Upload OpenVLA grasp model checkpoint

action_head--27000_checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8b43be82e89ef0f2c8d6ac814d93fb7bb24dcc5343289ed1a504e425c9bbbfc
+size 604453726

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<PAD>": 32000
+}

config.json

@@ -0,0 +1,415 @@
+{
+  "norm_stats": {
+    "gen72_grasp_stacking_cloth": {
+      "action": {
+        "mean": [
+          62.43017578125,
+          87.67520904541016,
+          -81.64241790771484,
+          -79.35697174072266,
+          -5.861265659332275,
+          10.143360137939453,
+          -2.90120792388916,
+          72.50067138671875,
+          -77.66656494140625,
+          86.92049407958984,
+          84.2964096069336,
+          -83.40449523925781,
+          5.118907928466797,
+          3.7968454360961914,
+          5.422410488128662,
+          86.0960922241211
+        ],
+        "std": [
+          26.70451545715332,
+          15.426373481750488,
+          25.905000686645508,
+          19.544811248779297,
+          22.8100643157959,
+          23.047954559326172,
+          19.49391746520996,
+          41.80753707885742,
+          29.825439453125,
+          14.745803833007812,
+          21.135257720947266,
+          22.255817413330078,
+          18.003395080566406,
+          18.94203758239746,
+          16.219724655151367,
+          32.87356948852539
+        ],
+        "max": [
+          166.1999969482422,
+          102.0,
+          18.280000686645508,
+          52.0,
+          169.0,
+          92.24500274658203,
+          152.92999267578125,
+          100.0,
+          52.90999984741211,
+          102.0,
+          169.0,
+          52.0,
+          121.50499725341797,
+          76.7300033569336,
+          119.13500213623047,
+          100.0
+        ],
+        "min": [
+          -16.790000915527344,
+          -35.904998779296875,
+          -169.0,
+          -98.3499984741211,
+          -105.63999938964844,
+          -86.56999969482422,
+          -108.1050033569336,
+          0.0,
+          -146.47000122070312,
+          -50.494998931884766,
+          -37.04499816894531,
+          -97.7300033569336,
+          -157.6750030517578,
+          -82.2699966430664,
+          -140.4949951171875,
+          0.0
+        ],
+        "q01": [
+          11.6899995803833,
+          30.454999923706055,
+          -126.7388484954834,
+          -96.11000061035156,
+          -66.4000015258789,
+          -51.33000183105469,
+          -55.10885036468506,
+          0.0,
+          -109.25,
+          28.17919984817505,
+          18.235000610351562,
+          -97.12000274658203,
+          -25.17080009460449,
+          -51.85499954223633,
+          -48.34000015258789,
+          0.0
+        ],
+        "q99": [
+          102.73999786376953,
+          102.0,
+          -13.369199647902697,
+          1.790799961090833,
+          47.369998931884766,
+          66.31500244140625,
+          48.95500183105469,
+          100.0,
+          -2.109999895095825,
+          102.0,
+          116.62999725341797,
+          10.723850355148409,
+          61.6588496017457,
+          51.77000045776367,
+          44.34000015258789,
+          100.0
+        ],
+        "mask": [
+          true,
+          true,
+          true,
+          true,
+          true,
+          true,
+          true,
+          true,
+          true,
+          true,
+          true,
+          true,
+          true,
+          true,
+          true,
+          true
+        ]
+      },
+      "proprio": {
