Undi PRO
Undi95
AI & ML interests
I search sleep
Organizations
Undi95's activity
Explain these Benchmark Results
2
#2 opened about 21 hours ago
by
Joseph717171
Update README.md
#3 opened 18 days ago
by
CombinHorizon
This is a pretty amazing model for 12B.
3
#3 opened about 2 months ago
by
Cypherfox
Possible to make another Toppy-esqe model based on Mistral Minitron?
#6 opened about 1 month ago
by
Hpub
another type of this model?
2
#4 opened about 1 month ago
by
nreyad
Commercial use
1
#5 opened about 2 months ago
by
Hpub
Dev + Schnell (50 steps)?
4
#1 opened about 2 months ago
by
bjohnson22
Is it possible for us to try out the 4th model?
4
#2 opened 2 months ago
by
ParasiticRogue
Feedback
4
#1 opened 2 months ago
by
MarinaraSpaghetti
Frankemerge
4
#7 opened 2 months ago
by
DazzlingXeno
What is OAS?
3
#1 opened 2 months ago
by
GhostGate
EXL2 quants
16
#3 opened 2 months ago
by
Cytho
Extreme repetition
5
#1 opened 2 months ago
by
itsnottme
Recommended settings
1
#2 opened 2 months ago
by
isr431
Did something go wrong during training?
6
#6 opened 2 months ago
by
CamiloMM
NeverSleep/Lumimaid-v0.2-8B-GGUF CRASH in Koboldcpp
6
#1 opened 2 months ago
by
Jdods84
An MoE of nemo I assume??
4
#1 opened 2 months ago
by
bartowski
My alternative quantizations.
5
#3 opened 2 months ago
by
ZeroWw
Feedback
5
#5 opened 2 months ago
by
SerialKicked
Any chance you can start providing quants for 24GB cards?
15
#1 opened 2 months ago
by
RazielAU
exception in koboldcpp
3
#2 opened 2 months ago
by
Szarka
Has this been converted with the recent llama.cpp patches applied?
1
#1 opened 2 months ago
by
FlareRebellion
GGUF quants?
1
#2 opened 2 months ago
by
Iommed
Conversion F32 -> BF16
1
#5 opened 2 months ago
by
Undi95
Gptq or GGUF
6
#2 opened 2 months ago
by
XiphosLyacris
NoRobots is not in the training data for this one?
7
#1 opened 2 months ago
by
Jdods84
Llama 3.1 version?
4
#3 opened 2 months ago
by
Jdods84
aqlm format
3
#3 opened 2 months ago
by
nreyad
error when loading this model
2
#1 opened 2 months ago
by
InspiredBubbles
Traning Details
2
#1 opened 2 months ago
by
Cossale
My alternative quantizations.
2
#1 opened 2 months ago
by
ZeroWw
Works pretty well. Fairly engaging. Seems to get stuck on a generalization sometimes.
2
#2 opened 5 months ago
by
Nazosan
Any experiment results about this dataset?
5
#2 opened 4 months ago
by
Weyaxi
EoS still isn't corrected to 128009?
1
#2 opened 4 months ago
by
Pyroserenus
Got Excellent Results in A RP Using This Model While Neutralizing Samplers
1
#1 opened 4 months ago
by
AlkaliV2
<START> needed?
1
#1 opened 4 months ago
by
Doomed1986
Prompt template fail in Jan.ai
2
#1 opened 4 months ago
by
refeirgrepus
Orthogonal Activation Steering
3
#2 opened 4 months ago
by
WesPro
Llama 3 chat template not working?
1
#1 opened 4 months ago
by
Jdods84
Could you merge this model?
4
#4 opened 4 months ago
by
Elfrino
8x22B Inquiry
9
#4 opened 5 months ago
by
OrangeApples
Merge config
2
#2 opened 5 months ago
by
khoantap
Preferable to the normal version
4
#2 opened 5 months ago
by
JoggyMuffin
OAS before finetuning?
2
#1 opened 5 months ago
by
zypcastles
ctx size?
1
#3 opened 5 months ago
by
Lesani
avoid model generate *action*
4
#1 opened 5 months ago
by
duongnghia222
Best model I've tried so far
3
#5 opened 5 months ago
by
Klayhamn
i like -alt, what's the difference?
1
#3 opened 5 months ago
by
ProphetOfBostrom
Very short responses on SillyTavern
4
#5 opened 5 months ago
by
arnorex
Not starting up on Ollama compared to Undi95/Llama-3-LewdPlay-8B-evo-GGUF, exact same settings.
2
#1 opened 5 months ago
by
askyforever
feedback
22
#2 opened 5 months ago
by
Szarka
GGUF conversion is incorrect
4
#2 opened 5 months ago
by
Noseu
DPO on top of OAS
2
#1 opened 5 months ago
by
EloyOn
Adding `safetensors` variant of this model
#1 opened 5 months ago
by
SFconvertbot
Reflecting changes in original repo with addition EOS token
5
#5 opened 6 months ago
by
froggeric