Upload 7 files

models/minivla-vq-libero90-prismatic/.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+prism-qwen25-dinosiglip-224px+0_5b+mx-libero-90+n1+b32+x7--vq_extra_tokenizer.jsonl filter=lfs diff=lfs merge=lfs -text

models/minivla-vq-libero90-prismatic/README.md

@@ -0,0 +1,40 @@
+---
+library_name: transformers
+tags:
+- robotics
+- vla
+- image-text-to-text
+- multimodal
+- pretraining
+license: mit
+language:
+- en
+pipeline_tag: image-text-to-text
+---
+
+# MiniVLA VQ 1B (Prismatic-Compatible Version)
+
+<b>This checkpoint is in a format that is compatible with the training script from the original [Prismatic VLMs project codebase](https://github.com/TRI-ML/prismatic-vlms), which the OpenVLA
+team built on top of to develop the OpenVLA model.</b>
+
+This Prismatic-compatible checkpoint may be useful if you wish to <b>fully fine-tune</b> MiniVLA (all 1 billion parameters) via native PyTorch Fully
+Sharded Data Parallel (FSDP) using the Prismatic VLMs training script. If you instead wish to do Parameter-Efficient Fine-Tuning via LoRA, you
+can use the MiniVLA checkpoint linked above, which is compatible with the Hugging Face `transformers` library. We recommend fine-tuning via LoRA if
+you do not have sufficient compute to fully fine-tune a 1B-parameter model (e.g., multiple A100/H100 GPUs).
+
+## Usage Instructions
+
+See the [MiniVLA GitHub README](https://github.com/Stanford-ILIAD/openvla-mini/blob/main/README.md) for instructions on how to use this checkpoint for full fine-tuning.
+
+## Citation
+
+**BibTeX:**
+
+```bibtex
+@article{belkhale24minivla,
+    title={MiniVLA: A Better VLA with a Smaller Footprint},
+    author={Suneel Belkhale and Dorsa Sadigh},
+    url={https://github.com/Stanford-ILIAD/openvla-mini}
+    year={2024}
+} 
+```

models/minivla-vq-libero90-prismatic/checkpoints/step-150000-epoch-67-loss=0.0934.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e99cfd157acca023e10b6b2d0305a2e4d480ff55a371646012404e9b32c3700b
+size 5554882540

models/minivla-vq-libero90-prismatic/config.json

@@ -0,0 +1,46 @@
+{
+  "data_root_dir": "/hai/scratch/belkhale/datasets",
+  "hf_token": ".hf_token",
+  "image_aug": false,
+  "is_resume": true,
+  "pretrained_checkpoint": "runs/prism-qwen25-dinosiglip-224px+0_5b+mx-libero-90+n1+b32+x7--vq_extra_tokenizer/checkpoints/step-065000-epoch-29-loss=0.4407.pt",
+  "resume_epoch": 29,
+  "resume_step": 65000,
+  "run_id": "prism-qwen25-dinosiglip-224px+0_5b+mx-libero-90+n1+b32+x7--vq_extra_tokenizer",
+  "run_id_note": "vq_extra_tokenizer",
+  "run_root_dir": "runs",
+  "save_interval": 2500,
+  "seed": 7,
+  "trackers": [
+    "jsonl",
+    "wandb"
+  ],
+  "vla": {
+    "action_tokenizer": "libero_vq_extra_action_tokenizer",
+    "base_vlm": "prism-qwen25-extra-dinosiglip-224px+0_5b",
+    "data_mix": "libero_90",
+    "enable_gradient_checkpointing": true,
+    "enable_mixed_precision_training": true,
+    "epochs": 1000,
+    "expected_world_size": 8,
+    "freeze_llm_backbone": false,
+    "freeze_vision_backbone": false,
+    "global_batch_size": 256,
+    "learning_rate": 2e-05,
+    "lr_scheduler_type": "constant",
+    "max_grad_norm": 1.0,
+    "max_steps": null,
+    "per_device_batch_size": 32,
+    "reduce_in_full_precision": true,
+    "save_every_n_steps": 25000,
+    "shuffle_buffer_size": 256000,
+    "train_strategy": "fsdp-full-shard",
+    "type": "prism-qwen25-dinosiglip-224px+0_5b+mx-libero-90",
+    "unfreeze_last_llm_layer": false,
+    "vla_id": "prism-qwen25-dinosiglip-224px+0_5b+mx-libero-90",
+    "warmup_ratio": 0.0,
+    "weight_decay": 0.0
+  },
+  "wandb_entity": null,
+  "wandb_project": "prismatic"
+}

