MC
mclassHF2023
AI & ML interests
None yet
Organizations
None yet
mclassHF2023's activity
calme-2.1 for qwen2-7b?
1
#17 opened 3 months ago
by
mclassHF2023
Why context 8k?
1
#4 opened 4 months ago
by
mclassHF2023
Context length of the model?
5
#30 opened 4 months ago
by
shipWr3ck
4k context by default?
1
#1 opened 4 months ago
by
mclassHF2023
which mistral version in the merge?
1
#1 opened 4 months ago
by
mclassHF2023
context size
1
#1 opened 4 months ago
by
lightsoutallout
Great work!
1
#3 opened 5 months ago
by
mclassHF2023
blocky blocky blocky
3
#1 opened 5 months ago
by
mclassHF2023
no system message?
8
#14 opened 6 months ago
by
mclassHF2023
what kind of model is this?
#1 opened 6 months ago
by
mclassHF2023
32k or 8k context?
2
#1 opened 6 months ago
by
mclassHF2023
higher context with alpha_value=2.5
#1 opened 6 months ago
by
mclassHF2023
original model gone / output bad for 16k context?
1
#1 opened 6 months ago
by
mclassHF2023
model doesn't stop generating
1
#2 opened 6 months ago
by
mclassHF2023
Higher context support?
1
#4 opened 6 months ago
by
aayushg159
GGUF
1
#1 opened 6 months ago
by
mclassHF2023
files?
2
#1 opened 6 months ago
by
mclassHF2023
Thanks for the fix!
#1 opened 7 months ago
by
mclassHF2023
Ollama can not create
4
#5 opened 7 months ago
by
jiyintor
INST spamming issue
4
#2 opened 7 months ago
by
Varkoyote