lyu-boxuan
/

llama-3-youko-8b-En-Ja-MT-LoRA

text-generation

machine translation

text-generation-inference

Model card Files Files and versions

lyu-boxuan commited on May 21, 2024

Commit

ec67359

·

verified ·

1 Parent(s): 915896e

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -13,7 +13,7 @@ pipeline_tag: translation
 ---
 # Overview
-This model is based on rinna's [rinna/llama-3-youko-8b], fine-tuned using LoRA on a small number of parallel sentences from English to Japanese. The model has a COMET (Unbabel/wmt22-comet-da) of 0.9031 and BLEU ("tok": "ja-mecab-0.996-IPA") of 34.0 on flores200 devtest.
 * **Model architecture**

 ---
 # Overview
+This model is based on rinna's [rinna/llama-3-youko-8b], fine-tuned using LoRA on a small number of parallel sentences from English to Japanese. The model has a COMET (Unbabel/wmt22-comet-da) of 0.9126 and BLEU ("tok": "ja-mecab-0.996-IPA") of 35.2 on flores200 devtest.
 * **Model architecture**