Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+pi05.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,64 @@
+---
+license: apache-2.0
+tags:
+  - pi0.5
+  - openpi
+  - gguf
+  - quantized
+  - vla
+base_model: zestcode5/ur3-5task-v1
+---
+
+# Pi 0.5 UR3 5-task — GGUF (Q8_0 LLM + Q4_K vision + Q5_K embed)
+
+Quantized GGUF export of `zestcode5/ur3-5task-v1` (step 6000) for inference with
+[OmniModel.cpp](https://github.com/) Pi 0.5 C++ runtime.
+
+## Quantization
+
+| Component        | Quant   | bpw   |
+|------------------|---------|-------|
+| Vision (SigLIP)  | Q4_K    | 4.55  |
+| Embedding        | Q5_K    | 5.50  |
+| PaliGemma LLM    | Q8_0    | 8.50  |
+| Action expert    | F16     | 16.0  |
+| **Total file**   | mixed   | **8.47** |
+
+File size: ~3.6 GB. V+LLM avg bpw: 7.38.
+
+## Files
+
+- `pi05.gguf` — unified GGUF (vision + projector + LLM + action expert + embedding + norm stats).
+- `tokenizer.model` — SentencePiece tokenizer (PaliGemma).
+- `norm_stats.json` — action/state mean/std/q01/q99 from the UR3 5-task dataset.
+
+## Tasks
+
+The base model was fine-tuned on `zestcode5/ur3-merged-5tasks-v1`. Calibration excluded
+"open the pot by removing its lid". Supported task prompts:
+
+- `pick up the pink cylinder and place it in the orange box`
+- `pick up the white glass and put on a brown coaster`
+- `Remove cup from nested cups`
+- `Single-finger push to blue marker`
+
+## Inference
+
+CLI:
+
+```
+./bin/pi05 -m /path/to/this/dir -i frame.png -p "<task prompt>" -d CUDA -s 10
+```
+
+WebSocket policy server (with the modified `serve_policy.py`):
+
+```
+uv run scripts/serve_policy.py policy:gguf \
+    --policy.dir=/path/to/this/dir \
+    --policy.device=CUDA --policy.steps=10 --policy.action-dim=7 \
+    --port=8000
+```
+
+Robot client uses OpenPI's `WebsocketClientPolicy` and sends an obs dict with
+keys `observation.images.fixed`, `observation.images.cam_wrist`,
+`observation.state` (11-dim), and `prompt`.

norm_stats.json

@@ -0,0 +1,90 @@
+{
+  "action_mean": [
+    -0.005246817599982023,
+    0.004768399987369776,
+    -0.0033975655678659678,
+    0.00031026932992972434,
+    0.0036542159505188465,
+    0.0013612688053399324,
+    0.5895225405693054
+  ],
+  "action_std": [
+    0.01949509233236313,
+    0.024492407217621803,
+    0.027331436052918434,
+    0.023165728896856308,
+    0.020561059936881065,
+    0.011431124061346054,
+    0.49192044138908386
+  ],
+  "action_q01": [
+    -0.0656973347067833,
+    -0.056118402630090714,
+    -0.06477333605289459,
+    -0.074713334441185,
+    -0.05702666565775871,
+    -0.024755600839853287,
+    0.0
+  ],
+  "action_q99": [
+    0.04932233318686485,
+    0.06897439807653427,
+    0.06892666965723038,
+    0.07499333471059799,
+    0.07797999680042267,
+    0.05098506435751915,
+    0.9998000264167786
+  ],
+  "state_mean": [
+    -0.506586492061615,
+    -0.039292529225349426,
+    0.05756710097193718,
+    -0.02392731048166752,
+    0.9943657517433167,
+    0.007554864976555109,
+    0.9939017295837402,
+    0.02348460629582405,
+    -0.005922637414187193,
+    0.589560866355896,
+    0.589560866355896
+  ],
+  "state_std": [
+    0.06114784628152847,
+    0.08564230799674988,
+    0.05101557821035385,
+    0.08927427232265472,
+    0.025002669543027878,
+    0.04485622048377991,
+    0.02506338618695736,
+    0.08926292508840561,
+    0.0545634850859642,
+    0.49191346764564514,
+    0.49191346764564514
+  ],
+  "state_q01": [
+    -0.610533595085144,
+    -0.20357808470726013,
+    -0.01586146093904972,
+    -0.4883570969104767,
+    0.8538995385169983,
+    -0.10944235324859619,
+    0.855462372303009,
+    -0.2302708476781845,
+    -0.1939956247806549,
+    0.0,
+    0.0
+  ],
+  "state_q99": [
+    -0.38722988963127136,
+    0.13152354955673218,
+    0.17774000763893127,
+    0.23073768615722656,
+    0.9999415874481201,
+    0.13705167174339294,
+    0.9999417066574097,
+    0.4878247380256653,
+    0.0853947103023529,
+    0.9998000264167786,
+    0.9998000264167786
+  ]
+}

pi05.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49f77bca1d8b72e7f85fcb1c692e074d06993dbd7abc42cb708985109a3429d6
+size 3587117824

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8986bb4f423f07f8c7f70d0dbe3526fb2316056c17bae71b1ea975e77a168fc6
+size 4264023