Amgad Hasan's picture

60 3 5

Amgad Hasan

amgadhasan

·

https://amgadhasan.com

AmgadHasan

AI & ML interests

LLM ASR

Recent Activity

updated a model 19 days ago

amgadhasan/phi-4

new activity 19 days ago

microsoft/phi-4:MIT

new activity 22 days ago

MadeAgents/Hammer2.1-7b:Request: More open License

View all activity

Organizations

amgadhasan's activity

updated a model 19 days ago

amgadhasan/phi-4

Text Generation • Updated 19 days ago • 303 • 3

New activity in microsoft/phi-4 19 days ago

MIT

#11 opened 19 days ago by

New activity in MadeAgents/Hammer2.1-7b 22 days ago

Request: More open License

#1 opened 22 days ago by

upvoted an article about 2 months ago

Article

Power steering: Squeeze massive power from small LLMs

By

•

Dec 9, 2024

• 4

updated a model 3 months ago

amgadhasan/sera-llama-3.1-8b-0.1

Text Generation • Updated Oct 24, 2024 • 3

updated a dataset 4 months ago

amgadhasan/longform-audio-transcription

Viewer • Updated Oct 9, 2024 • 3 • 6

New activity in openai/whisper-large-v3-turbo 4 months ago

Which infra to run openai/whisper-large-v3-turbo ?

#7 opened 4 months ago by

New activity in openai/whisper-large-v3 4 months ago

how many GPU memory do I need to finetune largeV3

#150 opened 5 months ago by

What is the accuracy of the model? Why can't I fine-tune when I set the accuracy to FP16?

#157 opened 5 months ago by

updated a model 4 months ago

amgadhasan/Meta-Llama-3.1-8B-Instruct

Text Generation • Updated Sep 22, 2024 • 7

New activity in openai/whisper 4 months ago

How to fine tuning with timestamps

#122 opened 5 months ago by

updated a model 5 months ago

Sera-Network/sera-llama-3.1-8b-0.1

Text Generation • Updated Sep 13, 2024 • 3 • 1

upvoted an article 5 months ago

Article

After 500+ LoRAs made, here is the secret

By

•

Oct 30, 2023

• 8

New activity in fixie-ai/ultravox-v0_4 5 months ago

Max sequence length

#2 opened 5 months ago by

updated a model 5 months ago

amgadhasan/lora-sera-llama-3.1-8b-0.1

Updated Sep 6, 2024

New activity in ibm-fms/llama3-8b-accelerator 6 months ago

llama3.1 version

#3 opened 6 months ago by

liked a model 6 months ago

ibm-fms/llama3-8b-accelerator

Updated May 15, 2024 • 22.3k • 15

New activity in NousResearch/Meta-Llama-3.1-8B-Instruct 6 months ago

Delete original

#1 opened 6 months ago by

liked a model 6 months ago

google/gemma-2-9b-it

Text Generation • Updated Aug 27, 2024 • 378k • • 636

New activity in NousResearch/Meta-Llama-3-8B-Instruct 6 months ago

What is the difference between this and official meta repo?

#9 opened 6 months ago by