Post
1013
remember boys and girls, always keep all your data, its never a waste of time!
MixtureMaxing
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
MixtureMaxing's activity
Alignment-Lab-AI
posted
an
update
about 2 months ago
Post
13332
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!
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!
- 4 replies
Post
11841
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
Post
16460
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
Post
20612
Hello!
The 8B/70B OG Llama-3 models made with the Orthogonal Activation Steering script as been pushed in private.
After multiple test with an empty prompt system, I can confirm it's not uncensored enough, but I wanted to try all the GGUF before (and it take time to do lmao)
If you want to try that yourself, here is the script : https://gist.github.com/wassname/42aba7168bb83e278fcfea87e70fa3af
And here is the same script that we modified to be able to use it on multiple GPU for 70B : https://files.catbox.moe/ya4rto.ipynb
Llama3-Unholy-8B-OAS don't have the problem as it was already trained to be less censored, but the OG one was really too much censored.
I will try to redo that soon, as it seems to HAVE WORKED for some prompt (as seen on the log, for exemple) but it's not enough.
32 entry of the dataset is clearly not enough, but it's okay, I really wanted to try that as it was something new.
I could take the Unholy way and retrain the 70B before using OAS but it should work without, that's not the goal.
The 8B/70B OG Llama-3 models made with the Orthogonal Activation Steering script as been pushed in private.
After multiple test with an empty prompt system, I can confirm it's not uncensored enough, but I wanted to try all the GGUF before (and it take time to do lmao)
If you want to try that yourself, here is the script : https://gist.github.com/wassname/42aba7168bb83e278fcfea87e70fa3af
And here is the same script that we modified to be able to use it on multiple GPU for 70B : https://files.catbox.moe/ya4rto.ipynb
Llama3-Unholy-8B-OAS don't have the problem as it was already trained to be less censored, but the OG one was really too much censored.
I will try to redo that soon, as it seems to HAVE WORKED for some prompt (as seen on the log, for exemple) but it's not enough.
32 entry of the dataset is clearly not enough, but it's okay, I really wanted to try that as it was something new.
I could take the Unholy way and retrain the 70B before using OAS but it should work without, that's not the goal.
- 61 replies
Post
9621
Soon new releases on NeverSleep 👀
8B/70B Llama3 RP fine-tune in the work!
8B/70B Llama3 RP fine-tune in the work!
-
-
- 2 replies
chargoddard
authored
a
paper
9 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
Post
From
@IkariDev
and
@Undi95
New release from NeverSleep!
MiquMaid-v2-70B
NeverSleep/MiquMaid-v2-70B
NeverSleep/MiquMaid-v2-70B-GGUF
DPO version
NeverSleep/MiquMaid-v2-70B-DPO
NeverSleep/MiquMaid-v2-70B-DPO-GGUF
MiquMaid-v2-2x70B
NeverSleep/MiquMaid-v2-2x70B
NeverSleep/MiquMaid-v2-2x70B-GGUF
DPO version
NeverSleep/MiquMaid-v2-2x70B-DPO
NeverSleep/MiquMaid-v2-2x70B-DPO-GGUF
Feedback appreciated!
New release from NeverSleep!
MiquMaid-v2-70B
NeverSleep/MiquMaid-v2-70B
NeverSleep/MiquMaid-v2-70B-GGUF
DPO version
NeverSleep/MiquMaid-v2-70B-DPO
NeverSleep/MiquMaid-v2-70B-DPO-GGUF
MiquMaid-v2-2x70B
NeverSleep/MiquMaid-v2-2x70B
NeverSleep/MiquMaid-v2-2x70B-GGUF
DPO version
NeverSleep/MiquMaid-v2-2x70B-DPO
NeverSleep/MiquMaid-v2-2x70B-DPO-GGUF
Feedback appreciated!
-
- 4 replies
alpindale
authored
a
paper
over 1 year ago