Hugging Face's logo
Undi's picture
336 2 32

Undi PRO

Undi95
antriksh7's profile picture kim512's profile picture locha117's profile picture
·
https://ko-fi.com/undiai

AI & ML interests

I search sleep

Recent Activity

updated a collection 3 days ago
Sushi
updated a model 3 days ago
Undi95/Sushi-v1.3
updated a model 3 days ago
Undi95/Sushi-v1.3-GGUF
View all activity

Organizations

Caldera AI's profile picture Pygmalion's profile picture unalignment's profile picture NeverSleep's profile picture OnlyThings's profile picture MinervaAI-Private's profile picture MinervaAI's profile picture Social Post Explorers's profile picture onlynow's profile picture NeverSleep - Historical's profile picture MergeFuel's profile picture He-He's profile picture MixtureMaxing's profile picture SillyTilly's profile picture Anthracite's profile picture OnlyNow2's profile picture 410's profile picture

Posts 7

view post
Post
13330
Exciting news!

After a long wait, Ikari and me finally made a new release of our last model on NeverSleep repo: Lumimaid-v0.2

This model can be used in different size, from the small Llama-3.1-8B to the gigantic Mistral-Large-123B, finetuned by us.

Try them now!

- NeverSleep/Lumimaid-v0.2-8B
- NeverSleep/Lumimaid-v0.2-12B
- NeverSleep/Lumimaid-v0.2-70B
- NeverSleep/Lumimaid-v0.2-123B

All the datasets we used will be added and credit will be given!
For the quant, we wait for fix to be applied (https://github.com/ggerganov/llama.cpp/pull/8676)
Hope you will enjoy them!
view post
Post
11839
Hello there,

New model released, my goal was to try finetune on the last Llama-3.1-8B-Instruct but not a small train, I wanted to do something useful.
One of the rare model that I didn't made for RP, or in the goal to uncensor it (but I did anyway kek).

The model was trained on 9M Claude conversations ONLY, giving him another writting style.

Undi95/Meta-Llama-3.1-8B-Claude > OG release fp32, it's the epoch 2
Undi95/Meta-Llama-3.1-8B-Claude-bf16 > Base model resharded in bf16 waiting for available quant without issues

Since it's frustrating to be censored using a local model, orthogonal activation steering was used, trying to force the model to never refuse a prompt.

Undi95/Meta-Llama-3.1-8B-Claude-68fail-3000total > Uncensored model, refuse 68 times on 3000 toxic prompt
Undi95/Meta-Llama-3.1-8B-Claude-39fail-3000total > Uncensored model, refuse 39 times on 3000 toxic prompt

It still refuse some prompt but the majority of them is uncensored. OAS can make a model more dumb or make the base perplexity go higher, so I didn't snipe for 0 refusal.

I don't do non-RP model a lot so any feedback is welcome, I would like to re-use this base for some others future project if needed.
View all posts

Collections 8