Commit
•
680f0fc
1
Parent(s):
1ab224b
Update README.md
Browse files
README.md
CHANGED
|
@@ -19,6 +19,7 @@ I want to use small llms and a focused data set so I can really get a good idea
|
|
| 19 |
|
| 20 |
My rough strat is to use the tiny stories data set, a trajectory based data set only using the human Monk trajectories, and select categories from the Nat hack Wiki. I plan to do some ablations to see which data sets are critical. And once I have the basic instruction tuning up so we can follow basic small instructions, I will then attempt to implement some combination of ideas of some papers that I've been interested in.
|
| 21 |
|
|
|
|
| 22 |
|
| 23 |
# 7/25/23
|
| 24 |
https://astralcodexten.substack.com/p/were-not-platonists-weve-just-learned
|
|
|
|
| 19 |
|
| 20 |
My rough strat is to use the tiny stories data set, a trajectory based data set only using the human Monk trajectories, and select categories from the Nat hack Wiki. I plan to do some ablations to see which data sets are critical. And once I have the basic instruction tuning up so we can follow basic small instructions, I will then attempt to implement some combination of ideas of some papers that I've been interested in.
|
| 21 |
|
| 22 |
+
I am carefully formatting my trajectory data set for two reasons: one I want to make parsing trivial. Two on I am assuming that regularity and format of state's presented to the llm will allow it to generate output that I desire more easily. This is just an assumption.
|
| 23 |
|
| 24 |
# 7/25/23
|
| 25 |
https://astralcodexten.substack.com/p/were-not-platonists-weve-just-learned
|