Training Data?
#1
by
dimitristaufer
- opened
Hello, this sounds super interesting. Would you mind sharing some information about the training data you used and whether the results seem promising?
Regards,
Dimitri
The training data is just some of the publicly available graphs I could find. This was a quick test on a weekend, I'm somewhat happy with it, though the prime kg one is more fit for my purposes. That said, I don't plan on releasing the dataset publicly at this time.
There is some example inference here: https://huggingface.co/M-Chimiste/Llama-3-8B-prime-graph-exp-1_merged
Do you have sample prompt and output?
I’d recommend this: https://huggingface.co/theseus-research/llama-3.1-8b-prime-kg-exp-1
It’s an updated model. It should have an example in the model card.