{ "norm_stats": { "libero_object_no_noops": { "action": { "mean": [ 0.07096531987190247, 0.13498827815055847, -0.04601384699344635, 0.001235201139934361, 0.006998842116445303, -0.015027613379061222, 0.46428999304771423 ], "std": [ 0.2681240439414978, 0.4384678304195404, 0.4474976658821106, 0.024446558207273483, 0.049355532974004745, 0.04210718721151352, 0.49879172444343567 ], "max": [ 0.9375, 0.8919642567634583, 0.9375, 0.17678570747375488, 0.35035714507102966, 0.1810714304447174, 1.0 ], "min": [ -0.8839285969734192, -0.9375, -0.9375, -0.15000000596046448, -0.29035714268684387, -0.32892856001853943, 0.0 ], "q01": [ -0.5383928418159485, -0.8758928775787354, -0.9375, -0.06964285671710968, -0.11678571254014969, -0.15964286029338837, 0.0 ], "q99": [ 0.8464285731315613, 0.84375, 0.9375, 0.08142857253551483, 0.14892856776714325, 0.0867857113480568, 1.0 ], "mask": [ true, true, true, true, true, true, false ] }, "proprio": { "mean": [ -0.02999032847583294, -0.007947112433612347, 0.20293493568897247, 3.108645439147949, -0.21404771506786346, -0.11307073384523392, 0.02938038855791092, -0.030556747689843178 ], "std": [ 0.06694898009300232, 0.1760847270488739, 0.07807070761919022, 0.08684837073087692, 0.33540451526641846, 0.20728285610675812, 0.009565756656229496, 0.009197475388646126 ], "max": [ 0.14580604434013367, 0.33216384053230286, 0.3857804834842682, 3.4003844261169434, 0.7954911589622498, 0.6642207503318787, 0.04104341194033623, -0.00018117300351150334 ], "min": [ -0.1765444278717041, -0.29457300901412964, 0.008128180168569088, 2.2890501022338867, -1.883241891860962, -1.0600427389144897, 0.0006495157140307128, -0.041782498359680176 ], "q01": [ -0.14911890715360643, -0.25978428691625594, 0.009925739830359817, 2.7545341420173646, -1.3996034812927245, -0.6867720144987106, 0.008197814421728254, -0.04015838988125324 ], "q99": [ 0.09063626825809479, 0.29066365867853167, 0.3370887073874472, 3.2611824750900267, 0.32092821151018125, 0.4037663781642913, 0.039891827926039694, -0.009106044843792932 ] }, "num_transitions": 66984, "num_trajectories": 454 } }, "n_action_bins": 256, "vision_backbone_id": "dinosiglip-vit-so-224px", "llm_backbone_id": "llama2-7b-pure", "arch_specifier": "no-align+fused-gelu-mlp", "output_projector_states": false, "use_fused_vision_backbone": true, "timm_model_ids": [ "vit_large_patch14_reg4_dinov2.lvd142m", "vit_so400m_patch14_siglip_224" ], "timm_override_act_layers": [ null, null ], "image_sizes": [ 224, 224 ], "image_resize_strategy": "resize-naive", "hf_llm_id": "meta-llama/Llama-2-7b-hf", "llm_max_length": 2048, "pad_token_id": 32000, "pad_to_multiple_of": 64, "text_config": { "vocab_size": 32064, "max_position_embeddings": 2048, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-06, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": "bfloat16", "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": null, "finetuning_task": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "tokenizer_class": null, "prefix": null, "bos_token_id": 1, "pad_token_id": 32000, "eos_token_id": 2, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "model_type": "llama" }, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": "bfloat16", "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": true, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": [ "OpenVLAForActionPrediction" ], "finetuning_task": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "tokenizer_class": null, "prefix": null, "bos_token_id": null, "eos_token_id": null, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "/data/juyi/hub/models--openvla--openvla-7b/snapshots/31f090d05236101ebfc381b61c674dd4746d4ce0", "_attn_implementation_autoset": true, "transformers_version": "4.47.0", "auto_map": { "AutoConfig": "configuration_prismatic.OpenVLAConfig", "AutoModelForVision2Seq": "modeling_prismatic.OpenVLAForActionPrediction" }, "model_type": "openvla" }