modality_trunks.vision.blocks.31.attn.in_proj_bias torch.Size([3840]) | |
| encoder.modality_trunks.vision.blocks.31.attn.out_proj.weight torch.Size([1280, 1280]) | |
| encoder.modality_trunks.vision.blocks.31.attn.out_proj.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.31.norm_1.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.31.norm_1.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.31.mlp.fc1.weight torch.Size([5120, 1280]) | |
| encoder.modality_trunks.vision.blocks.31.mlp.fc1.bias torch.Size([5120]) | |
| encoder.modality_trunks.vision.blocks.31.mlp.fc2.weight torch.Size([1280, 5120]) | |
| encoder.modality_trunks.vision.blocks.31.mlp.fc2.bias torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.31.norm_2.weight torch.Size([1280]) | |
| encoder.modality_trunks.vision.blocks.31.norm_2.bias torch.Size([1280]) | |
| encoder.modality_trunks.audio.blocks.0.attn.in_proj_weight torch.Size([2304, 768]) | |
| encoder.modality_trunks.audio.blocks.0.attn.in_proj_bias torch.Size([2304]) | |
| encoder.modality_trunks.audio.blocks.0.attn.bias_k torch.Size([1, 1, 768]) | |
| encoder.modality_trunks.audio.blocks.0.attn.bias_v torch.Size([1, 1, 768]) | |
| encoder.modality_trunks.audio.blocks.0.attn.out_proj.weight torch.Size([768, 768]) | |
| encoder.modality_trunks.audio.blocks.0.attn.out_proj.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.0.norm_1.weight torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.0.norm_1.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.0.mlp.fc1.weight torch.Size([3072, 768]) | |
| encoder.modality_trunks.audio.blocks.0.mlp.fc1.bias torch.Size([3072]) | |
| encoder.modality_trunks.audio.blocks.0.mlp.fc2.weight torch.Size([768, 3072]) | |
| encoder.modality_trunks.audio.blocks.0.mlp.fc2.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.0.norm_2.weight torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.0.norm_2.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.1.attn.in_proj_weight torch.Size([2304, 768]) | |
| encoder.modality_trunks.audio.blocks.1.attn.in_proj_bias torch.Size([2304]) | |
| encoder.modality_trunks.audio.blocks.1.attn.bias_k torch.Size([1, 1, 768]) | |
| encoder.modality_trunks.audio.blocks.1.attn.bias_v torch.Size([1, 1, 768]) | |
| encoder.modality_trunks.audio.blocks.1.attn.out_proj.weight torch.Size([768, 768]) | |
| encoder.modality_trunks.audio.blocks.1.attn.out_proj.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.1.norm_1.weight torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.1.norm_1.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.1.mlp.fc1.weight torch.Size([3072, 768]) | |
| encoder.modality_trunks.audio.blocks.1.mlp.fc1.bias torch.Size([3072]) | |
| encoder.modality_trunks.audio.blocks.1.mlp.fc2.weight torch.Size([768, 3072]) | |
| encoder.modality_trunks.audio.blocks.1.mlp.fc2.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.1.norm_2.weight torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.1.norm_2.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.2.attn.in_proj_weight torch.Size([2304, 768]) | |
| encoder.modality_trunks.audio.blocks.2.attn.in_proj_bias torch.Size([2304]) | |
| encoder.modality_trunks.audio.blocks.2.attn.bias_k torch.Size([1, 1, 768]) | |
| encoder.modality_trunks.audio.blocks.2.attn.bias_v torch.Size([1, 1, 768]) | |
| encoder.modality_trunks.audio.blocks.2.attn.out_proj.weight torch.Size([768, 768]) | |
| encoder.modality_trunks.audio.blocks.2.attn.out_proj.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.2.norm_1.weight torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.2.norm_1.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.2.mlp.fc1.weight torch.Size([3072, 768]) | |
| encoder.modality_trunks.audio.blocks.2.mlp.fc1.bias torch.Size([3072]) | |
| encoder.modality_trunks.audio.blocks.2.mlp.fc2.weight torch.Size([768, 3072]) | |
| encoder.modality_trunks.audio.blocks.2.mlp.fc2.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.2.norm_2.weight torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.2.norm_2.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.3.attn.in_proj_weight torch.Size([2304, 768]) | |
| encoder.modality_trunks.audio.blocks.3.attn.in_proj_bias torch.Size([2304]) | |
| encoder.modality_trunks.audio.blocks.3.attn.bias_k torch.Size([1, 1, 768]) | |
| encoder.modality_trunks.audio.blocks.3.attn.bias_v torch.Size([1, 1, 768]) | |
| encoder.modality_trunks.audio.blocks.3.attn.out_proj.weight torch.Size([768, 768]) | |
| encoder.modality_trunks.audio.blocks.3.attn.out_proj.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.3.norm_1.weight torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.3.norm_1.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.3.mlp.fc1.weight torch.Size([3072, 768]) | |
| encoder.modality_trunks.audio.blocks.3.mlp.fc1.bias torch.Size([3072]) | |
| encoder.modality_trunks.audio.blocks.3.mlp.fc2.weight torch.Size([768, 3072]) | |
