| { | |
| "_attn_implementation_autoset": true, | |
| "act_expert_config": { | |
| "_attn_implementation_autoset": true, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "head_dim": 256, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "max_position_embeddings": 8192, | |
| "model_type": "gemma", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 18, | |
| "num_key_value_heads": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 10000.0, | |
| "torch_dtype": "float32", | |
| "use_cache": true, | |
| "vocab_size": 257152 | |
| }, | |
| "architectures": [ | |
| "MWMForConditionalGeneration" | |
| ], | |
| "attention_implementation": "eager", | |
| "auto_map": { | |
| "AutoConfig": "configuration_mwm.MWMConfig", | |
| "AutoModel": "modeling_mwm.MWMForConditionalGeneration" | |
| }, | |
| "chunk_size": 30, | |
| "gen_expert_config": { | |
| "_attn_implementation_autoset": true, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "head_dim": 256, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "max_position_embeddings": 8192, | |
| "model_type": "gemma", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 18, | |
| "num_key_value_heads": 1, | |
| "num_resolutions": 4, | |
| "pn": "1_2_3_4_5_6_8_10_13_16", | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 10000.0, | |
| "temporal_conv_kernel_size": 4, | |
| "temporal_conv_stride": 4, | |
| "torch_dtype": "float32", | |
| "use_cache": true, | |
| "vae": { | |
| "ch": 160, | |
| "share_quant_resi": 4, | |
| "test_mode": true, | |
| "vae_ckpt": "/fs-computility/efm/shared/model_weights/var/vae_ch160v4096z32.pth", | |
| "vocab_size": 4096, | |
| "z_channels": 32 | |
| }, | |
| "vocab_size": 257152 | |
| }, | |
| "language_tokenizer_path": "/fs-computility/efm/shared/model_weights/paligemma-3b-pt-224", | |
| "max_action_dim": 32, | |
| "max_state_dim": 32, | |
| "model_type": "mwm", | |
| "num_steps": 10, | |
| "pretrained_path": "/fs-computility/efm/shared/model_weights/pi0/lerobot", | |
| "proj_width": 1024, | |
| "resize_imgs_with_padding": [ | |
| 224, | |
| 224 | |
| ], | |
| "tokenizer_max_length": 48, | |
| "transformers_version": "4.51.3", | |
| "und_expert_config": { | |
| "_attn_implementation_autoset": true, | |
| "_vocab_size": 257152, | |
| "bos_token_id": 2, | |
| "eos_token_id": 1, | |
| "hidden_size": 2048, | |
| "image_token_index": 257152, | |
| "model_type": "paligemma", | |
| "pad_token_id": 0, | |
| "projection_dim": 2048, | |
| "text_config": { | |
| "_attn_implementation_autoset": false, | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": null, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": 2, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": 1, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "head_dim": 256, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 2048, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 16384, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 8192, | |
| "min_length": 0, | |
| "model_type": "gemma", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 8, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_hidden_layers": 18, | |
| "num_image_tokens": 256, | |
| "num_key_value_heads": 1, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": 0, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 10000.0, | |
| "sep_token_id": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": "float32", | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "use_cache": true, | |
| "vocab_size": 257152 | |
| }, | |
| "vision_config": { | |
| "_attn_implementation_autoset": false, | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": null, | |
| "attention_dropout": 0.0, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": null, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "image_size": 224, | |
| "intermediate_size": 4304, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layer_norm_eps": 1e-06, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "model_type": "siglip_vision_model", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 16, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_channels": 3, | |
| "num_hidden_layers": 27, | |
| "num_image_tokens": 256, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "patch_size": 14, | |
| "prefix": null, | |
| "problem_type": null, | |
| "projection_dim": 2048, | |
| "projector_hidden_act": "gelu_fast", | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "sep_token_id": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": "float32", | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "vision_use_head": false | |
| } | |
| }, | |
| "use_cache": true, | |
| "use_world_model": true | |
| } | |