Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
akaistormherald
/
ToxicMist-v0.2-7B-DPO-LORA
like
0
Transformers
Safetensors
unalignment/toxic-dpo-v0.2
English
text-generation-inference
unsloth
mistral
trl
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
Edit model card
Uploaded model
Uploaded model
Developed by:
akaistormherald
License:
apache-2.0
Finetuned from model :
unsloth/zephyr-sft-bnb-4bit
Mistral7b + SFT + 4bit DPO training with unalignment/toxic-dpo-v0.2 == ToxicMist? ☣🌫
(Just the lora)
Downloads last month
0
Unable to determine this model’s pipeline type. Check the
docs
.
Finetuned from
unsloth/zephyr-sft-bnb-4bit
Dataset used to train
akaistormherald/ToxicMist-v0.2-7B-DPO-LORA
unalignment/toxic-dpo-v0.2
Viewer
•
Updated
Jan 9
•
1.21k
•
82