Why is the generated content always the same when I use this model?
#7 opened 9 months ago
by
LiMuyi
Phi 3 tokenizer_config has been updated upstream
#6 opened about 1 year ago
by
smcleod
Mistake in readme instructions
2
2
#5 opened about 1 year ago
by
adamkdean
gibberish results when context is greater 2048
9
#4 opened about 1 year ago
by
Bakanayatsu
Do they work with ollama? How was the conversion done for 128K, llama.cpp/convert.py complains about ROPE.
8
#2 opened about 1 year ago
by
BigDeeper