| encoder.modality_trunks.audio.blocks.3.mlp.fc2.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.3.norm_2.weight torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.3.norm_2.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.4.attn.in_proj_weight torch.Size([2304, 768]) | |
| encoder.modality_trunks.audio.blocks.4.attn.in_proj_bias torch.Size([2304]) | |
| encoder.modality_trunks.audio.blocks.4.attn.bias_k torch.Size([1, 1, 768]) | |
| encoder.modality_trunks.audio.blocks.4.attn.bias_v torch.Size([1, 1, 768]) | |
| encoder.modality_trunks.audio.blocks.4.attn.out_proj.weight torch.Size([768, 768]) | |
| encoder.modality_trunks.audio.blocks.4.attn.out_proj.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.4.norm_1.weight torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.4.norm_1.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.4.mlp.fc1.weight torch.Size([3072, 768]) | |
| encoder.modality_trunks.audio.blocks.4.mlp.fc1.bias torch.Size([3072]) | |
| encoder.modality_trunks.audio.blocks.4.mlp.fc2.weight torch.Size([768, 3072]) | |
| encoder.modality_trunks.audio.blocks.4.mlp.fc2.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.4.norm_2.weight torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.4.norm_2.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.5.attn.in_proj_weight torch.Size([2304, 768]) | |
| encoder.modality_trunks.audio.blocks.5.attn.in_proj_bias torch.Size([2304]) | |
| encoder.modality_trunks.audio.blocks.5.attn.bias_k torch.Size([1, 1, 768]) | |
| encoder.modality_trunks.audio.blocks.5.attn.bias_v torch.Size([1, 1, 768]) | |
| encoder.modality_trunks.audio.blocks.5.attn.out_proj.weight torch.Size([768, 768]) | |
| encoder.modality_trunks.audio.blocks.5.attn.out_proj.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.5.norm_1.weight torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.5.norm_1.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.5.mlp.fc1.weight torch.Size([3072, 768]) | |
| encoder.modality_trunks.audio.blocks.5.mlp.fc1.bias torch.Size([3072]) | |
| encoder.modality_trunks.audio.blocks.5.mlp.fc2.weight torch.Size([768, 3072]) | |
| encoder.modality_trunks.audio.blocks.5.mlp.fc2.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.5.norm_2.weight torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.5.norm_2.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.6.attn.in_proj_weight torch.Size([2304, 768]) | |
| encoder.modality_trunks.audio.blocks.6.attn.in_proj_bias torch.Size([2304]) | |
| encoder.modality_trunks.audio.blocks.6.attn.bias_k torch.Size([1, 1, 768]) | |
| encoder.modality_trunks.audio.blocks.6.attn.bias_v torch.Size([1, 1, 768]) | |
| encoder.modality_trunks.audio.blocks.6.attn.out_proj.weight torch.Size([768, 768]) | |
| encoder.modality_trunks.audio.blocks.6.attn.out_proj.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.6.norm_1.weight torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.6.norm_1.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.6.mlp.fc1.weight torch.Size([3072, 768]) | |
| encoder.modality_trunks.audio.blocks.6.mlp.fc1.bias torch.Size([3072]) | |
| encoder.modality_trunks.audio.blocks.6.mlp.fc2.weight torch.Size([768, 3072]) | |
| encoder.modality_trunks.audio.blocks.6.mlp.fc2.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.6.norm_2.weight torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.6.norm_2.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.7.attn.in_proj_weight torch.Size([2304, 768]) | |
| encoder.modality_trunks.audio.blocks.7.attn.in_proj_bias torch.Size([2304]) | |
| encoder.modality_trunks.audio.blocks.7.attn.bias_k torch.Size([1, 1, 768]) | |
| encoder.modality_trunks.audio.blocks.7.attn.bias_v torch.Size([1, 1, 768]) | |
| encoder.modality_trunks.audio.blocks.7.attn.out_proj.weight torch.Size([768, 768]) | |
| encoder.modality_trunks.audio.blocks.7.attn.out_proj.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.7.norm_1.weight torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.7.norm_1.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.7.mlp.fc1.weight torch.Size([3072, 768]) | |
| encoder.modality_trunks.audio.blocks.7.mlp.fc1.bias torch.Size([3072]) | |
| encoder.modality_trunks.audio.blocks.7.mlp.fc2.weight torch.Size([768, 3072]) | |
| encoder.modality_trunks.audio.blocks.7.mlp.fc2.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.7.norm_2.weight torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.7.norm_2.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.8.attn.in_proj_weight torch.Size([2304, 768]) | |
| encoder.modality_trunks.audio.blocks.8.attn.in_proj_bias torch.Size([2304]) | |
| encoder.modality_trunks.audio.blocks.8.attn.bias_k torch.Size([1, 1, 768]) | |
| encoder.modality_trunks.audio.blocks.8.attn.bias_v torch.Size([1, 1, 768]) | |
| encoder.modality_trunks.audio.blocks.8.attn.out_proj.weight torch.Size([768, 768]) | |