+        "mean": [
+          62.37788391113281,
+          87.68936157226562,
+          -81.61447143554688,
+          -79.36709594726562,
+          -5.8816938400268555,
+          10.13486385345459,
+          -2.892655849456787,
+          72.50101470947266,
+          -77.6031723022461,
+          86.94501495361328,
+          84.27079772949219,
+          -83.39244079589844,
+          5.130640983581543,
+          3.7632524967193604,
+          5.420851707458496,
+          86.09623718261719
+        ],
+        "std": [
+          25.871257781982422,
+          14.867486953735352,
+          25.252859115600586,
+          18.814409255981445,
+          22.16670036315918,
+          21.30392837524414,
+          18.7672061920166,
+          41.807701110839844,
+          29.216785430908203,
+          14.115077018737793,
+          20.53180503845215,
+          21.84934425354004,
+          17.31168556213379,
+          17.874422073364258,
+          15.709982872009277,
+          32.87362289428711
+        ],
+        "max": [
+          160.5500030517578,
+          102.02999877929688,
+          13.489999771118164,
+          52.02000045776367,
+          159.24000549316406,
+          89.77999877929688,
+          143.4199981689453,
+          100.0,
+          50.060001373291016,
+          102.08999633789062,
+          169.00999450683594,
+          52.029998779296875,
+          116.55999755859375,
+          69.1500015258789,
+          107.02999877929688,
+          100.0
+        ],
+        "min": [
+          -14.3100004196167,
+          -33.93000030517578,
+          -169.00999450683594,
+          -98.05000305175781,
+          -101.91000366210938,
+          -81.33000183105469,
+          -100.11000061035156,
+          0.0,
+          -141.3000030517578,
+          -48.31999969482422,
+          -29.790000915527344,
+          -97.66999816894531,
+          -147.30999755859375,
+          -80.5999984741211,
+          -131.22000122070312,
+          0.0
+        ],
+        "q01": [
+          12.260000228881836,
+          32.06999969482422,
+          -125.55999755859375,
+          -95.9000015258789,
+          -64.44999694824219,
+          -46.470001220703125,
+          -52.880001068115234,
+          0.0,
+          -108.62000274658203,
+          30.662299900054933,
+          19.889999389648438,
+          -97.11000061035156,
+          -23.90999984741211,
+          -48.310001373291016,
+          -46.52769916534424,
+          0.0
+        ],
+        "q99": [
+          101.80999755859375,
+          102.01000213623047,
+          -15.149999618530273,
+          -0.8115000146618113,
+          45.9900016784668,
+          62.34000015258789,
+          47.220001220703125,
+          100.0,
+          -3.6346001100536434,
+          102.01000213623047,
+          115.7300033569336,
+          9.609999656677246,
+          59.17769981384296,
+          48.88999938964844,
+          42.459999084472656,
+          100.0
+        ]
+      },
+      "num_transitions": 296424,
+      "num_trajectories": 498
+    }
+  },
+  "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,
+    "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": "",
+    "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": "openvla/openvla-7b",
+  "transformers_version": "4.40.1",
+  "auto_map": {
+    "AutoConfig": "openvla/openvla-7b--configuration_prismatic.OpenVLAConfig",
+    "AutoModelForVision2Seq": "openvla/openvla-7b--modeling_prismatic.OpenVLAForActionPrediction"
+  },
+  "model_type": "openvla"
+}

