Downloads · 30 days
606
4% of all-time downloads
RichardErkhov/alpindale_-_pygmalion-instruct-gguf
alpindale_-_pygmalion-instruct-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
606
4% of all-time downloads
All-time downloads
15.4K
Public
Repo size
69.4 GB
Likes
0
Public
Click a slice to open those files.
.gguf81.6 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
pygmalion-instruct - GGUF
| Name | Quant method | Size |
|---|---|---|
| pygmalion-instruct.Q2_K.gguf | Q2_K | 2.36GB |
| pygmalion-instruct.IQ3_XS.gguf | IQ3_XS | 2.6GB |
| pygmalion-instruct.IQ3_S.gguf | IQ3_S | 2.75GB |
| pygmalion-instruct.Q3_K_S.gguf | Q3_K_S | 2.75GB |
| pygmalion-instruct.IQ3_M.gguf | IQ3_M | 2.9GB |
| pygmalion-instruct.Q3_K.gguf | Q3_K | 3.07GB |
| pygmalion-instruct.Q3_K_M.gguf | Q3_K_M | 3.07GB |
| pygmalion-instruct.Q3_K_L.gguf | Q3_K_L | 3.35GB |
| pygmalion-instruct.IQ4_XS.gguf | IQ4_XS | 3.4GB |
| pygmalion-instruct.Q4_0.gguf | Q4_0 | 3.56GB |
| pygmalion-instruct.IQ4_NL.gguf | IQ4_NL | 3.58GB |
| pygmalion-instruct.Q4_K_S.gguf | Q4_K_S | 3.59GB |
| pygmalion-instruct.Q4_K.gguf | Q4_K | 3.8GB |
| pygmalion-instruct.Q4_K_M.gguf | Q4_K_M | 3.8GB |
| pygmalion-instruct.Q4_1.gguf | Q4_1 | 3.95GB |
| pygmalion-instruct.Q5_0.gguf | Q5_0 | 4.33GB |
| pygmalion-instruct.Q5_K_S.gguf | Q5_K_S | 4.33GB |
| pygmalion-instruct.Q5_K.gguf | Q5_K | 4.45GB |
| pygmalion-instruct.Q5_K_M.gguf | Q5_K_M | 4.45GB |
| pygmalion-instruct.Q5_1.gguf | Q5_1 | 4.72GB |
| pygmalion-instruct.Q6_K.gguf | Q6_K | 5.15GB |
Experimental model. Trained with the Pygmalion and the WizardLM datasets.
The purpose of this model is to enable complex Instruct prompting but with the RP capabilties of Pygmalion.
instruction:
output:
<!-- Provide the basic links for the model. -->
The intended use-case is Role-Playing with Instruct prompts. Guiding the bot towards a certain conversation style should be easier this way. Subject to experimentation.
The model can generate potentially harmful or NSFW outputs. Please use with caution.
WizardLM:
@misc{xu2023wizardlm,
title={WizardLM: Empowering Large Language Models to Follow Complex Instructions},
author={Can Xu and Qingfeng Sun and Kai Zheng and Xiubo Geng and Pu Zhao and Jiazhan Feng and Chongyang Tao and Daxin Jiang},
year={2023},
eprint={2304.12244},
archivePrefix={arXiv},
primaryClass={cs.CL}
}