| encoder.modality_trunks.audio.blocks.8.attn.out_proj.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.8.norm_1.weight torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.8.norm_1.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.8.mlp.fc1.weight torch.Size([3072, 768]) | |
| encoder.modality_trunks.audio.blocks.8.mlp.fc1.bias torch.Size([3072]) | |
| encoder.modality_trunks.audio.blocks.8.mlp.fc2.weight torch.Size([768, 3072]) | |
| encoder.modality_trunks.audio.blocks.8.mlp.fc2.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.8.norm_2.weight torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.8.norm_2.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.9.attn.in_proj_weight torch.Size([2304, 768]) | |
| encoder.modality_trunks.audio.blocks.9.attn.in_proj_bias torch.Size([2304]) | |
| encoder.modality_trunks.audio.blocks.9.attn.bias_k torch.Size([1, 1, 768]) | |
| encoder.modality_trunks.audio.blocks.9.attn.bias_v torch.Size([1, 1, 768]) | |
| encoder.modality_trunks.audio.blocks.9.attn.out_proj.weight torch.Size([768, 768]) | |
| encoder.modality_trunks.audio.blocks.9.attn.out_proj.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.9.norm_1.weight torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.9.norm_1.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.9.mlp.fc1.weight torch.Size([3072, 768]) | |
| encoder.modality_trunks.audio.blocks.9.mlp.fc1.bias torch.Size([3072]) | |
| encoder.modality_trunks.audio.blocks.9.mlp.fc2.weight torch.Size([768, 3072]) | |
| encoder.modality_trunks.audio.blocks.9.mlp.fc2.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.9.norm_2.weight torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.9.norm_2.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.10.attn.in_proj_weight torch.Size([2304, 768]) | |
| encoder.modality_trunks.audio.blocks.10.attn.in_proj_bias torch.Size([2304]) | |
| encoder.modality_trunks.audio.blocks.10.attn.bias_k torch.Size([1, 1, 768]) | |
| encoder.modality_trunks.audio.blocks.10.attn.bias_v torch.Size([1, 1, 768]) | |
| encoder.modality_trunks.audio.blocks.10.attn.out_proj.weight torch.Size([768, 768]) | |
| encoder.modality_trunks.audio.blocks.10.attn.out_proj.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.10.norm_1.weight torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.10.norm_1.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.10.mlp.fc1.weight torch.Size([3072, 768]) | |
| encoder.modality_trunks.audio.blocks.10.mlp.fc1.bias torch.Size([3072]) | |
| encoder.modality_trunks.audio.blocks.10.mlp.fc2.weight torch.Size([768, 3072]) | |
| encoder.modality_trunks.audio.blocks.10.mlp.fc2.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.10.norm_2.weight torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.10.norm_2.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.11.attn.in_proj_weight torch.Size([2304, 768]) | |
| encoder.modality_trunks.audio.blocks.11.attn.in_proj_bias torch.Size([2304]) | |
| encoder.modality_trunks.audio.blocks.11.attn.bias_k torch.Size([1, 1, 768]) | |
| encoder.modality_trunks.audio.blocks.11.attn.bias_v torch.Size([1, 1, 768]) | |
| encoder.modality_trunks.audio.blocks.11.attn.out_proj.weight torch.Size([768, 768]) | |
| encoder.modality_trunks.audio.blocks.11.attn.out_proj.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.11.norm_1.weight torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.11.norm_1.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.11.mlp.fc1.weight torch.Size([3072, 768]) | |
| encoder.modality_trunks.audio.blocks.11.mlp.fc1.bias torch.Size([3072]) | |
| encoder.modality_trunks.audio.blocks.11.mlp.fc2.weight torch.Size([768, 3072]) | |
| encoder.modality_trunks.audio.blocks.11.mlp.fc2.bias torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.11.norm_2.weight torch.Size([768]) | |
| encoder.modality_trunks.audio.blocks.11.norm_2.bias torch.Size([768]) | |
| encoder.modality_heads.vision.0.weight torch.Size([1280]) | |
| encoder.modality_heads.vision.0.bias torch.Size([1280]) | |
| encoder.modality_heads.vision.2.weight torch.Size([1024, 1280]) | |
| encoder.modality_heads.audio.0.weight torch.Size([768]) | |
| encoder.modality_heads.audio.0.bias torch.Size([768]) | |
| encoder.modality_heads.audio.2.weight torch.Size([1024, 768]) | |
| encoder.modality_postprocessors.audio.1.log_logit_scale torch.Size([]) | |
| reasoner.model.embed_tokens.weight torch.Size([151936, 896]) | |
| reasoner.model.layers.0.self_attn.q_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.0.self_attn.q_proj.bias torch.Size([896]) | |
| reasoner.model.layers.0.self_attn.k_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.0.self_attn.k_proj.bias torch.Size([128]) | |
| reasoner.model.layers.0.self_attn.v_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.0.self_attn.v_proj.bias torch.Size([128]) | |
