Huge VRAM consumption with 32k context
#9 opened about 4 hours ago
by
fimbulvntr

Getting token embeddings instead of sentence embeddings
#8 opened about 6 hours ago
by
cicada330117
Typo: lunch a server
#7 opened 1 day ago
by
tyr75
GGUF conversion script
1
#6 opened 1 day ago
by
sarav1n
Missing LAST pooling setting
#5 opened 1 day ago
by
ngxson

Tried on android - looks like the tokenizers are broke
🧠
1
1
#4 opened 2 days ago
by
manancode
Can it be used with sentence-transformers?
2
#3 opened 2 days ago
by
zrzakhan
Support for Hugging Face's Text Embeddings Inference would be ideal.
👍
1
#2 opened 2 days ago
by
gaolegao2024