Hugging Face's logo
Amgad Hasan's picture
58 3 5

Amgad Hasan

amgadhasan
fivetech's profile picture AhmedAshrafMarzouk's profile picture DrUmairKhan's profile picture
·
https://amgadhasan.com

AI & ML interests

LLM ASR

Recent Activity

updated a model 6 days ago
amgadhasan/phi-4
upvoted an article 12 days ago
Power steering: Squeeze massive power from small LLMs
updated a model about 2 months ago
amgadhasan/sera-llama-3.1-8b-0.1
View all activity

Organizations

Sahl AI's profile picture Sera Incorporated's profile picture

amgadhasan's activity

New activity in openai/whisper-large-v3-turbo 3 months ago

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

1
#7 opened 3 months ago by
Jack0o
New activity in openai/whisper-large-v3 3 months ago

how many GPU memory do I need to finetune largeV3

4
#150 opened 4 months ago by
lanejohn

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

1
#157 opened 3 months ago by
chengligen
New activity in openai/whisper 3 months ago

How to fine tuning with timestamps

2
#122 opened 3 months ago by
deepdml
New activity in fixie-ai/ultravox-v0_4 3 months ago

Max sequence length

3
#2 opened 3 months ago by
amgadhasan
New activity in ibm-fms/llama3-8b-accelerator 4 months ago

llama3.1 version

1
#3 opened 4 months ago by
amgadhasan
New activity in NousResearch/Meta-Llama-3.1-8B-Instruct 4 months ago

Delete original
#1 opened 4 months ago by
amgadhasan
New activity in NousResearch/Meta-Llama-3-8B-Instruct 4 months ago

What is the difference between this and official meta repo?

3
#9 opened 5 months ago by
fzyzcjy
New activity in mistralai/Mistral-Nemo-Instruct-2407 5 months ago

Issues with Fine-Tuning

9
#21 opened 5 months ago by
ironrock
New activity in ZeroWw/Phi-3-mini-4k-instruct-GGUF 5 months ago

Phi-3.1?

1
#1 opened 5 months ago by
amgadhasan
New activity in microsoft/Phi-3-mini-4k-instruct 5 months ago

The model stops after generating one new token

2
#76 opened 6 months ago by
rajiv-data-chef
New activity in mistralai/Mistral-Nemo-Instruct-2407 5 months ago

Why the lower temperature?

2
#4 opened 5 months ago by
amgadhasan
New activity in bartowski/Lite-Mistral-150M-v2-Instruct-GGUF 5 months ago

Wrong chat template

5
#1 opened 5 months ago by
amgadhasan
New activity in HuggingFaceTB/SmolLM-360M-Instruct 5 months ago

Prompting Style?

1
#3 opened 5 months ago by
xriminact
New activity in OuteAI/Lite-Mistral-150M-v2-Instruct-GGUF 5 months ago

Add support for chat tempalte in llama.cpp

2
#1 opened 5 months ago by
amgadhasan
New activity in OuteAI/Lite-Mistral-150M-v2-Instruct 5 months ago

Where is v1?
#2 opened 5 months ago by
amgadhasan
New activity in mlabonne/NeuralDaredevil-7B 5 months ago

Prompt Template?

3
#2 opened 5 months ago by
amgadhasan

Add info about the prompt template

1
#4 opened 5 months ago by
amgadhasan

Add chat template from mistralai/Mistral-7B-Instruct-v0.2
#3 opened 5 months ago by
amgadhasan
New activity in CohereForAI/aya-23-8B 7 months ago

Typo in winrates figure

1
#2 opened 7 months ago by
amgadhasan