| reasoner.model.layers.0.self_attn.o_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.0.mlp.gate_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.0.mlp.up_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.0.mlp.down_proj.weight torch.Size([896, 4864]) | |
| reasoner.model.layers.0.input_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.0.post_attention_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.1.self_attn.q_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.1.self_attn.q_proj.bias torch.Size([896]) | |
| reasoner.model.layers.1.self_attn.k_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.1.self_attn.k_proj.bias torch.Size([128]) | |
| reasoner.model.layers.1.self_attn.v_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.1.self_attn.v_proj.bias torch.Size([128]) | |
| reasoner.model.layers.1.self_attn.o_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.1.mlp.gate_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.1.mlp.up_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.1.mlp.down_proj.weight torch.Size([896, 4864]) | |
| reasoner.model.layers.1.input_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.1.post_attention_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.2.self_attn.q_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.2.self_attn.q_proj.bias torch.Size([896]) | |
| reasoner.model.layers.2.self_attn.k_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.2.self_attn.k_proj.bias torch.Size([128]) | |
| reasoner.model.layers.2.self_attn.v_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.2.self_attn.v_proj.bias torch.Size([128]) | |
| reasoner.model.layers.2.self_attn.o_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.2.mlp.gate_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.2.mlp.up_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.2.mlp.down_proj.weight torch.Size([896, 4864]) | |
| reasoner.model.layers.2.input_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.2.post_attention_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.3.self_attn.q_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.3.self_attn.q_proj.bias torch.Size([896]) | |
| reasoner.model.layers.3.self_attn.k_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.3.self_attn.k_proj.bias torch.Size([128]) | |
| reasoner.model.layers.3.self_attn.v_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.3.self_attn.v_proj.bias torch.Size([128]) | |
| reasoner.model.layers.3.self_attn.o_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.3.mlp.gate_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.3.mlp.up_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.3.mlp.down_proj.weight torch.Size([896, 4864]) | |
| reasoner.model.layers.3.input_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.3.post_attention_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.4.self_attn.q_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.4.self_attn.q_proj.bias torch.Size([896]) | |
| reasoner.model.layers.4.self_attn.k_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.4.self_attn.k_proj.bias torch.Size([128]) | |
| reasoner.model.layers.4.self_attn.v_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.4.self_attn.v_proj.bias torch.Size([128]) | |
| reasoner.model.layers.4.self_attn.o_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.4.mlp.gate_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.4.mlp.up_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.4.mlp.down_proj.weight torch.Size([896, 4864]) | |
| reasoner.model.layers.4.input_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.4.post_attention_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.5.self_attn.q_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.5.self_attn.q_proj.bias torch.Size([896]) | |
| reasoner.model.layers.5.self_attn.k_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.5.self_attn.k_proj.bias torch.Size([128]) | |
| reasoner.model.layers.5.self_attn.v_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.5.self_attn.v_proj.bias torch.Size([128]) | |
| reasoner.model.layers.5.self_attn.o_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.5.mlp.gate_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.5.mlp.up_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.5.mlp.down_proj.weight torch.Size([896, 4864]) | |
| reasoner.model.layers.5.input_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.5.post_attention_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.6.self_attn.q_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.6.self_attn.q_proj.bias torch.Size([896]) | |
| reasoner.model.layers.6.self_attn.k_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.6.self_attn.k_proj.bias torch.Size([128]) | |
| reasoner.model.layers.6.self_attn.v_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.6.self_attn.v_proj.bias torch.Size([128]) | |
