Flatten structure: remove subdirectory

README.md

@@ -1,39 +0,0 @@
----
-license: mit
-tags:
-  - mlx
-  - 4bit
-  - whisper
-  - stt
-  - metalrt
-  - apple-silicon
----
-
-# Whisper Tiny — MLX 4-bit Quantized
-
-Custom MLX 4-bit quantization of [OpenAI Whisper Tiny](https://huggingface.co/openai/whisper-tiny) optimized for [MetalRT](https://github.com/RunanywhereAI/metalrt-binaries) GPU inference on Apple Silicon.
-
-## Usage
-
-Used by [RCLI](https://github.com/RunanywhereAI/RCLI) with the MetalRT engine for speech-to-text:
-
-```bash
-rcli setup          # select MetalRT or Both engines
-```
-
-## Performance (Apple M3 Max)
-
-| Metric | Value |
-|--------|-------|
-| Latency (1.2s audio) | **46 ms** |
-| RTF | 0.04x |
-| Quantization | MLX 4-bit |
-
-## License
-
-Model weights: [MIT](https://github.com/openai/whisper/blob/main/LICENSE) (OpenAI)
-MetalRT engine: [Proprietary](https://github.com/RunanywhereAI/metalrt-binaries/blob/main/LICENSE) (RunAnywhere, Inc.)
-
-## Contact
-
-founder@runanywhere.ai | https://runanywhere.ai

whisper-tiny-mlx-4bit/config.json

@@ -1,17 +0,0 @@
-{
-    "model_type": "whisper",
-    "n_audio_ctx": 1500,
-    "n_audio_head": 6,
-    "n_audio_layer": 4,
-    "n_audio_state": 384,
-    "n_mels": 80,
-    "n_text_ctx": 448,
-    "n_text_head": 6,
-    "n_text_layer": 4,
-    "n_text_state": 384,
-    "n_vocab": 51865,
-    "quantization": {
-        "bits": 4,
-        "group_size": 64
-    }
-}