Request: DOI
1
#14 opened 6 days ago
by
pari-5461
Fine-tuned Gemma-3-1b model produces gibberish/empty output after quantization (GPTQ/AWQ/BitsAndBytes all fail)
1
#13 opened 3 months ago
by
grpathak22
Video Handling & Training
2
#9 opened 6 months ago
by
mosama
When evaluating Wiki2, I just get Loss: Nan, while with gemma-3-1b-it it works..
2
#8 opened 6 months ago
by
jonny-vr
Reproduce the reported benchmark score using LM Harness
👀
1
#7 opened 9 months ago
by
SimonX
Add missing torch when run with pipeline API
2
#5 opened 9 months ago
by
quocbao747