Appreciate the model , Prefix caching not working
1
#16 opened 5 days ago
by
nimishchaudhari
Will there be a vision 8B model ?
1
#15 opened 7 days ago
by
thesby
Is this model more about technique validation or production ready usability?
2
#14 opened 8 days ago
by
weicj
Almost Impossible to run
3
#13 opened 9 days ago
by
LLaMA-lover
Reproducibility
2
#12 opened 9 days ago
by
RoflanVglorius
Impressive results
#11 opened 9 days ago
by
leonelcde
When will this be availbale on llama.cpp?
❤️🔥 16
3
#10 opened 10 days ago
by
Kendolph
gguf?
🚀 13
2
#7 opened 12 days ago
by
deniiiiiij
quantized and RSA
2
#5 opened 13 days ago
by
ainz
What is recommended top-p , temp, top-k etc. value for this model?
👍 2
1
#4 opened 13 days ago
by
acharyaaditya26
OOM on a RTX 4090 24GB
5
#3 opened 13 days ago
by
bird0867
Add community evaluation results for GPQA, MMLU-PRO
❤️ 2
#1 opened 15 days ago
by
nielsr