Fine-tuning Mistral 7B on Magic the Gathering Draft
generallyintelligent.substack.com
Fine-tuning Mistral 7B on Magic the Gathering Draft
1–10 of 101 posts
Re: Fine-tuning Mistral 7B on Magic the Gathering Draft
#2It's not the most revolutionary change to our daily lives, but I do genuinely look forward to playing against bots that have interesting play styles for games like Magic: the Gathering. I think this is a clear case where it could drastically improve the ability for the R&D team to come up with and test new mechanics at different levels of play.
Re: Fine-tuning Mistral 7B on Magic the Gathering Draft
#3Super interesting that drafts can be represented with LLMs.
The best performing draft AI's I've seen leverage representation learning in some form.
Re: Fine-tuning Mistral 7B on Magic the Gathering Draft
#4> I was particularly interested in testing models’ ability to reason (i.e., perform a somewhat complex task that requires high context understanding) about out-of-distribution (i.e., unseen) data.
I was under the assumption that finetuneing LLMs was useful only when you need to change the model's tone (speak like a pirate, voldemort etc).
Are there other examples where LLMs were trained to reason a particular way?
Re: Fine-tuning Mistral 7B on Magic the Gathering Draft
#5Wow, I have exactly the same side project in progress, minus the fine tuning part. We even chose the same names and phrasing for parts of the project.
Re: Fine-tuning Mistral 7B on Magic the Gathering Draft
#6Would like to know, how many matches were won per draft token? If it's less than 2, I'll stick to my shitty hand picks :/
Re: Fine-tuning Mistral 7B on Magic the Gathering Draft
#7> I was particularly interested in testing models’ ability to reason (i.e., perform a somewhat complex task that requires high context understanding) about out-of-distribution (i.e., unseen) data. I was under the assumption that finetuneing LLMs was useful only when you need to change the model's tone (speak like a pirate, voldemort etc). Are there other examples where LLMs were trained to reason a particular way?
You can get a standard LLM to change tone just by giving it a system prompt/instruction to follow a certain tone.
The only issue there is that sometimes the RLHF seeps through, which can be solved by system prompting even harder.
Re: Fine-tuning Mistral 7B on Magic the Gathering Draft
#8Super interesting that drafts can be represented with LLMs. The best performing draft AI's I've seen leverage representation learning in some form. See: https://arxiv.org/pdf/2107.04438.pdf
I hadn't seen this, this is awesome! You'd think given the volume of data available that this type of method would outperform an LLM, cool results.
Still some fun things about LLM representations -- you can do fun things like give the bots preferences / personality in a system prompt which is entertaining!
Re: Fine-tuning Mistral 7B on Magic the Gathering Draft
#9I like how it identified that you haven't committed to either white or blue yet. It was aware of deck composition and not just going for the jugular. Keep tuning. It could also be Human-bias because you also played the hand. Have someone else draft against your LLM and then you play it and see if it's the same. Statistically it should match given enough games.
Re: Fine-tuning Mistral 7B on Magic the Gathering Draft
#10Wow, I have exactly the same side project in progress, minus the fine tuning part. We even chose the same names and phrasing for parts of the project.
Would love to compare notes, drop me a email at dshersh at umich dot edu if you'd be interested!