Downloads · 30 days
0
Ichsan2895/Eval_Indo_LLM
Eval_Indo_LLM is a machine learning model from Ichsan2895. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
We try to evaluate the LLM model performance in Indonesian. There are many ways for calculate it, for example: BLEU, Perplexity, Human Eval, and GPT4 as Judge. However, In our opinion, we use Perplexity as it was the…
Downloads · 30 days
0
Access
Public
Updated Aug 13, 2023
Repo size
1.1 GB
Likes
0
Public
Click a slice to open those files.
.csv993 MB · 95%
From the Hugging Face model README
We try to evaluate the LLM model performance in Indonesian.
There are many ways for calculate it, for example: BLEU, Perplexity, Human Eval, and GPT4 as Judge.
However, In our opinion, we use Perplexity as it was the fastest way for big evaluation dataset.
If you have any faster and easier ways for calculating BLUE or any other metrics. Feel free to contribute in this repo.