dataset_statistics.json

@@ -0,0 +1,244 @@
+{
+  "gen72_grasp_stacking_cloth": {
+    "action": {
+      "mean": [
+        62.43017578125,
+        87.67520904541016,
+        -81.64241790771484,
+        -79.35697174072266,
+        -5.861265659332275,
+        10.143360137939453,
+        -2.90120792388916,
+        72.50067138671875,
+        -77.66656494140625,
+        86.92049407958984,
+        84.2964096069336,
+        -83.40449523925781,
+        5.118907928466797,
+        3.7968454360961914,
+        5.422410488128662,
+        86.0960922241211
+      ],
+      "std": [
+        26.70451545715332,
+        15.426373481750488,
+        25.905000686645508,
+        19.544811248779297,
+        22.8100643157959,
+        23.047954559326172,
+        19.49391746520996,
+        41.80753707885742,
+        29.825439453125,
+        14.745803833007812,
+        21.135257720947266,
+        22.255817413330078,
+        18.003395080566406,
+        18.94203758239746,
+        16.219724655151367,
+        32.87356948852539
+      ],
+      "max": [
+        166.1999969482422,
+        102.0,
+        18.280000686645508,
+        52.0,
+        169.0,
+        92.24500274658203,
+        152.92999267578125,
+        100.0,
+        52.90999984741211,
+        102.0,
+        169.0,
+        52.0,
+        121.50499725341797,
+        76.7300033569336,
+        119.13500213623047,
+        100.0
+      ],
+      "min": [
+        -16.790000915527344,
+        -35.904998779296875,
+        -169.0,
+        -98.3499984741211,
+        -105.63999938964844,
+        -86.56999969482422,
+        -108.1050033569336,
+        0.0,
+        -146.47000122070312,
+        -50.494998931884766,
+        -37.04499816894531,
+        -97.7300033569336,
+        -157.6750030517578,
+        -82.2699966430664,
+        -140.4949951171875,
+        0.0
+      ],
+      "q01": [
+        11.6899995803833,
+        30.454999923706055,
+        -126.7388484954834,
+        -96.11000061035156,
+        -66.4000015258789,
+        -51.33000183105469,
+        -55.10885036468506,
+        0.0,
+        -109.25,
+        28.17919984817505,
+        18.235000610351562,
+        -97.12000274658203,
+        -25.17080009460449,
+        -51.85499954223633,
+        -48.34000015258789,
+        0.0
+      ],
+      "q99": [
+        102.73999786376953,
+        102.0,
+        -13.369199647902697,
+        1.790799961090833,
+        47.369998931884766,
+        66.31500244140625,
+        48.95500183105469,
+        100.0,
+        -2.109999895095825,
+        102.0,
+        116.62999725341797,
+        10.723850355148409,
+        61.6588496017457,
+        51.77000045776367,
+        44.34000015258789,
+        100.0
+      ],
+      "mask": [
+        true,
+        true,
+        true,
+        true,
+        true,
+        true,
+        true,
+        true,
+        true,
+        true,
+        true,
+        true,
+        true,
+        true,
+        true,
+        true
+      ]
+    },
+    "proprio": {
+      "mean": [
+        62.37788391113281,
+        87.68936157226562,
+        -81.61447143554688,
+        -79.36709594726562,
+        -5.8816938400268555,
+        10.13486385345459,
+        -2.892655849456787,
+        72.50101470947266,
+        -77.6031723022461,
+        86.94501495361328,
+        84.27079772949219,
+        -83.39244079589844,
+        5.130640983581543,
+        3.7632524967193604,
+        5.420851707458496,
+        86.09623718261719
+      ],
+      "std": [
+        25.871257781982422,
+        14.867486953735352,
+        25.252859115600586,
+        18.814409255981445,
+        22.16670036315918,
+        21.30392837524414,
+        18.7672061920166,
+        41.807701110839844,
+        29.216785430908203,
+        14.115077018737793,
+        20.53180503845215,
+        21.84934425354004,
+        17.31168556213379,
+        17.874422073364258,
+        15.709982872009277,
+        32.87362289428711
+      ],
+      "max": [
+        160.5500030517578,
+        102.02999877929688,
+        13.489999771118164,
+        52.02000045776367,
+        159.24000549316406,
+        89.77999877929688,
+        143.4199981689453,
+        100.0,
+        50.060001373291016,
+        102.08999633789062,
+        169.00999450683594,
+        52.029998779296875,
+        116.55999755859375,
+        69.1500015258789,
+        107.02999877929688,
+        100.0
+      ],
+      "min": [
+        -14.3100004196167,
+        -33.93000030517578,
+        -169.00999450683594,
+        -98.05000305175781,
+        -101.91000366210938,
+        -81.33000183105469,
+        -100.11000061035156,
+        0.0,
+        -141.3000030517578,
+        -48.31999969482422,
+        -29.790000915527344,
+        -97.66999816894531,
+        -147.30999755859375,
+        -80.5999984741211,
+        -131.22000122070312,
+        0.0
+      ],
+      "q01": [
+        12.260000228881836,
+        32.06999969482422,
+        -125.55999755859375,
+        -95.9000015258789,
+        -64.44999694824219,
+        -46.470001220703125,
+        -52.880001068115234,
+        0.0,
+        -108.62000274658203,
+        30.662299900054933,
+        19.889999389648438,
+        -97.11000061035156,
+        -23.90999984741211,
+        -48.310001373291016,
+        -46.52769916534424,
+        0.0
+      ],
+      "q99": [
+        101.80999755859375,
+        102.01000213623047,
+        -15.149999618530273,
+        -0.8115000146618113,
+        45.9900016784668,
+        62.34000015258789,
+        47.220001220703125,
+        100.0,
+        -3.6346001100536434,
+        102.01000213623047,
+        115.7300033569336,
+        9.609999656677246,
+        59.17769981384296,
+        48.88999938964844,
+        42.459999084472656,
+        100.0
+      ]
+    },
+    "num_transitions": 296424,
+    "num_trajectories": 498
+  }
+}

