Undi PRO
Undi95
AI & ML interests
I search sleep
Organizations
Undi95's activity
8x22B Inquiry
5
#4 opened 2 days ago
by
OrangeApples
Merge config
2
#2 opened 5 days ago
by
khoantap
Preferable to the normal version
4
#2 opened 10 days ago
by
JoggyMuffin
OAS before finetuning?
2
#1 opened 11 days ago
by
zypcastles
ctx size?
1
#3 opened 11 days ago
by
Lesani
avoid model generate *action*
4
#1 opened 11 days ago
by
duongnghia222
Best model I've tried so far
3
#5 opened 11 days ago
by
Klayhamn
i like -alt, what's the difference?
1
#3 opened 13 days ago
by
ProphetOfBostrom
Very short responses on SillyTavern
4
#5 opened 14 days ago
by
arnorex
feedback
21
#2 opened 15 days ago
by
Szarka
GGUF conversion is incorrect
4
#2 opened 14 days ago
by
Noseu
DPO on top of OAS
2
#1 opened 14 days ago
by
EloyOn
Adding `safetensors` variant of this model
#1 opened 16 days ago
by
SFconvertbot
Reflecting changes in original repo with addition EOS token
5
#5 opened 28 days ago
by
froggeric
Updating the GGUF files
4
#4 opened 18 days ago
by
Armada22
Again an intrusive question.
1
#1 opened 19 days ago
by
Debich
Silly Tavern Presets
1
#3 opened 20 days ago
by
Firepin
I tried to create GGUF but it doesn't work. can you make one please?
2
#2 opened 27 days ago
by
Ransss
Evo vs non-Evo
1
#1 opened 22 days ago
by
lazyDataScientist
When can we expect you to train llama 3 70B on a NSFW dataset?
1
#1 opened 23 days ago
by
AS1200
FAILED model, can you put it back into the waiting list?
6
#665 opened about 1 month ago
by
Undi95
It's an excellent version, but...
20
#1 opened 28 days ago
by
Anderson452
"We took great care to optimize helpfulness and safety."
4
#2 opened about 1 month ago
by
Novelo
Master Undi, we all know what needs to be done.
3
#3 opened 30 days ago
by
MrHillsss
The new MMLU King
3
#3 opened about 1 month ago
by
weezywitasneezy
Abnormal response
1
#1 opened about 1 month ago
by
l1280847857
iMatrix?
3
#1 opened about 1 month ago
by
Nekotekina
Finetuning is very complicated, could you help?
10
#12 opened about 2 months ago
by
Undi95
Instruction format
3
#1 opened about 1 month ago
by
duongnghia222
Preformance or comparision?
1
#1 opened about 1 month ago
by
lazyDataScientist
EXL2 RPCAL - for those interested
1
#1 opened about 1 month ago
by
zaq-hack
Results of testing.
6
#1 opened about 2 months ago
by
Rance47
Quantized GGUF or exl2?
4
#1 opened about 2 months ago
by
MLDataScientist
Hey thanks for using my model 😉
2
#1 opened about 2 months ago
by
rombodawg
Errors During Training for the Original Implementation and the Fixes for the Errors
1
#7 opened about 2 months ago
by
v2ray
Update README.md
1
#6 opened about 2 months ago
by
Walmart-the-bag
thanks owo
1
#3 opened about 2 months ago
by
v2ray
Sliding window
1
#1 opened about 2 months ago
by
saishf
Please, authorize access for the base weight!
39
#5 opened about 2 months ago
by
Undi95
Missing config.json
8
#2 opened 4 months ago
by
Cayleb
It uses too much RAM for a 7B model
3
#1 opened about 2 months ago
by
Kenshiro-28
Where's the Sauce?
3
#1 opened about 2 months ago
by
Joseph717171
What’s the context size?
3
#1 opened about 2 months ago
by
MarinaraSpaghetti
Excellent in my (limited) use-case
3
#2 opened about 2 months ago
by
Kimikimis
Requesting a merge with LLaMA2-13B-Tiefighter
3
#6 opened 3 months ago
by
Xabab
Personal experience was terrible.
4
#1 opened 2 months ago
by
Eilian
Problem with finetuning with Axolotl (qlora, lora, and FFT)
6
#1 opened 2 months ago
by
Undi95
This is THE best AI I've come across!
7
#5 opened 3 months ago
by
elluAI
Very Important question
1
#2 opened 2 months ago
by
cubestarx
Using Alpaca prompt format
3
#1 opened 2 months ago
by
Jdods84
Can I see a sample dataset?
1
#3 opened 2 months ago
by
kbuwel
TrinityMaid-13b
6
#5 opened 3 months ago
by
Joseph717171
Context lenght?
10
#1 opened 3 months ago
by
xxx777xxxASD
Why not post the lora?
1
#2 opened 3 months ago
by
jackboot