[]
Kenshiro-28
·
AI & ML interests
None yet
Recent Activity
New activity
about 1 month ago
Sao10K/Euryale-2.2-q4-gguf:Best model i've tried so far
Organizations
None yet
Kenshiro-28's activity
Best model i've tried so far
3
#1 opened 3 months ago
by
Szarka
CORRECTION: THIS SYSTEM MESSAGE IS ***PURE GOLD***!!!
16
#33 opened 3 months ago
by
jukofyork
"llama.cpp error: 'error loading model vocabulary: unknown pre-tokenizer type: 'dolphin12b''"
23
#1 opened 4 months ago
by
jrell
Feedback
14
#1 opened 6 months ago
by
TravelingMan
Reacted to
Undi95's
post with 🔥
7 months ago
It uses too much RAM for a 7B model
3
#1 opened 8 months ago
by
Kenshiro-28
Great model! I suggest switching to ChatML prompt format for next versions.
#8 opened 9 months ago
by
Kenshiro-28
Bad EOS
2
#5 opened 10 months ago
by
Kenshiro-28
Bad EOS
2
#6 opened 10 months ago
by
Kenshiro-28
Bad EOS
#1 opened 10 months ago
by
Kenshiro-28
Bad EOS token
#1 opened 11 months ago
by
Kenshiro-28
Prompt format
1
#2 opened 11 months ago
by
Kenshiro-28
The model doesn't report the ChatML EOS token
2
#1 opened about 1 year ago
by
Kenshiro-28
ChatML prompt format confusion - please reconsider
36
#3 opened about 1 year ago
by
kalomaze
The best model
3
#1 opened about 1 year ago
by
Kenshiro-28
Change prompt format to Vicuna v1.1
2
#7 opened over 1 year ago
by
Kenshiro-28
Change prompt format to Vicuna v1.1
2
#7 opened over 1 year ago
by
Kenshiro-28
Change prompt format to Vicuna v1.1
2
#7 opened over 1 year ago
by
Kenshiro-28