QuantFactory / Llama-3.2-3B-Instruct-abliterated-GGUF

huggingface.co
Total runs: 7.7K
24-hour runs: 147
7-day runs: -191
30-day runs: -410
Model's Last Updated: October 09 2024

Introduction of Llama-3.2-3B-Instruct-abliterated-GGUF

Model Details of Llama-3.2-3B-Instruct-abliterated-GGUF

QuantFactory Banner

QuantFactory/Llama-3.2-3B-Instruct-abliterated-GGUF

This is quantized version of huihui-ai/Llama-3.2-3B-Instruct-abliterated created using llama.cpp

Original Model Card

🦙 Llama-3.2-3B-Instruct-abliterated

This is an uncensored version of Llama 3.2 3B Instruct created with abliteration (see this article to know more about it).

Special thanks to @FailSpy for the original code and technique. Please follow him if you're interested in abliterated models.

Evaluations

The following data has been re-evaluated and calculated as the average for each test.

Benchmark Llama-3.2-3B-Instruct Llama-3.2-3B-Instruct-abliterated
IF_Eval 76.55 76.76
MMLU Pro 27.88 28.00
TruthfulQA 50.55 50.73
BBH 41.81 41.86
GPQA 28.39 28.41

The script used for evaluation can be found inside this repository under /eval.sh, or click here

Runs of QuantFactory Llama-3.2-3B-Instruct-abliterated-GGUF on huggingface.co

7.7K
Total runs
147
24-hour runs
212
3-day runs
-191
7-day runs
-410
30-day runs

More Information About Llama-3.2-3B-Instruct-abliterated-GGUF huggingface.co Model

More Llama-3.2-3B-Instruct-abliterated-GGUF license Visit here:

https://choosealicense.com/licenses/llama3.2

Llama-3.2-3B-Instruct-abliterated-GGUF huggingface.co

Llama-3.2-3B-Instruct-abliterated-GGUF huggingface.co is an AI model on huggingface.co that provides Llama-3.2-3B-Instruct-abliterated-GGUF's model effect (), which can be used instantly with this QuantFactory Llama-3.2-3B-Instruct-abliterated-GGUF model. huggingface.co supports a free trial of the Llama-3.2-3B-Instruct-abliterated-GGUF model, and also provides paid use of the Llama-3.2-3B-Instruct-abliterated-GGUF. Support call Llama-3.2-3B-Instruct-abliterated-GGUF model through api, including Node.js, Python, http.

Llama-3.2-3B-Instruct-abliterated-GGUF huggingface.co Url

https://huggingface.co/QuantFactory/Llama-3.2-3B-Instruct-abliterated-GGUF

QuantFactory Llama-3.2-3B-Instruct-abliterated-GGUF online free

Llama-3.2-3B-Instruct-abliterated-GGUF huggingface.co is an online trial and call api platform, which integrates Llama-3.2-3B-Instruct-abliterated-GGUF's modeling effects, including api services, and provides a free online trial of Llama-3.2-3B-Instruct-abliterated-GGUF, you can try Llama-3.2-3B-Instruct-abliterated-GGUF online for free by clicking the link below.

QuantFactory Llama-3.2-3B-Instruct-abliterated-GGUF online free url in huggingface.co:

https://huggingface.co/QuantFactory/Llama-3.2-3B-Instruct-abliterated-GGUF

Llama-3.2-3B-Instruct-abliterated-GGUF install

Llama-3.2-3B-Instruct-abliterated-GGUF is an open source model from GitHub that offers a free installation service, and any user can find Llama-3.2-3B-Instruct-abliterated-GGUF on GitHub to install. At the same time, huggingface.co provides the effect of Llama-3.2-3B-Instruct-abliterated-GGUF install, users can directly use Llama-3.2-3B-Instruct-abliterated-GGUF installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Llama-3.2-3B-Instruct-abliterated-GGUF install url in huggingface.co:

https://huggingface.co/QuantFactory/Llama-3.2-3B-Instruct-abliterated-GGUF

Url of Llama-3.2-3B-Instruct-abliterated-GGUF

Llama-3.2-3B-Instruct-abliterated-GGUF huggingface.co Url

Provider of Llama-3.2-3B-Instruct-abliterated-GGUF huggingface.co

QuantFactory
ORGANIZATIONS

Other API from QuantFactory