Add decoder-only model files (encoder tensors removed) for Core ML encoder builds

README.md

@@ -31,7 +31,17 @@ Unzip an encoder next to its `.bin`: whisper.cpp built with Core ML finds `ggml-
 | `ggml-tiny.en-q5_1.bin` | 32,166,155 | `c77c5766f1cef09b6b7d47f21b546cbddd4157886b3b5d6d4f709e91e66c7c2b` |
 | `ggml-tiny.en-encoder.mlmodelc.zip` | 15,034,655 | `82b32eef73c94bb0c432a776a047b757d9525c26d84038a15d8798d7c8d1ee58` |
 
-All are byte-identical to the files at the revision above.
+The files above are byte-identical to the files at the revision above.
+
+## Decoder-only files
+
+- `ggml-tiny-q5_1-decoder.bin`: `ggml-tiny-q5_1.bin` with the encoder's tensors (`encoder.*`) removed, for whisper.cpp builds that run the encoder only through its Core ML encoder (Character Agent patches whisper.cpp to load these).
+- `ggml-tiny.en-q5_1-decoder.bin`: `ggml-tiny.en-q5_1.bin` with the encoder's tensors (`encoder.*`) removed, for whisper.cpp builds that run the encoder only through its Core ML encoder (Character Agent patches whisper.cpp to load these).
+
+| File | Bytes | SHA-256 |
+|---|---|---|
+| `ggml-tiny-q5_1-decoder.bin` | 23,388,163 | `8e892e9a3d7e8857543a07aa6197ab98131f069e9f46ecef15381cd4fca77200` |
+| `ggml-tiny.en-q5_1-decoder.bin` | 23,401,645 | `38190ac024471999a5830d8fb05d22951ed218323098b5c34b60d67f39526e60` |
 
 ## License
 

ggml-tiny-q5_1-decoder.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e892e9a3d7e8857543a07aa6197ab98131f069e9f46ecef15381cd4fca77200
+size 23388163

ggml-tiny.en-q5_1-decoder.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38190ac024471999a5830d8fb05d22951ed218323098b5c34b60d67f39526e60
+size 23401645