Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
MohamedRashad 
posted an update 26 days ago
Post
1716
For those who love the Arabic language like me, This is a summary of my different models, datasets and spaces i made the last couple of months:

1. MohamedRashad/Arabic-Orpo-Llama-3-8B-Instruct is a finetuned version of Meta-Llama-3-8B-Instruct using ORPO on 2A2I/argilla-dpo-mix-7k-arabic and the space to try it is here MohamedRashad/Arabic-Chatbot-Arena.

2. MohamedRashad/arabic-small-nougat is a finetuned version of facebook/nougat-small on Arabic book pages to be a capable arabic-ocr and its space is also avialable here MohamedRashad/Arabic-Small-Nougat.

3. There is MohamedRashad/Arabic-CivitAi-Images dataset for text-to-image in the Arabic language (Hope someone utilize it to build something great).

4. MohamedRashad/arabic-sts for those who want to train an Arabic Text Embedder model.

5. Finally, a small arabic dataset about translation from Fusha Arabic to English called MohamedRashad/rasaif-translations (This dataset is very important in my opinion).

Salam Mohamed Rashad. Is there any GGUF version of these LLMs? Is there anyway to run an English to Arabic translation inside of Oobabooga? Choukran. Othmane.

·

Arabic ORPO has AWQ and GGUF quantization.
I would recommend AWQ over GGUF because i think there is bugs with llama.cpp with llama3 and may output to you rubbish.