models/minivla-vq-libero90-prismatic/config.yaml

@@ -0,0 +1,42 @@
+data_root_dir: /hai/scratch/belkhale/datasets
+hf_token: .hf_token
+image_aug: false
+is_resume: true
+pretrained_checkpoint: runs/prism-qwen25-dinosiglip-224px+0_5b+mx-libero-90+n1+b32+x7--vq_extra_tokenizer/checkpoints/step-065000-epoch-29-loss=0.4407.pt
+resume_epoch: 29
+resume_step: 65000
+run_id: prism-qwen25-dinosiglip-224px+0_5b+mx-libero-90+n1+b32+x7--vq_extra_tokenizer
+run_id_note: vq_extra_tokenizer
+run_root_dir: runs
+save_interval: 2500
+seed: 7
+trackers:
+- jsonl
+- wandb
+vla:
+  action_tokenizer: libero_vq_extra_action_tokenizer
+  base_vlm: prism-qwen25-extra-dinosiglip-224px+0_5b
+  data_mix: libero_90
+  enable_gradient_checkpointing: true
+  enable_mixed_precision_training: true
+  epochs: 1000
+  expected_world_size: 8
+  freeze_llm_backbone: false
+  freeze_vision_backbone: false
+  global_batch_size: 256
+  learning_rate: 2.0e-05
+  lr_scheduler_type: constant
+  max_grad_norm: 1.0
+  max_steps: null
+  per_device_batch_size: 32
+  reduce_in_full_precision: true
+  save_every_n_steps: 25000
+  shuffle_buffer_size: 256000
+  train_strategy: fsdp-full-shard
+  type: prism-qwen25-dinosiglip-224px+0_5b+mx-libero-90
+  unfreeze_last_llm_layer: false
+  vla_id: prism-qwen25-dinosiglip-224px+0_5b+mx-libero-90
+  warmup_ratio: 0.0
+  weight_decay: 0.0
+wandb_entity: null
+wandb_project: prismatic

models/minivla-vq-libero90-prismatic/dataset_statistics.json

@@ -0,0 +1,127 @@
+{
+  "libero_90": {
+    "action": {
+      "mean": [
+        0.04548764228820801,
+        0.037047673016786575,
+        -0.09770790487527847,
+        0.005058619659394026,
+        0.00224184594117105,
+        -0.006234025117009878,
+        0.528744101524353
+      ],
+      "std": [
+        0.2989887297153473,
+        0.361598402261734,
+        0.4069668650627136,
+        0.04840222746133804,
+        0.058257583528757095,
+        0.08737559616565704,
+        0.49890485405921936
+      ],
+      "max": [
+        0.9375,
+        0.9375,
+        0.9375,
+        0.375,
+        0.375,
+        0.375,
+        1.0
+      ],
+      "min": [
+        -0.9375,
+        -0.9375,
+        -0.9375,
+        -0.3257142901420593,
+        -0.375,
+        -0.375,
+        0.0
+      ],
+      "q01": [
+        -0.6321428418159485,
+        -0.8732143044471741,
+        -0.8973214030265808,
+        -0.12321428209543228,
+        -0.15642857551574707,
+        -0.2807142734527588,
+        0.0
+      ],
+      "q99": [
+        0.8517857193946838,
+        0.8464285731315613,
+        0.9375,
+        0.1875,
+        0.1778571456670761,
+        0.34928572177886963,
+        1.0
+      ],
+      "mask": [
+        true,
+        true,
+        true,
+        true,
+        true,
+        true,
+        false
+      ]
+    },
+    "proprio": {
+      "mean": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "std": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "max": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "min": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q01": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q99": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ]
+    },
+    "num_transitions": 569230,
+    "num_trajectories": 3924
+  }
+}

models/minivla-vq-libero90-prismatic/run-metrics.jsonl

@@ -0,0 +1 @@
+{"hparams": {"data_root_dir": "/hai/scratch/belkhale/datasets", "hf_token": ".hf_token", "image_aug": false, "is_resume": true, "pretrained_checkpoint": "runs/prism-qwen25-dinosiglip-224px+0_5b+mx-libero-90+n1+b32+x7--vq_extra_tokenizer/checkpoints/step-065000-epoch-29-loss=0.4407.pt", "resume_epoch": 29, "resume_step": 65000, "run_id": "prism-qwen25-dinosiglip-224px+0_5b+mx-libero-90+n1+b32+x7--vq_extra_tokenizer", "run_id_note": "vq_extra_tokenizer", "run_root_dir": "runs", "save_interval": 2500, "seed": 7, "trackers": ["jsonl", "wandb"], "vla": {"action_tokenizer": "libero_vq_extra_action_tokenizer", "base_vlm": "prism-qwen25-extra-dinosiglip-224px+0_5b", "data_mix": "libero_90", "enable_gradient_checkpointing": true, "enable_mixed_precision_training": true, "epochs": 1000, "expected_world_size": 8, "freeze_llm_backbone": false, "freeze_vision_backbone": false, "global_batch_size": 256, "learning_rate": 2e-05, "lr_scheduler_type": "constant", "max_grad_norm": 1.0, "max_steps": null, "per_device_batch_size": 32, "reduce_in_full_precision": true, "save_every_n_steps": 25000, "shuffle_buffer_size": 256000, "train_strategy": "fsdp-full-shard", "type": "prism-qwen25-dinosiglip-224px+0_5b+mx-libero-90", "unfreeze_last_llm_layer": false, "vla_id": "prism-qwen25-dinosiglip-224px+0_5b+mx-libero-90", "warmup_ratio": 0.0, "weight_decay": 0.0}, "wandb_entity": null, "wandb_project": "prismatic"}, "run_id": "prism-qwen25-dinosiglip-224px+0_5b+mx-libero-90+n1+b32+x7--vq_extra_tokenizer"}