Amgad Hasan
amgadhasan
AI & ML interests
LLM
ASR
Organizations
amgadhasan's activity
Delete .DS_Store
#2 opened 3 days ago
by
amgadhasan
Which infra to run openai/whisper-large-v3-turbo ?
1
#7 opened 20 days ago
by
Jack0o
how many GPU memory do I need to finetune largeV3
4
#150 opened 2 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 about 1 month ago
by
chengligen
How to fine tuning with timestamps
2
#122 opened about 1 month ago
by
deepdml
Max sequence length
3
#2 opened about 1 month ago
by
amgadhasan
llama3.1 version
1
#3 opened 2 months ago
by
amgadhasan
Delete original
#1 opened 2 months ago
by
amgadhasan
What is the difference between this and official meta repo?
3
#9 opened 3 months ago
by
fzyzcjy
Issues with Fine-Tuning
9
#21 opened 3 months ago
by
ironrock
Phi-3.1?
1
#1 opened 3 months ago
by
amgadhasan
The model stops after generating one new token
2
#76 opened 4 months ago
by
rajiv-data-chef
Why the lower temperature?
2
#4 opened 3 months ago
by
amgadhasan
Wrong chat template
5
#1 opened 3 months ago
by
amgadhasan
Prompting Style?
1
#3 opened 3 months ago
by
xriminact
Add support for chat tempalte in llama.cpp
2
#1 opened 3 months ago
by
amgadhasan
Where is v1?
#2 opened 3 months ago
by
amgadhasan
Prompt Template?
3
#2 opened 3 months ago
by
amgadhasan
Add info about the prompt template
1
#4 opened 3 months ago
by
amgadhasan
Add chat template from mistralai/Mistral-7B-Instruct-v0.2
#3 opened 3 months ago
by
amgadhasan
Typo in winrates figure
1
#2 opened 5 months ago
by
amgadhasan
Difference vs v1?
1
#1 opened 7 months ago
by
amgadhasan
Is it possible to decrease vocabulary size?
2
#50 opened 9 months ago
by
omers66
Thanks
1
#2 opened 8 months ago
by
amgadhasan
Transcription and Translation In the same call
1
#81 opened 8 months ago
by
saalnlp
7B or 8B?
4
#24 opened 8 months ago
by
amgadhasan
Context length?
10
#2 opened 9 months ago
by
turboderp
How
2
#1 opened 9 months ago
by
amgadhasan
License
7
#4 opened 9 months ago
by
mrfakename
8x3B?
1
#2 opened 10 months ago
by
amgadhasan
Problem: Result from the NER prediction
1
#1 opened over 1 year ago
by
ffkharbat
License
1
#67 opened 10 months ago
by
amgadhasan
gguf
1
#3 opened 10 months ago
by
amgadhasan
Prompt Template?
3
#1 opened 10 months ago
by
amgadhasan
Apache 2.0?
2
#1 opened 10 months ago
by
amgadhasan
Is it suitable for translation?
2
#7 opened 10 months ago
by
amgadhasan
whisper outputs non stop no no no
3
#32 opened 11 months ago
by
rizwanishaq
Excellent model card
1
#4 opened 10 months ago
by
amgadhasan
How is this different from v1?
7
#2 opened 11 months ago
by
amgadhasan
When v2?
1
#88 opened 11 months ago
by
amgadhasan
What AWS instance/configuration/requirement will be for this model?
2
#87 opened 11 months ago
by
rikomi7571
Model size gets double when saving locally
3
#13 opened about 1 year ago
by
DhruvBhimani
how to evaluate use model-00001-of-00002.safetensors and model-00002-of-00002.safetensors
5
#36 opened 11 months ago
by
andyweiqiu
🚩 Report: Not working
#4 opened 11 months ago
by
amgadhasan
can i use this free ?
7
#18 opened 11 months ago
by
AamirFarooq
whisper v3
#88 opened 12 months ago
by
amgadhasan
License?
1
#1 opened 12 months ago
by
amgadhasan
Run it on Colab.
4
#4 opened 12 months ago
by
girrajjangid
tokenizer error
2
#2 opened about 1 year ago
by
amgadhasan
Two different prompt formats
3
#1 opened about 1 year ago
by
amgadhasan
Chat version
6
#4 opened about 1 year ago
by
amgadhasan
How to reproduce the results
1
#13 opened about 1 year ago
by
amgadhasan
More info
9
#1 opened over 1 year ago
by
amgadhasan
demo
#1 opened over 1 year ago
by
amgadhasan
Why is the inference api unavailable?
1
#8 opened over 1 year ago
by
amgadhasan