Undi PRO
Undi95
AI & ML interests
I search sleep
Organizations
Undi95's activity
Works pretty well. Fairly engaging. Seems to get stuck on a generalization sometimes.
2
#2 opened about 1 month ago
by
Nazosan
Any experiment results about this dataset?
5
#2 opened 8 days ago
by
Weyaxi
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6468ce47e134d050a58aa89c/ApFcPlOzgI6Cjr0SYPpk6.png)
EoS still isn't corrected to 128009?
1
#2 opened 11 days ago
by
Pyroserenus
Got Excellent Results in A RP Using This Model While Neutralizing Samplers
1
#1 opened 10 days ago
by
AlkaliV2
<START> needed?
1
#1 opened 11 days ago
by
Doomed1986
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/HP9e3Xfn5XlMdV3GINYJe.jpeg)
Prompt template fail in Jan.ai
2
#1 opened 12 days ago
by
refeirgrepus
Orthogonal Activation Steering
3
#2 opened 18 days ago
by
WesPro
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6580862babafd960c82ed31a/ABP_U3y_nISbDGqCHwXa2.png)
Llama 3 chat template not working?
1
#1 opened 19 days ago
by
Jdods84
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/zGvzXDS4qiETNviEWK2d-.jpeg)
Could you merge this model?
4
#4 opened 24 days ago
by
Elfrino
8x22B Inquiry
9
#4 opened about 1 month ago
by
OrangeApples
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/6rJmMwNSqswKhvckak5vn.jpeg)
Merge config
2
#2 opened about 1 month ago
by
khoantap
Preferable to the normal version
4
#2 opened about 1 month ago
by
JoggyMuffin
OAS before finetuning?
2
#1 opened about 1 month ago
by
zypcastles
ctx size?
1
#3 opened about 1 month ago
by
Lesani
avoid model generate *action*
4
#1 opened about 1 month ago
by
duongnghia222
Best model I've tried so far
3
#5 opened about 1 month ago
by
Klayhamn
![](https://cdn-avatars.huggingface.co/v1/production/uploads/65d9ca55e0ae639883de5ddb/93iqsX9h-dpH9jB1SkVus.jpeg)
i like -alt, what's the difference?
1
#3 opened about 1 month ago
by
ProphetOfBostrom
![](https://cdn-avatars.huggingface.co/v1/production/uploads/644dbb7d53ad80c6593bdee1/YulTWMLWulSy-DvpnxwZF.jpeg)
Very short responses on SillyTavern
4
#5 opened about 1 month ago
by
arnorex
Not starting up on Ollama compared to Undi95/Llama-3-LewdPlay-8B-evo-GGUF, exact same settings.
2
#1 opened about 1 month ago
by
askyforever
feedback
22
#2 opened about 2 months ago
by
Szarka
GGUF conversion is incorrect
4
#2 opened about 2 months ago
by
Noseu
DPO on top of OAS
2
#1 opened about 2 months ago
by
EloyOn
Adding `safetensors` variant of this model
#1 opened about 2 months ago
by
SFconvertbot
![](https://cdn-avatars.huggingface.co/v1/production/uploads/635fd4cc14657fb8cff2a081/GDkyDwAcuqDBpaOvQgJuq.png)
Reflecting changes in original repo with addition EOS token
5
#5 opened about 2 months ago
by
froggeric
![](https://cdn-avatars.huggingface.co/v1/production/uploads/65a681d3da9f6df1410562e9/WEM0smEQq8os99cMSmnoq.png)
Updating the GGUF files
4
#4 opened about 2 months ago
by
Armada22
Again an intrusive question.
1
#1 opened about 2 months ago
by
Debich
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/VYrIxaTuv6b4M-4yh17I2.png)
Silly Tavern Presets
1
#3 opened about 2 months ago
by
Firepin
I tried to create GGUF but it doesn't work. can you make one please?
