tensortemplar/
prometheus2:8x7b-Q3_K_L

450 1 year ago

prometheus2 judge from prometheus-eval converted for ollama support

1 year ago

7da90c6c3653 · 24GB ·

llama
·
46.7B
·
Q3_K_L
{ "stop": [ "<|start_header_id|>", "<|end_header_id|>", "<|eot_id|>"
[INST] {{ if .System }}{{ .System }} {{ end }}{{ .Prompt }}[/INST] {{ .Response }}</s>

Readme

This is the ollama port of the original model. All credit belongs to the authors

PROMETHEUS 2: An Open Source Language Model Specialized in Evaluating Other Language Models

scoring_options.png

See github

@misc{kim2024prometheus,
      title={Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models}, 
      author={Seungone Kim and Juyoung Suk and Shayne Longpre and Bill Yuchen Lin and Jamin Shin and Sean Welleck and Graham Neubig and Moontae Lee and Kyungjae Lee and Minjoon Seo},
      year={2024},
      eprint={2405.01535},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}