Ammar
Daemontatox
AI & ML interests
NLP , LLMs , SSMs , SLMs
Organizations
Daemontatox's activity
Finetuning example ?
#37 opened about 21 hours ago
by
Daemontatox
Compared to nemo?
#1 opened 23 days ago
by
Daemontatox
Why not llama 3.1 ?
#1 opened 26 days ago
by
Daemontatox
🚩 Report: Ethical issue(s)
#67 opened 27 days ago
by
Daemontatox
Hallucinations
1
#1 opened 28 days ago
by
Daemontatox
Requirements to run ?
#3 opened 29 days ago
by
Daemontatox
Gemma2 hermes ?
#14 opened about 1 month ago
by
Daemontatox
Error when trying to quantize
#4 opened 3 months ago
by
Daemontatox
It looks the model is in 8K context length. May I ask why context length of Llama3.1 is 128K
2
#153 opened 25 days ago
by
tonyaw
model not working as intended
3
#14 opened 29 days ago
by
Daemontatox
Bad at Following Following instructions
3
#3 opened 26 days ago
by
Daemontatox
Is this a fraud?
1
#79 opened 26 days ago
by
funnewsr
Why dataset tag?
7
#1 opened 26 days ago
by
rombodawg
[bot] Conversion to Parquet
#1 opened about 2 months ago
by
parquet-converter
unable to inference
1
#1 opened about 1 month ago
by
Daemontatox
Update app.py
3
#3 opened about 1 month ago
by
John6666
Update app.py
#2 opened about 1 month ago
by
John6666
Quantization help?
2
#4 opened about 1 month ago
by
Daemontatox
Cant quantize
1
#36 opened about 1 month ago
by
Daemontatox
tensor size mismatch
2
#9 opened about 1 month ago
by
Daemontatox
Llama version?
#2 opened about 1 month ago
by
Daemontatox
mamba codestral support ?
2
#118 opened about 1 month ago
by
Daemontatox
Repeating generation prompt when answering
#1 opened 2 months ago
by
Daemontatox
too smart ?
2
#4 opened about 1 month ago
by
Daemontatox
Apply for community grant: Company project (gpu)
#1 opened 3 months ago
by
Daemontatox
ChatML template does not work properly
10
#2 opened about 1 month ago
by
WasamiKirua
Multilingual?
1
#1 opened about 2 months ago
by
Daemontatox
Amazing model!
1
#2 opened about 2 months ago
by
Daemontatox
Update README.md
#1 opened about 2 months ago
by
Daemontatox
Context length?
3
#3 opened about 2 months ago
by
SicariusSicariiStuff
The checkpoint you are trying to load has model type `falcon_mamba`
2
#1 opened about 2 months ago
by
loong
Fine tune code ?
2
#4 opened about 2 months ago
by
Daemontatox
[bot] Conversion to Parquet
#1 opened 2 months ago
by
parquet-converter
[bot] Conversion to Parquet
#1 opened 3 months ago
by
parquet-converter
[bot] Conversion to Parquet
#1 opened 3 months ago
by
parquet-converter
[bot] Conversion to Parquet
#1 opened 3 months ago
by
parquet-converter
error when trying to quantize NousResearch/Hermes-2-Theta-Llama-3-8B fine tuned model
1
#102 opened 3 months ago
by
Daemontatox
[bot] Conversion to Parquet
#1 opened 3 months ago
by
parquet-converter
Update requirements.txt
#1 opened 3 months ago
by
Daemontatox
gemma 9b with llama cpp b3259
1
#3 opened 3 months ago
by
sdyy