Undi95/Phi4-abliterated
Updated
•
118
•
6
Aton Mountlook
AtonMountlook
AI & ML interests
None yet
Recent Activity
liked
a model
2 days ago
Undi95/Phi4-abliterated
Organizations
None yet
AtonMountlook's activity
liked
a
model
2 days ago
liked
a
model
5 months ago
upvoted
a
collection
6 months ago
reacted to
Undi95's
post with ❤️
6 months ago
Post
12790
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.
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.
-
- 4 replies
liked
2
models
8 months ago
reacted to
Undi95's
post with 🤗
8 months ago
Post
16480
Hey everyone,
Just wanted to shout out a massive thank you to all 2000 of you who've followed me on Hugging Face! 🎉 It's incredible to have such an awesome crew backing me up as I dive into all these LLM experiments.
Even though not all my models turn out perfect, I've found some real gems and methods along the way 💎. It's like digging for treasure – sometimes you found nothing, but sometimes you find a pearl, and sometimes you find a new method to try.
Your support and encouragement mean the world to me, and I'm really stoked to keep experimenting and learning. If you told me some years ago I would have so much people following me for what I do, I wouldn't have believed it. Here's to more discoveries and adventures ahead! 🚀
Also, big thanks once again, and a huge shoutout to @IkariDev for being there through this journey and supporting me. I'm excited for our future work together and hope we will continue to make people happy! 👏
I want to thank @Gryphe too, since my early work was heavily inspired from MythoMax and the RP/ERP vibe of it. If I'm here today it's probably because of you 😂
I was so close to forget @chargoddard and his amazing tool too! What will we do without mergekit in our life? Thank you! 🙏
See y'all at 3k!
Just wanted to shout out a massive thank you to all 2000 of you who've followed me on Hugging Face! 🎉 It's incredible to have such an awesome crew backing me up as I dive into all these LLM experiments.
Even though not all my models turn out perfect, I've found some real gems and methods along the way 💎. It's like digging for treasure – sometimes you found nothing, but sometimes you find a pearl, and sometimes you find a new method to try.
Your support and encouragement mean the world to me, and I'm really stoked to keep experimenting and learning. If you told me some years ago I would have so much people following me for what I do, I wouldn't have believed it. Here's to more discoveries and adventures ahead! 🚀
Also, big thanks once again, and a huge shoutout to @IkariDev for being there through this journey and supporting me. I'm excited for our future work together and hope we will continue to make people happy! 👏
I want to thank @Gryphe too, since my early work was heavily inspired from MythoMax and the RP/ERP vibe of it. If I'm here today it's probably because of you 😂
I was so close to forget @chargoddard and his amazing tool too! What will we do without mergekit in our life? Thank you! 🙏
See y'all at 3k!
- 5 replies
reacted to
abhishek's
post with 🔥
9 months ago
Post
3477
With AutoTrain, you can already finetune the latest llama3 models without writing a single line of code. Here's an example finetune of llama3 8b model:
abhishek/autotrain-llama3-no-robots
- 2 replies
reacted to
Undi95's
post with 👍
10 months ago
Post
Hey, it took some time but I finally moved out and got internet back, so here I am again!
A lot of things to get updated on, I will try to reply to each of you ASAP.
See you soon!
A lot of things to get updated on, I will try to reply to each of you ASAP.
See you soon!
- 1 reply
reacted to
DmitryRyumin's
post with 👍
10 months ago
Post
1605
🚀🎭🌟 New Research Alert! 🌟 🎭🚀
📄 Title: FlashFace: Human Image Personalization with High-fidelity Identity Preservation 🔝
📝 Description: FlashFace is a personalized photo editing tool that focuses on high-fidelity identity preservation and improved compliance through advanced encoding and integration strategies.
👥 Authors: Shilong Zhang, Lianghua Huang, @xichenhku et al.
🔗 Paper: FlashFace: Human Image Personalization with High-fidelity Identity Preservation (2403.17008)
🌐 Github Page: https://jshilong.github.io/flashface-page
📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
🚀 Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36
🔍 Keywords: #FlashFace #Personalization #HighFidelityIdentity #DeepLearning #Innovation
📄 Title: FlashFace: Human Image Personalization with High-fidelity Identity Preservation 🔝
📝 Description: FlashFace is a personalized photo editing tool that focuses on high-fidelity identity preservation and improved compliance through advanced encoding and integration strategies.
👥 Authors: Shilong Zhang, Lianghua Huang, @xichenhku et al.
🔗 Paper: FlashFace: Human Image Personalization with High-fidelity Identity Preservation (2403.17008)
🌐 Github Page: https://jshilong.github.io/flashface-page
📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
🚀 Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36
🔍 Keywords: #FlashFace #Personalization #HighFidelityIdentity #DeepLearning #Innovation
liked
4
models
10 months ago
liked
a
dataset
10 months ago
reacted to
Undi95's
post with ❤️
10 months ago
Post
Hey, it took some time but I finally moved out and got internet back, so here I am again!
A lot of things to get updated on, I will try to reply to each of you ASAP.
See you soon!
A lot of things to get updated on, I will try to reply to each of you ASAP.
See you soon!
-
- 1 reply
liked
a
dataset
11 months ago
Thanks man!
10
#1 opened 12 months ago
by
Nexesenex
Interesting model (feedback).
1
#1 opened 12 months ago
by
AtonMountlook