m

README.md

@@ -6,6 +6,12 @@ This repo catalogs my weights for use with my [VALL-E](https://github.com/e-c-k-
 
 The model currently is in a *usable* state under `ar+nar-llama-8` (the default model thats downloaded).
 
+## Branches
+
+The [GGUF](https://huggingface.co/ecker/vall-e/tree/gguf) branch contains [`vall_e.cpp`](https://github.com/e-c-k-e-r/vall-e/commits/master/vall_e.cpp/) weights.
+
+The [HF](https://huggingface.co/ecker/vall-e/tree/gguf) branch contains an HF-ified version of the model weights.
+
 ## Models
 
 This repo contains the following configurations under `./models/`:
@@ -138,4 +144,4 @@ Using a LoRA is the same as a base model, except you're required to have the bas
 The only caveat is that my original dataset *does* contain (most of) these samples already, but given the sheer size of it, they're probably underutilized.
 * However, the base model already has *almost adequate* output from these speakers, but not enough to be satisfactory.
 
-LoRAs under `ckpt[ar+nar-old-llama-8]` are LoRAs married to an older checkpoint, while `ckpt` *should* work under the reference model. 
+LoRAs under `ckpt[ar+nar-old-llama-8]` are LoRAs married to an older checkpoint, while `ckpt` *should* work under the reference model.