| reasoner.model.layers.6.self_attn.o_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.6.mlp.gate_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.6.mlp.up_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.6.mlp.down_proj.weight torch.Size([896, 4864]) | |
| reasoner.model.layers.6.input_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.6.post_attention_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.7.self_attn.q_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.7.self_attn.q_proj.bias torch.Size([896]) | |
| reasoner.model.layers.7.self_attn.k_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.7.self_attn.k_proj.bias torch.Size([128]) | |
| reasoner.model.layers.7.self_attn.v_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.7.self_attn.v_proj.bias torch.Size([128]) | |
| reasoner.model.layers.7.self_attn.o_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.7.mlp.gate_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.7.mlp.up_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.7.mlp.down_proj.weight torch.Size([896, 4864]) | |
| reasoner.model.layers.7.input_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.7.post_attention_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.8.self_attn.q_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.8.self_attn.q_proj.bias torch.Size([896]) | |
| reasoner.model.layers.8.self_attn.k_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.8.self_attn.k_proj.bias torch.Size([128]) | |
| reasoner.model.layers.8.self_attn.v_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.8.self_attn.v_proj.bias torch.Size([128]) | |
| reasoner.model.layers.8.self_attn.o_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.8.mlp.gate_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.8.mlp.up_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.8.mlp.down_proj.weight torch.Size([896, 4864]) | |
| reasoner.model.layers.8.input_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.8.post_attention_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.9.self_attn.q_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.9.self_attn.q_proj.bias torch.Size([896]) | |
| reasoner.model.layers.9.self_attn.k_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.9.self_attn.k_proj.bias torch.Size([128]) | |
| reasoner.model.layers.9.self_attn.v_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.9.self_attn.v_proj.bias torch.Size([128]) | |
| reasoner.model.layers.9.self_attn.o_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.9.mlp.gate_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.9.mlp.up_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.9.mlp.down_proj.weight torch.Size([896, 4864]) | |
| reasoner.model.layers.9.input_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.9.post_attention_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.10.self_attn.q_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.10.self_attn.q_proj.bias torch.Size([896]) | |
| reasoner.model.layers.10.self_attn.k_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.10.self_attn.k_proj.bias torch.Size([128]) | |
| reasoner.model.layers.10.self_attn.v_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.10.self_attn.v_proj.bias torch.Size([128]) | |
| reasoner.model.layers.10.self_attn.o_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.10.mlp.gate_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.10.mlp.up_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.10.mlp.down_proj.weight torch.Size([896, 4864]) | |
| reasoner.model.layers.10.input_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.10.post_attention_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.11.self_attn.q_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.11.self_attn.q_proj.bias torch.Size([896]) | |
| reasoner.model.layers.11.self_attn.k_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.11.self_attn.k_proj.bias torch.Size([128]) | |
| reasoner.model.layers.11.self_attn.v_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.11.self_attn.v_proj.bias torch.Size([128]) | |
| reasoner.model.layers.11.self_attn.o_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.11.mlp.gate_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.11.mlp.up_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.11.mlp.down_proj.weight torch.Size([896, 4864]) | |
| reasoner.model.layers.11.input_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.11.post_attention_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.12.self_attn.q_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.12.self_attn.q_proj.bias torch.Size([896]) | |
| reasoner.model.layers.12.self_attn.k_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.12.self_attn.k_proj.bias torch.Size([128]) | |
| reasoner.model.layers.12.self_attn.v_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.12.self_attn.v_proj.bias torch.Size([128]) | |
