osmarks/documentation
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Edit ‘autogollark’

Browse Source
This commit is contained in:
osmarks
2025-06-04 12:09:28 +00:00
committed by wikimind
parent e8dc56d8d1
commit 8df621998a
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
autogollark.myco
View File

@@ -22,7 +22,7 @@ Autogollark currently comprises the dataset, the search API server and the [[htt
} }
* {Tool capabilities (how to get the data? Examples in context only?!). * {Tool capabilities (how to get the data? Examples in context only?!).
* Synthetic via instruct model. * Synthetic via instruct model.
* {RL (also include reasoning, of course). Probably hard though (sparse rewards). https://arxiv.org/abs/2403.09629. [[https://arxiv.org/abs/2503.22828]] would probably work. * {RL (also include reasoning, of course). Probably hard though (sparse rewards). https://arxiv.org/abs/2403.09629. [[https://arxiv.org/abs/2503.22828]] would probably work. [[https://arxiv.org/abs/2505.15778]]
* Unclear whether model could feasibly learn tool use "from scratch", so still need SFT pipeline. * Unclear whether model could feasibly learn tool use "from scratch", so still need SFT pipeline.
} }
* https://arxiv.org/abs/2310.04363 can improve sampling (roughly) //and// train for tool use. * https://arxiv.org/abs/2310.04363 can improve sampling (roughly) //and// train for tool use.
@@ -33,7 +33,7 @@ Autogollark currently comprises the dataset, the search API server and the [[htt
* Decision theory training data (synthetic, probably) (ref https://arxiv.org/abs/2411.10588). * Decision theory training data (synthetic, probably) (ref https://arxiv.org/abs/2411.10588).
* Pending: XEROGRAPHIC BIFROST 3. * Pending: XEROGRAPHIC BIFROST 3.
} }
* MCTS over conversations with non-gollark simulacra? Should find //something// to use spare parallelism on local inference. Best-of-n? * MCTS over conversations with non-gollark simulacra? Should find //something// to use spare parallelism on local inference. Best-of-n? https://arxiv.org/abs/2505.10475
* {Longer context, mux several channels. * {Longer context, mux several channels.
* {No obvious reason Autogollark can't train (and run inference!) on every channel simultaneously, with messages sorted by time and other non-Discord things (tool calls?) inline. Not good use of parallelism but does neatly solve the when-to-respond thing. * {No obvious reason Autogollark can't train (and run inference!) on every channel simultaneously, with messages sorted by time and other non-Discord things (tool calls?) inline. Not good use of parallelism but does neatly solve the when-to-respond thing.
* Context length issues, and subquadratic models are sort of bad, though maybe we can "upcycle" a midsized model to RWKV. This exists somewhere. Not sure of efficiency. * Context length issues, and subquadratic models are sort of bad, though maybe we can "upcycle" a midsized model to RWKV. This exists somewhere. Not sure of efficiency.