Kazuhiro Ohsawa
yamikumods
·
AI & ML interests
None yet
Organizations
None yet
yamikumods's activity
Usage in the model card seems to be ChatML format.
1
#1 opened 4 months ago
by
yamikumods
Will you re-upload these quants?
4
#2 opened 7 months ago
by
yamikumods
I'm generating a imatrix using `groups_merged.txt` if you want me to run any tests?
19
#15 opened 7 months ago
by
jukofyork
config.json: max_position_embeddings vs. model_max_length vs. total context
2
#24 opened 8 months ago
by
FlareRebellion
Any difference from Meta-Llama-3-70B-Instruct-4bit-mlx?
2
#2 opened 7 months ago
by
yamikumods
Fast work by the people on the llama.cpp team
3
#8 opened 8 months ago
by
qaraleza
Failed to load model?
1
#7 opened 8 months ago
by
yamikumods
iq3_xxs request
2
#1 opened 8 months ago
by
yamikumods
Failed to use Q8 model in LM Studio
3
#1 opened 8 months ago
by
rorrerror