Q4_K_S suspiciously small
#2
by
PartyParrot
- opened
The Meta-Llama-3-8B-Instruct.Q4_K_S.gguf quant is much smaller than the other models (1.75 GB vs 4GB+). I haven't checked it, but there might be something wrong with it.
It got interrupted in middle of upload, uploading again
amongus
Hey this should be fixed now. Reuploaded with the fixed end token
0-hero
changed discussion status to
closed