Upload folder using huggingface_hub

.gitattributes

@@ -27,9 +27,12 @@ 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
+*.litertlm filter=lfs diff=lfs merge=lfs -text
+*.task 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
+supergemma4-e4b-abliterated.litertlm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,104 @@
+---
+license: gemma
+library_name: litert-lm
+base_model:
+  - google/gemma-4-E4B-it
+  - Jiunsong/supergemma4-e4b-abliterated
+tags:
+  - litert-lm
+  - gemma
+  - gemma4
+  - apple-silicon
+  - text-generation
+  - on-device
+  - abliterated
+pipeline_tag: text-generation
+---
+
+# SuperGemma 4 E4B Abliterated — LiteRT-LM
+
+> ⚠️ **Unofficial build.** This LiteRT-LM package is **not** published by
+> Google, the LiteRT team, or `Jiunsong` — it is a community conversion.
+> Because of int4/int8 re-quantisation during packaging, outputs may
+> differ from the source
+> [`Jiunsong/supergemma4-e4b-abliterated`](https://huggingface.co/Jiunsong/supergemma4-e4b-abliterated)
+> checkpoint and, in particular, the abliterated behaviour may be
+> attenuated on some prompts. For reference behaviour, run the source
+> checkpoint directly (e.g. via `transformers`) or use the
+> [MLX 4-bit companion build](https://huggingface.co/Jiunsong/supergemma4-e4b-abliterated-mlx)
+> on Apple Silicon.
+
+On-device build of
+[`Jiunsong/supergemma4-e4b-abliterated`](https://huggingface.co/Jiunsong/supergemma4-e4b-abliterated)
+in the `.litertlm` format for the
+[LiteRT-LM](https://github.com/google-ai-edge/LiteRT-LM) runtime
+(Android, iOS, macOS, Linux, Windows, Web).
+
+Companion Apple-Silicon-targeted builds for this fine-tune:
+
+| Target | Repo |
+|---|---|
+| **LiteRT-LM** (this repo) — CPU + Metal GPU via LiteRT-LM CLI / Android / iOS / Desktop | `litert-lm` format, 3.65 GB |
+| [MLX 4-bit](https://huggingface.co/Jiunsong/supergemma4-e4b-abliterated-mlx) | MLX safetensors, Mac Studio class local serving |
+
+The LiteRT-LM bundle is the path for cross-platform on-device deployment
+(Android, iOS, Desktop, Web — all through the same file). The MLX build
+above is the fastest option for local serving on macOS specifically.
+
+## Base models
+
+- [`google/gemma-4-E4B-it`](https://huggingface.co/google/gemma-4-E4B-it) —
+  the original Gemma 4 E4B instruct checkpoint.
+- [`Jiunsong/supergemma4-e4b-abliterated`](https://huggingface.co/Jiunsong/supergemma4-e4b-abliterated) —
+  the abliterated fine-tune. Abliteration removes the refusal direction
+  from the residual stream; see the source card for release behaviour notes.
+
+## Run it
+
+### CLI (fastest way to try it)
+
+```bash
+uv tool install litert-lm  # one-time
+
+# Run directly from this HF repo, on Apple Silicon Metal GPU:
+litert-lm run --from-huggingface-repo typomonster/supergemma4-e4b-abliterated-litert-lm \
+              supergemma4-e4b-abliterated.litertlm \
+              --prompt "Write a three-sentence story about a robot who discovers music." \
+              --backend gpu \
+              --enable-speculative-decoding=false
+```
+
+`--backend gpu` routes through `libLiteRtMetalAccelerator` on macOS ARM64;
+measured ~40 tok/s decode on Metal vs ~13 tok/s on CPU (M-series, your
+mileage will vary).
+
+`--enable-speculative-decoding=false` is recommended — see the caveats.
+
+### Platform SDKs
+
+- **Android / iOS / Desktop**: see the
+  [LiteRT-LM documentation](https://ai.google.dev/edge/litert-lm/overview)
+  for platform integration guides.
+- **Python**: see `python/litert_lm/examples/simple_main.py` in the
+  [LiteRT-LM repo](https://github.com/google-ai-edge/LiteRT-LM).
+
+## Caveats
+
+1. **Soft-refusal behaviour may be attenuated** vs. the source
+   HF fine-tune. If you need the strongest abliterated behaviour on Apple
+   Silicon, use the MLX build linked above.
+
+2. **Run with `--enable-speculative-decoding=false`**. The MTP drafter in
+   this bundle may have a reduced accept rate against the modified main
+   model. Speculative decoding remains correct (the main model verifies
+   each proposed token) but is not guaranteed to be a speedup here.
+
+## License
+
+This build inherits the [Gemma license](https://ai.google.dev/gemma/terms)
+from its upstream bases. Review the terms there before redistribution.
+
+## Acknowledgements
+
+- Upstream model: `google/gemma-4-E4B-it` (Google DeepMind).
+- Abliteration fine-tune: `Jiunsong/supergemma4-e4b-abliterated`.

supergemma4-e4b-abliterated.litertlm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83399794f0ad10166c0034451e06b9cdb120590eab3665863ff20e443b3f9750
+size 3654467584