huihui-ai/QRWKV6-32B-Instruct-Preview-v0.1-abliterated

This is an uncensored version of recursal/QRWKV6-32B-Instruct-Preview-v0.1 created with abliteration (see remove-refusals-with-transformers to know more about it).
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.

Safetensors

Model size

34.7B params

Tensor type

BF16

Inference Examples

Inference API (serverless) does not yet support model repos that contain custom code.

Model tree for huihui-ai/QRWKV6-32B-Instruct-Preview-v0.1-abliterated

Base model

Finetuned

(1)

this model

Quantizations