Where is the explicit definition and reference to Q* ??
this post was submitted on 23 Nov 2023
1 points (100.0% liked)
LocalLLaMA
3 readers
1 users here now
Community to discuss about Llama, the family of large language models created by Meta AI.
founded 1 year ago
MODERATORS
U/Xnohat - wanna answer this one?
I think that's a bit out of date. My guess is its building on this work
https://openai.com/research/improving-mathematical-reasoning-with-process-supervision
This definitely sounds like the paper. 100% worth the read, surprised I hadn't heard much about it until this ordeal
PRM8k, made the rounds maybe 6+ months but they never publicly released the model.
I've recently just got into LLM's have you tried these math models? They seem to follow math related instructions reasonably well.
wizard-math:13b-q6_KMathLLM-MathCoder-CL-7B.Q8_0.ggufmetamath-mistral-7b.Q5_K_M.gguf
I'll definitely be asking my GPT to read this paper to me as my bedtime story.
yea, that seems to be what a few news articles have referenced.
Strange, I thought they would naturally be rewarding the process, by rewarding each word that's generated by the sequence to sequence model, rather than the final words, for example. Maybe they over-optimised and skipped training on all output.
When AI model can understand and really doing Math, that a critical jump.
Grammarly is free, my man
Not free unfortunately
chatGPT is
The free version could do a better job than OP.
This doesn't smell right to me.
All references around Q* and the drama around proto-AGI...e.g. Altman talking about veil of ignorance being pulled back seem to point to something that happened in the last couple of weeks. Not 2020.
If they found a proto-AGI and it was relatively trivial to implement, it would be a good idea to throw competitors off the trail with a red herring.
doesn't seem directly related but surely it's indirectly related,, this is an interesting idea: "We demonstrate that iteratively training a value function on statements generated by our language model leads to improved prover performance, which immediately suggests a strategy for continuous self improvement: keep training on proofs generated by the prover."