mirror of
https://github.com/huggingface/candle.git
synced 2025-06-15 10:26:33 +00:00

* add olmo support * add olmo readme * Fix fmt. * Fix clippy. * Get olmo to work on cuda. --------- Co-authored-by: laurent <laurent.mazare@gmail.com>
candle-olmo: Open Language Models designed to enable the science of language models
OLMo is a series of Open Language Models designed to enable the science of language models.
- Project Page: https://allenai.org/olmo
- Paper: Link
- Technical blog post: https://blog.allenai.org/olmo-open-language-model-87ccfc95f580
- W&B Logs: https://wandb.ai/ai2-llm/OLMo-1B/reports/OLMo-1B--Vmlldzo2NzY1Njk1
Running the example
$ cargo run --example olmo --release -- --prompt "It is only with the heart that one can see rightly"
avx: true, neon: false, simd128: false, f16c: true
temp: 0.20 repeat-penalty: 1.10 repeat-last-n: 64
retrieved the files in 354.977µs
loaded the model in 19.87779666s
It is only with the heart that one can see rightly; what is essential is invisible to the eye.
Various model sizes are available via the --model
argument.
$ cargo run --example olmo --release -- --model 1.7-7b --prompt 'It is only with the heart that one can see rightly'
avx: true, neon: false, simd128: false, f16c: true
temp: 0.20 repeat-penalty: 1.10 repeat-last-n: 64
retrieved the files in 1.226087ms
loaded the model in 171.274578609s
It is only with the heart that one can see rightly; what is essential is invisible to the eye.”
~ Antoine de Saint-Exupery, The Little Prince
I am a big fan of this quote. It reminds me that I need to be open and aware of my surroundings in order to truly appreciate them.