RichardErkhov/jasonhwan_-_phi3-redteamer-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

phi3-redteamer - GGUF

• Model creator: https://huggingface.co/jasonhwan/
• Original model: https://huggingface.co/jasonhwan/phi3-redteamer/

Name	Quant method	Size
phi3-redteamer.Q2_K.gguf	Q2_K	1.32GB
phi3-redteamer.IQ3_XS.gguf	IQ3_XS	1.51GB
phi3-redteamer.IQ3_S.gguf	IQ3_S	1.57GB
phi3-redteamer.Q3_K_S.gguf	Q3_K_S	1.57GB
phi3-redteamer.IQ3_M.gguf	IQ3_M	1.73GB
phi3-redteamer.Q3_K.gguf	Q3_K	1.82GB
phi3-redteamer.Q3_K_M.gguf	Q3_K_M	1.82GB
phi3-redteamer.Q3_K_L.gguf	Q3_K_L	1.94GB
phi3-redteamer.IQ4_XS.gguf	IQ4_XS	1.93GB
phi3-redteamer.Q4_0.gguf	Q4_0	2.03GB
phi3-redteamer.IQ4_NL.gguf	IQ4_NL	2.04GB
phi3-redteamer.Q4_K_S.gguf	Q4_K_S	2.04GB
phi3-redteamer.Q4_K.gguf	Q4_K	2.23GB
phi3-redteamer.Q4_K_M.gguf	Q4_K_M	2.23GB
phi3-redteamer.Q4_1.gguf	Q4_1	2.24GB
phi3-redteamer.Q5_0.gguf	Q5_0	2.46GB
phi3-redteamer.Q5_K_S.gguf	Q5_K_S	2.46GB
phi3-redteamer.Q5_K.gguf	Q5_K	2.62GB
phi3-redteamer.Q5_K_M.gguf	Q5_K_M	2.62GB
phi3-redteamer.Q5_1.gguf	Q5_1	2.68GB
phi3-redteamer.Q6_K.gguf	Q6_K	2.92GB
phi3-redteamer.Q8_0.gguf	Q8_0	3.78GB

Original model description:

library_name: transformers tags: []

Model Card

A lightweight Microsoft Phi3 3.8B model fine-tuned on AllenAI's WildJailbreak model to automatically generate jailbreak prompts for target LLMs.