Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


pygmalion-instruct - GGUF
- Model creator: https://huggingface.co/alpindale/
- Original model: https://huggingface.co/alpindale/pygmalion-instruct/


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [pygmalion-instruct.Q2_K.gguf](https://huggingface.co/RichardErkhov/alpindale_-_pygmalion-instruct-gguf/blob/main/pygmalion-instruct.Q2_K.gguf) | Q2_K | 2.36GB |
| [pygmalion-instruct.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/alpindale_-_pygmalion-instruct-gguf/blob/main/pygmalion-instruct.IQ3_XS.gguf) | IQ3_XS | 2.6GB |
| [pygmalion-instruct.IQ3_S.gguf](https://huggingface.co/RichardErkhov/alpindale_-_pygmalion-instruct-gguf/blob/main/pygmalion-instruct.IQ3_S.gguf) | IQ3_S | 2.75GB |
| [pygmalion-instruct.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/alpindale_-_pygmalion-instruct-gguf/blob/main/pygmalion-instruct.Q3_K_S.gguf) | Q3_K_S | 2.75GB |
| [pygmalion-instruct.IQ3_M.gguf](https://huggingface.co/RichardErkhov/alpindale_-_pygmalion-instruct-gguf/blob/main/pygmalion-instruct.IQ3_M.gguf) | IQ3_M | 2.9GB |
| [pygmalion-instruct.Q3_K.gguf](https://huggingface.co/RichardErkhov/alpindale_-_pygmalion-instruct-gguf/blob/main/pygmalion-instruct.Q3_K.gguf) | Q3_K | 3.07GB |
| [pygmalion-instruct.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/alpindale_-_pygmalion-instruct-gguf/blob/main/pygmalion-instruct.Q3_K_M.gguf) | Q3_K_M | 3.07GB |
| [pygmalion-instruct.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/alpindale_-_pygmalion-instruct-gguf/blob/main/pygmalion-instruct.Q3_K_L.gguf) | Q3_K_L | 3.35GB |
| [pygmalion-instruct.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/alpindale_-_pygmalion-instruct-gguf/blob/main/pygmalion-instruct.IQ4_XS.gguf) | IQ4_XS | 3.4GB |
| [pygmalion-instruct.Q4_0.gguf](https://huggingface.co/RichardErkhov/alpindale_-_pygmalion-instruct-gguf/blob/main/pygmalion-instruct.Q4_0.gguf) | Q4_0 | 3.56GB |
| [pygmalion-instruct.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/alpindale_-_pygmalion-instruct-gguf/blob/main/pygmalion-instruct.IQ4_NL.gguf) | IQ4_NL | 3.58GB |
| [pygmalion-instruct.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/alpindale_-_pygmalion-instruct-gguf/blob/main/pygmalion-instruct.Q4_K_S.gguf) | Q4_K_S | 3.59GB |
| [pygmalion-instruct.Q4_K.gguf](https://huggingface.co/RichardErkhov/alpindale_-_pygmalion-instruct-gguf/blob/main/pygmalion-instruct.Q4_K.gguf) | Q4_K | 3.8GB |
| [pygmalion-instruct.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/alpindale_-_pygmalion-instruct-gguf/blob/main/pygmalion-instruct.Q4_K_M.gguf) | Q4_K_M | 3.8GB |
| [pygmalion-instruct.Q4_1.gguf](https://huggingface.co/RichardErkhov/alpindale_-_pygmalion-instruct-gguf/blob/main/pygmalion-instruct.Q4_1.gguf) | Q4_1 | 3.95GB |
| [pygmalion-instruct.Q5_0.gguf](https://huggingface.co/RichardErkhov/alpindale_-_pygmalion-instruct-gguf/blob/main/pygmalion-instruct.Q5_0.gguf) | Q5_0 | 4.33GB |
| [pygmalion-instruct.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/alpindale_-_pygmalion-instruct-gguf/blob/main/pygmalion-instruct.Q5_K_S.gguf) | Q5_K_S | 4.33GB |
| [pygmalion-instruct.Q5_K.gguf](https://huggingface.co/RichardErkhov/alpindale_-_pygmalion-instruct-gguf/blob/main/pygmalion-instruct.Q5_K.gguf) | Q5_K | 4.45GB |
| [pygmalion-instruct.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/alpindale_-_pygmalion-instruct-gguf/blob/main/pygmalion-instruct.Q5_K_M.gguf) | Q5_K_M | 4.45GB |
| [pygmalion-instruct.Q5_1.gguf](https://huggingface.co/RichardErkhov/alpindale_-_pygmalion-instruct-gguf/blob/main/pygmalion-instruct.Q5_1.gguf) | Q5_1 | 4.72GB |
| [pygmalion-instruct.Q6_K.gguf](https://huggingface.co/RichardErkhov/alpindale_-_pygmalion-instruct-gguf/blob/main/pygmalion-instruct.Q6_K.gguf) | Q6_K | 5.15GB |




Original model description:
---
license: mit
---

## Model Details

Experimental model. Trained with the [Pygmalion](https://huggingface.co/PygmalionAI/pygmalion-6b/tree/dev) and the [WizardLM](https://huggingface.co/ehartford/WizardLM-7B-Uncensored) datasets.

The purpose of this model is to enable complex Instruct prompting but with the RP capabilties of Pygmalion. 

### Prompting format
```
instruction:
output:
```

<!-- Provide the basic links for the model. -->

- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]

### Uses

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.



### Out-of-Scope Use

- Assistant Bot [subject to providing incorrect instructions]
- Complex multi-character chat

### Risks

The model can generate potentially harmful or NSFW outputs. Please use with caution.

### Citation

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}
}
```