2
#2 opened about 2 months ago
by
Ransss
![](https://cdn-avatars.huggingface.co/v1/production/uploads/643445297b824748010b120a/nTF86Y7WF6qoZlIJBn8OO.jpeg)
Evo vs non-Evo
1
#1 opened about 2 months ago
by
lazyDataScientist
![](https://cdn-avatars.huggingface.co/v1/production/uploads/633a39ec8f27255b6b571101/7J_BcRm7ua0WZNIGwEzlo.png)
When can we expect you to train llama 3 70B on a NSFW dataset?
1
#1 opened about 2 months ago
by
AS1200
FAILED model, can you put it back into the waiting list?
6
#665 opened 2 months ago
by
Undi95
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63ab1241ad514ca8d1430003/shjRx3yOP2eQvIyOWsQYV.png)
It's an excellent version, but...
20
#1 opened about 2 months ago
by
Anderson452
"We took great care to optimize helpfulness and safety."
4
#2 opened 2 months ago
by
Novelo
Master Undi, we all know what needs to be done.
3
#3 opened 2 months ago
by
MrHillsss
The new MMLU King
3
#3 opened 2 months ago
by
weezywitasneezy
![](https://cdn-avatars.huggingface.co/v1/production/uploads/632b22e66cb20ba0ae82bf06/VOdWxYveKRrp94yOLfv9w.png)
Abnormal response
1
#1 opened 2 months ago
by
l1280847857
iMatrix?
3
#1 opened 2 months ago
by
Nekotekina
Finetuning is very complicated, could you help?
10
#12 opened 3 months ago
by
Undi95
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63ab1241ad514ca8d1430003/shjRx3yOP2eQvIyOWsQYV.png)
Instruction format
3
#1 opened 2 months ago
by
duongnghia222
Preformance or comparision?
1
#1 opened 2 months ago
by
lazyDataScientist
![](https://cdn-avatars.huggingface.co/v1/production/uploads/633a39ec8f27255b6b571101/7J_BcRm7ua0WZNIGwEzlo.png)
EXL2 RPCAL - for those interested
1
#1 opened 2 months ago
by
zaq-hack
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63b534842bd3611e666bbdc3/TLhYkNTb7xKiKkyuBJAc1.png)
Results of testing.
6
#1 opened 3 months ago
by
Rance47
Quantized GGUF or exl2?
4
#1 opened 3 months ago
by
MLDataScientist
Hey thanks for using my model 😉
2
#1 opened 3 months ago
by
rombodawg
![](https://cdn-avatars.huggingface.co/v1/production/uploads/642cc1c253e76b4c2286c58e/fGtQ_QeTjUgBhIT89dpUt.jpeg)
Errors During Training for the Original Implementation and the Fixes for the Errors
1
#7 opened 3 months ago
by
v2ray
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/fTCV7VLY0eK4OXbwgIT2n.png)
Update README.md
1
#6 opened 3 months ago
by
Walmart-the-bag
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6530994e70a88b63f007324d/3oRlaZg34975k1wCxII6W.png)
thanks owo
1
#3 opened 3 months ago
by
v2ray
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/fTCV7VLY0eK4OXbwgIT2n.png)
Sliding window
1
#1 opened 3 months ago
by
saishf
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1675590698085-noauth.jpeg)
Please, authorize access for the base weight!
39
#5 opened 3 months ago
by
Undi95
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63ab1241ad514ca8d1430003/shjRx3yOP2eQvIyOWsQYV.png)
Missing config.json
8
#2 opened 5 months ago
by
Cayleb
It uses too much RAM for a 7B model
3
#1 opened 3 months ago
by
Kenshiro-28
Where's the Sauce?
3
#1 opened 3 months ago
by
Joseph717171
What’s the context size?
3
#1 opened 3 months ago
by
MarinaraSpaghetti
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6550b16f7490049d6237f200/xyq2CPV73PBdZTd6uu9Uc.png)
Excellent in my (limited) use-case
3
#2 opened 3 months ago
by
Kimikimis
Requesting a merge with LLaMA2-13B-Tiefighter
3
#6 opened 4 months ago
by
Xabab