| reasoner.model.layers.12.self_attn.o_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.12.mlp.gate_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.12.mlp.up_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.12.mlp.down_proj.weight torch.Size([896, 4864]) | |
| reasoner.model.layers.12.input_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.12.post_attention_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.13.self_attn.q_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.13.self_attn.q_proj.bias torch.Size([896]) | |
| reasoner.model.layers.13.self_attn.k_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.13.self_attn.k_proj.bias torch.Size([128]) | |
| reasoner.model.layers.13.self_attn.v_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.13.self_attn.v_proj.bias torch.Size([128]) | |
| reasoner.model.layers.13.self_attn.o_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.13.mlp.gate_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.13.mlp.up_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.13.mlp.down_proj.weight torch.Size([896, 4864]) | |
| reasoner.model.layers.13.input_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.13.post_attention_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.14.self_attn.q_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.14.self_attn.q_proj.bias torch.Size([896]) | |
| reasoner.model.layers.14.self_attn.k_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.14.self_attn.k_proj.bias torch.Size([128]) | |
| reasoner.model.layers.14.self_attn.v_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.14.self_attn.v_proj.bias torch.Size([128]) | |
| reasoner.model.layers.14.self_attn.o_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.14.mlp.gate_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.14.mlp.up_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.14.mlp.down_proj.weight torch.Size([896, 4864]) | |
| reasoner.model.layers.14.input_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.14.post_attention_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.15.self_attn.q_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.15.self_attn.q_proj.bias torch.Size([896]) | |
| reasoner.model.layers.15.self_attn.k_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.15.self_attn.k_proj.bias torch.Size([128]) | |
| reasoner.model.layers.15.self_attn.v_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.15.self_attn.v_proj.bias torch.Size([128]) | |
| reasoner.model.layers.15.self_attn.o_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.15.mlp.gate_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.15.mlp.up_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.15.mlp.down_proj.weight torch.Size([896, 4864]) | |
| reasoner.model.layers.15.input_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.15.post_attention_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.16.self_attn.q_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.16.self_attn.q_proj.bias torch.Size([896]) | |
| reasoner.model.layers.16.self_attn.k_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.16.self_attn.k_proj.bias torch.Size([128]) | |
| reasoner.model.layers.16.self_attn.v_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.16.self_attn.v_proj.bias torch.Size([128]) | |
| reasoner.model.layers.16.self_attn.o_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.16.mlp.gate_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.16.mlp.up_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.16.mlp.down_proj.weight torch.Size([896, 4864]) | |
| reasoner.model.layers.16.input_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.16.post_attention_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.17.self_attn.q_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.17.self_attn.q_proj.bias torch.Size([896]) | |
| reasoner.model.layers.17.self_attn.k_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.17.self_attn.k_proj.bias torch.Size([128]) | |
| reasoner.model.layers.17.self_attn.v_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.17.self_attn.v_proj.bias torch.Size([128]) | |
| reasoner.model.layers.17.self_attn.o_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.17.mlp.gate_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.17.mlp.up_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.17.mlp.down_proj.weight torch.Size([896, 4864]) | |
| reasoner.model.layers.17.input_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.17.post_attention_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.18.self_attn.q_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.18.self_attn.q_proj.bias torch.Size([896]) | |
| reasoner.model.layers.18.self_attn.k_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.18.self_attn.k_proj.bias torch.Size([128]) | |
