Upload README.md with huggingface_hub

README.md

@@ -1,27 +1,53 @@
 ---
-license: agpl-3.0
+library_name: litertlm
+license: apache-2.0
 tags:
-- gemma
+- heretic
+- uncensored
+- decensored
+- abliterated
+- ara
 - litertlm
 - android
+- on-device
+- litert
+pipeline_tag: any-to-any
+base_model:
+- google/gemma-4-E2B-it-qat-q4_0-unquantized
+license_link: https://ai.google.dev/gemma/docs/gemma_4_license
 ---
 
 # gemma-4-E2B-it-qat-heretic-LiteRT
 
-Gemma 4 E2B converted to the LiteRT-LM (`.litertlm`) format for on-device
-inference with [LiteRT-LM](https://github.com/google-ai-edge/litert-lm) /
-the Free Slopdroid Android app.
+> [!NOTE]
+> This is a **quantized / format-converted derivative** of an upstream
+> checkpoint, repackaged into the LiteRT-LM (`.litertlm`) format for
+> on-device inference. It is **not** a retrained or fine-tuned model — the
+> weights are the upstream checkpoint's, reformatted for LiteRT-LM.
 
-## Source & method
+## Model details
 
+- **Format:** LiteRT-LM `.litertlm` (weights + tokenizer + graph in one file)
+- **Runtime:** [LiteRT-LM](https://github.com/google-ai-edge/litert-lm) (XNNPACK CPU / OpenCL GPU)
 - **Source checkpoint:** `coder3101/gemma-4-E2B-it-qat-q4_0-unquantized-heretic`
-- **Quantization:** `mixed48` (Google gemma4 mixed 4/8-bit mobile scheme)
+- **Base model(s):**
 
-Produced with the Free Slopdroid `convert_gemma4.py` converter (export ->
-quantize -> package), which runs the same three stages as the
-[Google docs](https://github.com/google-ai-edge/ai-edge-quantizer/tree/main).
+- `google/gemma-4-E2B-it-qat-q4_0-unquantized`
+
+- **Quantization:** `mixed48` (Google gemma4 mixed 4/8-bit mobile scheme (INT4 weights + INT8 projections))
+- **License:** `apache-2.0` + [Gemma Terms of Use](https://ai.google.dev/gemma/docs/gemma_4_license)
+
+## How it was produced
+
+Converted with `convert_gemma4.py`, which runs the same three stages described in the [Google ai-edge-quantizer docs](https://github.com/google-ai-edge/ai-edge-quantizer/tree/main):
+
+1. **Export** — HF checkpoint (PyTorch/safetensors) → float TFLite flatbuffer (via `litert-torch` `export_hf`)
+2. **Quantize** — float TFLite → quantized TFLite (via `ai-edge-quantizer` recipe `mixed48`)
+3. **Package** — quantized TFLite → `.litertlm` bundle (via `litert-torch` `litert_lm_builder`)
+
+No weights were modified, retrained, or merged — only reformatted and quantized.
 
 ## Usage
 
-Place `model.litertlm` under the app's models folder on the device and the
-app loads it automatically. See the Free Slopdroid README for details.
+Load `model.litertlm` with any LiteRT-LM runtime or client. Place it under your
+app's models folder and the runtime loads it automatically.