lora_adapter/README.md

@@ -0,0 +1,202 @@
+---
+base_model: openvla/openvla-7b
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

lora_adapter/adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "OpenVLAForActionPrediction",
+    "parent_library": "prismatic.extern.hf.modeling_prismatic"
+  },
+  "base_model_name_or_path": "/home/guangyu/.cache/huggingface/hub/models--openvla--openvla-7b/snapshots/31f090d05236101ebfc381b61c674dd4746d4ce0",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "fc3",
+    "kv",
+    "fc2",
+    "fc1",
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "qkv",
+    "q_proj",
+    "q",
+    "lm_head",
+    "proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

lora_adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30e622a5edd99860f8630faf4db977421ed2785f8bef108f7017cd5d117dde4e
+size 484467800

preprocessor_config.json

@@ -0,0 +1,114 @@
+{
+  "auto_map": {
+    "AutoImageProcessor": "openvla/openvla-7b--processing_prismatic.PrismaticImageProcessor",
+    "AutoProcessor": "openvla/openvla-7b--processing_prismatic.PrismaticProcessor"
+  },
+  "image_processor_type": "PrismaticImageProcessor",
+  "image_resize_strategy": "resize-naive",
+  "input_sizes": [
+    [
+      3,
+      224,
+      224
+    ],
+    [
+      3,
+      224,
+      224
+    ]
+  ],
+  "interpolations": [
+    "bicubic",
+    "bicubic"
+  ],
+  "means": [
+    [
+      0.485,
+      0.456,
+      0.406
+    ],
+    [
+      0.5,
+      0.5,
+      0.5
+    ]
+  ],
+  "processor_class": "PrismaticProcessor",
+  "stds": [
+    [
+      0.229,
+      0.224,
+      0.225
+    ],
+    [
+      0.5,
+      0.5,
+      0.5
+    ]
+  ],
+  "tvf_crop_params": [
+    {
+      "output_size": [
+        224,
+        224
+      ]
+    },
+    {
+      "output_size": [
+        224,
+        224
+      ]
+    }
+  ],
+  "tvf_do_letterbox": false,
+  "tvf_letterbox_fill": null,
+  "tvf_normalize_params": [
+    {
+      "inplace": false,
+      "mean": [
+        0.484375,
+        0.455078125,
+        0.40625
+      ],
+      "std": [
+        0.228515625,
+        0.2236328125,
+        0.224609375
+      ]
+    },
+    {
+      "inplace": false,
+      "mean": [
+        0.5,
+        0.5,
+        0.5
+      ],
+      "std": [
+        0.5,
+        0.5,
+        0.5
+      ]
+    }
+  ],
+  "tvf_resize_params": [
+    {
+      "antialias": true,
+      "interpolation": 3,
+      "max_size": null,
+      "size": [
+        224,
+        224
+      ]
+    },
+    {
+      "antialias": true,
+      "interpolation": 3,
+      "max_size": null,
+      "size": [
+        224,
+        224
+      ]
+    }
+  ],
+  "use_fused_vision_backbone": true
+}

proprio_projector--27000_checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8d17aba5beabf0dc6921886f5585afa212cfa556cc9cc933d6fe70b6374b54c
+size 67406320

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "auto_map": {
+    "AutoProcessor": "openvla/openvla-7b--processing_prismatic.PrismaticProcessor"
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<PAD>",
+  "padding_side": "right",
+  "processor_class": "PrismaticProcessor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

vision_backbone--27000_checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2869d70431d7d50b5bda0c0efac1a2346d3a436a9e490aa5b2eb2f87291b8e0
+size 3344957817