Quantization made by Richard Erkhov.

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

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

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


GritLM-8x7B-KTO - GGUF
- Model creator: https://huggingface.co/GritLM/
- Original model: https://huggingface.co/GritLM/GritLM-8x7B-KTO/


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [GritLM-8x7B-KTO.Q2_K.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-8x7B-KTO-gguf/blob/main/GritLM-8x7B-KTO.Q2_K.gguf) | Q2_K | 16.12GB |
| [GritLM-8x7B-KTO.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-8x7B-KTO-gguf/blob/main/GritLM-8x7B-KTO.IQ3_XS.gguf) | IQ3_XS | 18.02GB |
| [GritLM-8x7B-KTO.IQ3_S.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-8x7B-KTO-gguf/blob/main/GritLM-8x7B-KTO.IQ3_S.gguf) | IQ3_S | 19.03GB |
| [GritLM-8x7B-KTO.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-8x7B-KTO-gguf/blob/main/GritLM-8x7B-KTO.Q3_K_S.gguf) | Q3_K_S | 19.03GB |
| [GritLM-8x7B-KTO.IQ3_M.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-8x7B-KTO-gguf/blob/main/GritLM-8x7B-KTO.IQ3_M.gguf) | IQ3_M | 19.96GB |
| [GritLM-8x7B-KTO.Q3_K.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-8x7B-KTO-gguf/blob/main/GritLM-8x7B-KTO.Q3_K.gguf) | Q3_K | 21.0GB |
| [GritLM-8x7B-KTO.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-8x7B-KTO-gguf/blob/main/GritLM-8x7B-KTO.Q3_K_M.gguf) | Q3_K_M | 21.0GB |
| [GritLM-8x7B-KTO.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-8x7B-KTO-gguf/blob/main/GritLM-8x7B-KTO.Q3_K_L.gguf) | Q3_K_L | 22.51GB |
| [GritLM-8x7B-KTO.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-8x7B-KTO-gguf/blob/main/GritLM-8x7B-KTO.IQ4_XS.gguf) | IQ4_XS | 23.63GB |
| [GritLM-8x7B-KTO.Q4_0.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-8x7B-KTO-gguf/blob/main/GritLM-8x7B-KTO.Q4_0.gguf) | Q4_0 | 24.63GB |
| [GritLM-8x7B-KTO.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-8x7B-KTO-gguf/blob/main/GritLM-8x7B-KTO.IQ4_NL.gguf) | IQ4_NL | 24.91GB |
| [GritLM-8x7B-KTO.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-8x7B-KTO-gguf/blob/main/GritLM-8x7B-KTO.Q4_K_S.gguf) | Q4_K_S | 24.91GB |
| [GritLM-8x7B-KTO.Q4_K.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-8x7B-KTO-gguf/blob/main/GritLM-8x7B-KTO.Q4_K.gguf) | Q4_K | 26.49GB |
| [GritLM-8x7B-KTO.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-8x7B-KTO-gguf/blob/main/GritLM-8x7B-KTO.Q4_K_M.gguf) | Q4_K_M | 26.49GB |
| [GritLM-8x7B-KTO.Q4_1.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-8x7B-KTO-gguf/blob/main/GritLM-8x7B-KTO.Q4_1.gguf) | Q4_1 | 27.32GB |
| [GritLM-8x7B-KTO.Q5_0.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-8x7B-KTO-gguf/blob/main/GritLM-8x7B-KTO.Q5_0.gguf) | Q5_0 | 30.02GB |
| [GritLM-8x7B-KTO.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-8x7B-KTO-gguf/blob/main/GritLM-8x7B-KTO.Q5_K_S.gguf) | Q5_K_S | 30.02GB |
| [GritLM-8x7B-KTO.Q5_K.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-8x7B-KTO-gguf/blob/main/GritLM-8x7B-KTO.Q5_K.gguf) | Q5_K | 30.95GB |
| [GritLM-8x7B-KTO.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-8x7B-KTO-gguf/blob/main/GritLM-8x7B-KTO.Q5_K_M.gguf) | Q5_K_M | 30.95GB |
| [GritLM-8x7B-KTO.Q5_1.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-8x7B-KTO-gguf/blob/main/GritLM-8x7B-KTO.Q5_1.gguf) | Q5_1 | 32.71GB |
| [GritLM-8x7B-KTO.Q6_K.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-8x7B-KTO-gguf/blob/main/GritLM-8x7B-KTO.Q6_K.gguf) | Q6_K | 35.74GB |
| [GritLM-8x7B-KTO.Q8_0.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-8x7B-KTO-gguf/tree/main/) | Q8_0 | 46.22GB |




Original model description:
---
pipeline_tag: text-generation
inference: true
license: apache-2.0
datasets:
- GritLM/tulu2

---

# Model Summary

A [**KTO**](https://arxiv.org/abs/2402.01306) version of https://huggingface.co/GritLM/GritLM-8x7B

> GritLM is a generative representational instruction tuned language model. It unifies text representation (embedding) and text generation into a single model achieving state-of-the-art performance on both types of tasks.

- **Repository:** [ContextualAI/gritlm](https://github.com/ContextualAI/gritlm)
- **Paper:** https://arxiv.org/abs/2402.09906
- **Logs:** https://wandb.ai/muennighoff/gritlm/runs/0uui712t/overview
- **Script:** https://github.com/ContextualAI/gritlm/blob/main/scripts/training/train_gritlm_7b.sh

| Model | Description |
|-------|-------------|
| [GritLM 7B](https://hf.co/GritLM/GritLM-7B) | Mistral 7B finetuned using GRIT |
| [GritLM 8x7B](https://hf.co/GritLM/GritLM-8x7B) | Mixtral 8x7B finetuned using GRIT |

# Use

The model usage is documented [here](https://github.com/ContextualAI/gritlm?tab=readme-ov-file#inference).

# Citation

```bibtex
@misc{muennighoff2024generative,
      title={Generative Representational Instruction Tuning}, 
      author={Niklas Muennighoff and Hongjin Su and Liang Wang and Nan Yang and Furu Wei and Tao Yu and Amanpreet Singh and Douwe Kiela},
      year={2024},
      eprint={2402.09906},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}
```