Add BitVLA LIBERO I2S GGUF components

.gitattributes

@@ -33,3 +33,7 @@ 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
+bitvla-llm-i2s.gguf filter=lfs diff=lfs merge=lfs -text
+bitvla-vision-i2s.gguf filter=lfs diff=lfs merge=lfs -text
+bitvla-proprio-i2s.gguf filter=lfs diff=lfs merge=lfs -text
+bitvla-action-i2s.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,54 @@
+---
+license: mit
+base_model: hongyuw/ft-bitvla-bitsiglipL-224px-libero_spatial-bf16
+tags:
+- gguf
+- robotics
+- bitvla
+---
+
+# BitVLA LIBERO-Spatial I2S for Robot.cpp
+
+Four GGUF components for Robot.cpp's BitVLA runtime. The source is the author's
+[BitVLA checkpoint](https://huggingface.co/hongyuw/ft-bitvla-bitsiglipL-224px-libero_spatial-bf16/tree/df6d27c4ad2ce10ce510c68a6fb18130752130c7),
+revision `df6d27c4ad2ce10ce510c68a6fb18130752130c7`. This is the fine-tuned version without robotics pre-training.
+The normalization key is `libero_spatial_no_noops`.
+
+## Files and precision
+
+- `bitvla-llm-i2s.gguf`
+- `bitvla-vision-i2s.gguf`
+- `bitvla-proprio-i2s.gguf`
+- `bitvla-action-i2s.gguf`
+
+The converter applies BitVLA WeightQuant in BF16, then packs 366 ternary matrices
+as `i2s-matrix-v1`. Other tensors retain BF16/F32 storage. I2S is a Robot.cpp-specific
+layout; these files require its patched gguf/ggml runtime, not a standalone llama.cpp CLI.
+Use all four components from the same checkpoint.
+
+## Run
+
+Use [Robot.cpp with BitVLA support](https://github.com/Robot-cpp/robot.cpp/tree/cf0712c2751fdd8519de22f822b7baa1b08b5937) and apply its llama.cpp patches before building. Use a model-server binary built from this revision or a later compatible revision.
+
+```bash
+GGUF_DIR=/path/to/bitvla-libero-spatial-i2s
+/path/to/model-server \
+  --model-type bitvla \
+  --llm "${GGUF_DIR}/bitvla-llm-i2s.gguf" \
+  --mmproj "${GGUF_DIR}/bitvla-vision-i2s.gguf" \
+  --state-proj "${GGUF_DIR}/bitvla-proprio-i2s.gguf" \
+  --action-expert "${GGUF_DIR}/bitvla-action-i2s.gguf" \
+  --threads 8 --host 127.0.0.1 --port 5555
+```
+
+For these LIBERO checkpoints, send two 224×224 HWC RGB uint8 images in the `full_image`, then `wrist_image` order,
+eight raw proprio values, and a nonempty task instruction. Resize/crop images
+according to the source checkpoint's evaluation preprocessing before sending them.
+The runtime normalizes images/state and returns an 8×7 denormalized action chunk.
+Robot-specific action postprocessing remains the client's responsibility.
+
+## Validation
+
+Release checks verify all four GGUF headers and SHA256 hashes. Uploaded file sizes
+and SHA256 hashes are compared with the local conversion outputs. This model card
+does not claim a new success-rate, numerical-equivalence, or latency result.

bitvla-action-i2s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63548221d4f79b6635ffd03de3569d366e0b68083be266e81920030876c3481a
+size 118237952

bitvla-llm-i2s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:473650a9499027709211971cd2eb3bcb781638b74b1e95612747dfd683fa8c0c
+size 1187325312

bitvla-proprio-i2s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3a398f4aa7d7bc732323f358e2c5870f5973253e21a8c511fd9f42951668d52
+size 13169536

bitvla-vision-i2s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0deda233c8aa70a95ab38137d77173e0efe8f6042a66a0f1c54b41b9709a5f51
+size 121491936