You can deploy this model and start earning money today!

RichardErkhov/
xzyao_-_openllama-3b-chat-gguf

Name: xzyao_-_openllama-3b-chat-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

openllama-3b-chat - GGUF

Model creator: https://huggingface.co/xzyao/
Original model: https://huggingface.co/xzyao/openllama-3b-chat/

Name	Quant method	Size
openllama-3b-chat.Q2_K.gguf	Q2_K	1.84GB
openllama-3b-chat.IQ3_XS.gguf	IQ3_XS	1.84GB
openllama-3b-chat.IQ3_S.gguf	IQ3_S	1.84GB
openllama-3b-chat.Q3_K_S.gguf	Q3_K_S	1.84GB
openllama-3b-chat.IQ3_M.gguf	IQ3_M	1.92GB
openllama-3b-chat.Q3_K.gguf	Q3_K	1.99GB
openllama-3b-chat.Q3_K_M.gguf	Q3_K_M	1.99GB
openllama-3b-chat.Q3_K_L.gguf	Q3_K_L	2.06GB
openllama-3b-chat.IQ4_XS.gguf	IQ4_XS	1.86GB
openllama-3b-chat.Q4_0.gguf	Q4_0	1.84GB
openllama-3b-chat.IQ4_NL.gguf	IQ4_NL	1.86GB
openllama-3b-chat.Q4_K_S.gguf	Q4_K_S	2.24GB
openllama-3b-chat.Q4_K.gguf	Q4_K	2.4GB
openllama-3b-chat.Q4_K_M.gguf	Q4_K_M	2.4GB
openllama-3b-chat.Q4_1.gguf	Q4_1	2.04GB
openllama-3b-chat.Q5_0.gguf	Q5_0	2.23GB
openllama-3b-chat.Q5_K_S.gguf	Q5_K_S	2.42GB
openllama-3b-chat.Q5_K.gguf	Q5_K	2.57GB
openllama-3b-chat.Q5_K_M.gguf	Q5_K_M	2.57GB
openllama-3b-chat.Q5_1.gguf	Q5_1	2.42GB
openllama-3b-chat.Q6_K.gguf	Q6_K	3.39GB
openllama-3b-chat.Q8_0.gguf	Q8_0	3.39GB

Original model description:

license: apache-2.0 language:

en library_name: transformers

OpenLLaMA-3B-Chat: Chat Model on top of Open Reproduction of LLaMA

Training Traces

wandb

Prompt Format

<human>: Who is Alan Turing?<|endoftext|><assistant>:

Reference

If you found OpenLLaMA useful in your research or applications, please cite using the following BibTeX:

@software{Yao_FMEngine_Library_for_2023,
  author = {Yao, Xiaozhe},
  doi = {10.5281/zenodo.8314779},
  month = sep,
  title = {{FMEngine: Library for Training Foundation Models}},
  url = {https://github.com/eth-easl/fmengine},
  version = {0.0.1},
  year = {2023}
}
@software{openlm2023openllama,
  author = {Geng, Xinyang and Liu, Hao},
  title = {OpenLLaMA: An Open Reproduction of LLaMA},
  month = May,
  year = 2023,
  url = {https://github.com/openlm-research/open_llama}
}
@software{together2023redpajama,
  author = {Together Computer},
  title = {RedPajama-Data: An Open Source Recipe to Reproduce LLaMA training dataset},
  month = April,
  year = 2023,
  url = {https://github.com/togethercomputer/RedPajama-Data}
}
@article{touvron2023llama,
  title={Llama: Open and efficient foundation language models},
  author={Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timoth{\'e}e and Rozi{\`e}re, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and others},
  journal={arXiv preprint arXiv:2302.13971},
  year={2023}
}

Limitations and Bias

As with all language models, openllama-3b-chat may generate incorrect or biased content. It's important to keep this in mind when using the model.

RichardErkhov/xzyao_-_openllama-3b-chat-gguf