Downloads · 30 days
4
7% of all-time downloads
Hellisotherpeople/toxic-dpo-v2-mistral7b-lora
toxic-dpo-v2-mistral7b-lora is a machine learning model from Hellisotherpeople. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as mit.
This is an example of how easy it is to effeciently fine-tune a SOTA 7B paramater language model adapter (in this case badsaijaskier-7b-dpo-v5.6 was used, but the lora works on most mistral 7b models) to remove "align…
Downloads · 30 days
4
7% of all-time downloads
All-time downloads
54
Public
Repo size
2.6 GB
Likes
3
Public
Click a slice to open those files.
.pt1.7 GB · 67%
From the Hugging Face model README
This is an example of how easy it is to effeciently fine-tune a SOTA 7B paramater language model adapter (in this case badsai_jaskier-7b-dpo-v5.6 was used, but the lora works on most mistral 7b models) to remove "alignment" and "safety" restrictions on a single 3090 GPU with about 12 hours worth of compute on a dataset of about 600 examples.
The dataset used was https://huggingface.co/datasets/unalignment/toxic-dpo-v0.2 Trained for 9 epochs
Exclusively designed and intended for non-malicious research or personal usage. Please don't do bad things with this.
Intendend Use: Test how well your mistral 7b model or derivative of it survives a targeted alignment breaker adapter.
I think most people who want uncensored LLMs want them for a few primary reasons:
I'm not especially concerned about these relatively legitimate use-cases.
I'm much more concerned about the following, which the overwhelming majority likely wouldn't miss if it wasn't available:
Unfortunately, with current unalignment practices, we often get all of these possibilities. I hope that most hobbyist "unalignment" work is made in the future with the intention to primarily support the former and reject the latter use-cases.
(Copied from https://huggingface.co/datasets/unalignment/toxic-dpo-v0.2)
To use this model, you must acknowledge/agree to the following:
Made exclusively on my own time, using my own resources, unaffiliated with other organizations.