Downloads · 30 days
19
14% of all-time downloads
grimjim/Mistral-7B-Instruct-v0.2-8bit-abliterated
Mistral-7B-Instruct-v0.2-8bit-abliterated is a text generation model from grimjim. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
This model was abliterated by computing a refusal vector an 8-bit bitsandbytes quant, and then applying the vector to the full weight model. Abliteration was performed locally using a CUDA GPU, the VRAM memory consump…
Downloads · 30 days
19
14% of all-time downloads
All-time downloads
134
Public
Parameters
7.2B
14.5 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors14.5 GB · 100%
From the Hugging Face model README
This model was abliterated by computing a refusal vector an 8-bit bitsandbytes quant, and then applying the vector to the full weight model. Abliteration was performed locally using a CUDA GPU, the VRAM memory consumption appeared to be constrained to be under 12GB.
No additional fine-tuning was performed on these weights. Repair is required for proper use.
The code used can be found on Github at https://github.com/jim-plus/llm-abliteration.