| reasoner.model.layers.18.self_attn.v_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.18.self_attn.v_proj.bias torch.Size([128]) | |
| reasoner.model.layers.18.self_attn.o_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.18.mlp.gate_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.18.mlp.up_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.18.mlp.down_proj.weight torch.Size([896, 4864]) | |
| reasoner.model.layers.18.input_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.18.post_attention_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.19.self_attn.q_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.19.self_attn.q_proj.bias torch.Size([896]) | |
| reasoner.model.layers.19.self_attn.k_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.19.self_attn.k_proj.bias torch.Size([128]) | |
| reasoner.model.layers.19.self_attn.v_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.19.self_attn.v_proj.bias torch.Size([128]) | |
| reasoner.model.layers.19.self_attn.o_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.19.mlp.gate_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.19.mlp.up_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.19.mlp.down_proj.weight torch.Size([896, 4864]) | |
| reasoner.model.layers.19.input_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.19.post_attention_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.20.self_attn.q_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.20.self_attn.q_proj.bias torch.Size([896]) | |
| reasoner.model.layers.20.self_attn.k_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.20.self_attn.k_proj.bias torch.Size([128]) | |
| reasoner.model.layers.20.self_attn.v_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.20.self_attn.v_proj.bias torch.Size([128]) | |
| reasoner.model.layers.20.self_attn.o_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.20.mlp.gate_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.20.mlp.up_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.20.mlp.down_proj.weight torch.Size([896, 4864]) | |
| reasoner.model.layers.20.input_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.20.post_attention_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.21.self_attn.q_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.21.self_attn.q_proj.bias torch.Size([896]) | |
| reasoner.model.layers.21.self_attn.k_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.21.self_attn.k_proj.bias torch.Size([128]) | |
| reasoner.model.layers.21.self_attn.v_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.21.self_attn.v_proj.bias torch.Size([128]) | |
| reasoner.model.layers.21.self_attn.o_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.21.mlp.gate_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.21.mlp.up_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.21.mlp.down_proj.weight torch.Size([896, 4864]) | |
| reasoner.model.layers.21.input_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.21.post_attention_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.22.self_attn.q_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.22.self_attn.q_proj.bias torch.Size([896]) | |
| reasoner.model.layers.22.self_attn.k_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.22.self_attn.k_proj.bias torch.Size([128]) | |
| reasoner.model.layers.22.self_attn.v_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.22.self_attn.v_proj.bias torch.Size([128]) | |
| reasoner.model.layers.22.self_attn.o_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.22.mlp.gate_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.22.mlp.up_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.22.mlp.down_proj.weight torch.Size([896, 4864]) | |
| reasoner.model.layers.22.input_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.22.post_attention_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.23.self_attn.q_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.23.self_attn.q_proj.bias torch.Size([896]) | |
| reasoner.model.layers.23.self_attn.k_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.23.self_attn.k_proj.bias torch.Size([128]) | |
| reasoner.model.layers.23.self_attn.v_proj.weight torch.Size([128, 896]) | |
| reasoner.model.layers.23.self_attn.v_proj.bias torch.Size([128]) | |
| reasoner.model.layers.23.self_attn.o_proj.weight torch.Size([896, 896]) | |
| reasoner.model.layers.23.mlp.gate_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.23.mlp.up_proj.weight torch.Size([4864, 896]) | |
| reasoner.model.layers.23.mlp.down_proj.weight torch.Size([896, 4864]) | |
| reasoner.model.layers.23.input_layernorm.weight torch.Size([896]) | |
| reasoner.model.layers.23.post_attention_layernorm.weight torch.Size([896]) | |
| reasoner.model.norm.weight torch.Size([896]) | |
| reasoner.lm_head.weight torch.Size([151936, 896]) | |
| input_projetor.weight torch.Size([896, 1024]) | |
| input_projetor.bias torch.Size([896]) |