Hugging Face's logo

akaistormherald
/
ToxicMist-v0.2-7B-DPO

Text Generation
Transformers
Safetensors
English
mistral
text-generation-inference
unsloth
trl
dpo
conversational
Inference Endpoints
Model card Files Community
Edit model card

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? ☣🌫

Downloads last month
3
Safetensors
Model size
7.24B params
Tensor type
BF16
·

Finetuned from

Dataset used to train akaistormherald/ToxicMist-v0.2-7B-DPO