Qwen2.5-72B-Instruct-abliterated

Name: Qwen2.5-72B-Instruct-abliterated
Author: Hugging Face

other73B

This is an uncensored version of Qwen/Qwen2.5-72B-Instruct 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.

Context

33K

Capabilities

Show unsupported (5)

Reasoning & Interaction

Tool Calling

Infrastructure

Streaming

Fine-tuning

Details

Model IDhuihui-ai/Qwen2.5-72B-Instruct-abliterated

ProviderHugging Face

Creatorhuihui-ai

Family—

Licenseother

Status—

Typechat

Input modalitiestext

Output modalitiestext

Open weightYes

Parameters73B

Architecturetransformer

Context window33K tokens

Max input—

Max output—

Reasoning tokens—

Knowledge cutoff—

Release date2024-10-26

Sourceofficial

Tools

Function Callingfunction_calling

Call external functions and APIs

API

GET/v1/models/huggingface/huihui-ai/Qwen2.5-72B-Instruct-abliterated