Update README.md
Browse files
README.md
CHANGED
@@ -5,4 +5,5 @@ license: other
|
|
5 |
* Experimental Cebuano fine-tune: safe or accurate outputs not guaranteed (not for production use)!
|
6 |
* Observing fine-tune effects on dataset of roughly 10k lines of Cebuano (roughly formatted/"raw" chat)
|
7 |
* Trained on llama 7b chat for 1 epoch
|
8 |
-
* May still generate English, Tagalog, Taglish, or gibberish.
|
|
|
|
5 |
* Experimental Cebuano fine-tune: safe or accurate outputs not guaranteed (not for production use)!
|
6 |
* Observing fine-tune effects on dataset of roughly 10k lines of Cebuano (roughly formatted/"raw" chat)
|
7 |
* Trained on llama 7b chat for 1 epoch
|
8 |
+
* May still generate English, Tagalog, Taglish, or gibberish.
|
9 |
+
* [QLoras (hf and GGML)](https://huggingface.co/922-Narra/cebuano-lm-lora-tests/tree/main/lc2_08212023a)
|