| { |
| "architectures": [ |
| "PI0Model" |
| ], |
| "chunk_size": 4, |
| "dit_config": { |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 2, |
| "eos_token_id": 1, |
| "head_dim": 8, |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_size": 16, |
| "initializer_range": 0.02, |
| "intermediate_size": 32, |
| "is_causal": true, |
| "max_position_embeddings": 8192, |
| "model_type": "gemma", |
| "num_attention_heads": 2, |
| "num_hidden_layers": 2, |
| "num_key_value_heads": 1, |
| "pad_token_id": 0, |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "rope_theta": 10000.0, |
| "rope_type": "default" |
| }, |
| "tie_word_embeddings": true, |
| "use_bidirectional_attention": true, |
| "use_cache": true, |
| "vocab_size": 128 |
| }, |
| "dtype": "float32", |
| "loss_reduction": "mean", |
| "max_action_dim": 8, |
| "max_period": 4.0, |
| "max_state_dim": 8, |
| "min_period": 0.004, |
| "model_type": "pi0", |
| "num_inference_steps": 3, |
| "time_sampling_beta_alpha": 1.5, |
| "time_sampling_beta_beta": 1.0, |
| "time_sampling_offset": 0.001, |
| "time_sampling_scale": 0.999, |
| "transformers_version": "5.16.0.dev0", |
| "vlm_config": { |
| "hidden_size": 2048, |
| "image_token_index": 127, |
| "model_type": "paligemma", |
| "projection_dim": 16, |
| "text_config": { |
| "_name_or_path": "", |
| "architectures": null, |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 2, |
| "chunk_size_feed_forward": 0, |
| "dtype": null, |
| "eos_token_id": 1, |
| "head_dim": 8, |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_size": 16, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 32, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "max_position_embeddings": 8192, |
| "model_type": "gemma", |
| "num_attention_heads": 2, |
| "num_hidden_layers": 2, |
| "num_image_tokens": 4, |
| "num_key_value_heads": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "pad_token_id": 0, |
| "problem_type": null, |
| "return_dict": true, |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "rope_theta": 10000.0, |
| "rope_type": "default" |
| }, |
| "tie_word_embeddings": true, |
| "use_bidirectional_attention": true, |
| "use_cache": true, |
| "vocab_size": 128 |
| }, |
| "tie_word_embeddings": true, |
| "vision_config": { |
| "_name_or_path": "", |
| "architectures": null, |
| "attention_dropout": 0.0, |
| "chunk_size_feed_forward": 0, |
| "dtype": null, |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_size": 16, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "image_size": 8, |
| "intermediate_size": 32, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "layer_norm_eps": 1e-06, |
| "model_type": "siglip_vision_model", |
| "num_attention_heads": 2, |
| "num_channels": 3, |
| "num_hidden_layers": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "patch_size": 4, |
| "problem_type": null, |
| "projection_dim": 16, |
| "return_dict": true, |
| "vision_use_head": false |
| }, |
| "vocab_size": 257152 |
| } |
| } |
|
|
