Ecosyste.ms: Repos
An open API service providing repository metadata for many open source software ecosystems.
GitHub / abaheti95 / LoL-RL
Advantage Leftover Lunch Reinforcement Learning (A-LoL RL): Improving Language Models with Advantage-based Offline Policy Gradients
JSON API: https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/abaheti95%2FLoL-RL
Stars: 20
Forks: 5
Open Issues: 2
License: None
Language: Python
Repo Size: 3.98 MB
Dependencies:
23
Created: 12 months ago
Updated: about 2 months ago
Last pushed: about 2 months ago
Last synced: about 2 months ago
Topics: language-model, natural-language-processing, policy-gradient, reinforcement-learning
Files
Dependencies
- accelerate ==0.22.0
- bitsandbytes ==0.41.1
- datasets *
- ftfy *
- matplotlib *
- names *
- nltk *
- numba *
- numpy *
- nvidia-ml-py3 *
- openai *
- pandas *
- peft ==0.5.0
- scikit-learn *
- scipy *
- seaborn *
- sentence_transformers *
- sentencepiece *
- torch *
- tqdm *
- transformers ==4.32.1
- trl *
- wandb *