M Asad Iqbal's picture

5 1 26

M Asad Iqbal

MAsad789565

·

AI & ML interests

None yet

Recent Activity

replied to MohamedRashad's post 9 days ago

I think we have released the best Arabic model under 25B at least based on https://huggingface.co/spaces/inceptionai/AraGen-Leaderboard Yehia = https://huggingface.co/ALLaM-AI/ALLaM-7B-Instruct-preview + GRPO and its ranked number one model under the 25B parameter size mark. Now, i said "i think" not "i am sure" because this model used the same metric of evaluation the AraGen developers use (the 3C3H) as a reward model to improve its responses and this sparks the question. Is this something good for users or is it another type of overfitting that we don't want ? I don't know if this is a good thing or a bad thing but what i know is that you can try it from here: https://huggingface.co/spaces/Navid-AI/Yehia-7B-preview or Download it for your personal experiments from here: https://huggingface.co/Navid-AI/Yehia-7B-preview Ramadan Kareem 🌙

reacted to MohamedRashad's post with ❤️ 9 days ago

I think we have released the best Arabic model under 25B at least based on https://huggingface.co/spaces/inceptionai/AraGen-Leaderboard Yehia = https://huggingface.co/ALLaM-AI/ALLaM-7B-Instruct-preview + GRPO and its ranked number one model under the 25B parameter size mark. Now, i said "i think" not "i am sure" because this model used the same metric of evaluation the AraGen developers use (the 3C3H) as a reward model to improve its responses and this sparks the question. Is this something good for users or is it another type of overfitting that we don't want ? I don't know if this is a good thing or a bad thing but what i know is that you can try it from here: https://huggingface.co/spaces/Navid-AI/Yehia-7B-preview or Download it for your personal experiments from here: https://huggingface.co/Navid-AI/Yehia-7B-preview Ramadan Kareem 🌙

liked a dataset 3 months ago

TuneIt/o1-python

View all activity

Organizations

MAsad789565's activity

New activity in Hansimov/hf-llm-api 11 months ago

[Feature Addition Request] - Web Search

#5 opened 11 months ago by

Model Adding Request

#1 opened 12 months ago by

New activity in aws-neuron/optimum-neuron-cache 12 months ago

[Cache Request] abacaj/phi-2-super

#29 opened 12 months ago by

New activity in MAsad789565/llmfine about 1 year ago

Your training has failed ❌

#2 opened about 1 year ago by

Your training has failed ❌

#1 opened about 1 year ago by