NeuralDaredevil-8B-abliterated

Name: NeuralDaredevil-8B-abliterated
Author: Hugging Face

llama38B

This is a DPO fine-tune of mlabonne/Daredevil-8-abliterated, trained on one epoch of mlabonne/orpo-dpo-mix-40k. The DPO fine-tuning successfully recovers the performance loss due to the abliteration process, making it an excellent uncensored model.

Context

Capabilities

Show unsupported (5)

Reasoning & Interaction

Tool Calling

Infrastructure

Streaming

Fine-tuning

Details

Model IDmlabonne/NeuralDaredevil-8B-abliterated

ProviderHugging Face

Creatormlabonne

Family—

Licensellama3

Status—

Type—

Input modalities—

Output modalities—

Open weightYes

Parameters8B

Architecturetransformer

Context window8K tokens

Max input—

Max output—

Reasoning tokens—

Knowledge cutoff—

Release date2024-05-27

Sourceofficial

Tools

Function Callingfunction_calling

Call external functions and APIs

API

GET/v1/models/huggingface/mlabonne/NeuralDaredevil-8B-abliterated