Giters
vwxyzjn
/
lm-human-preference-details
RLHF implementation details of OAI's 2019 codebase
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
130
Watchers:
4
Issues:
7
Forks:
7
vwxyzjn/lm-human-preference-details Issues
Reward Shape
Closed
4 months ago
Comments count
1
right_to_left_pad optimization
Closed
6 months ago
Comments count
6
Creating a jax implementation
Closed
7 months ago
Question about KL divergence computation
Closed
7 months ago
Comments count
3
A question about `normalize_after`
Closed
9 months ago
Comments count
3
Add accelerate to poetry dependencies
Closed
9 months ago
Comments count
2
Questions about `left_padding_to_right_padding`
Closed
10 months ago
Comments count
4