percyraskova
/

llm-training

Text Generation

political-theory

Model card Files Files and versions

llm-training / src /prolewiki_llm

126 kB

1 contributor

History: 1 commit

percyraskova's picture

Upload folder using huggingface_hub

81b3473 verified about 1 month ago

__init__.py

2.76 kB

Upload folder using huggingface_hub about 1 month ago
convert_to_qwen.py

1.44 kB

Upload folder using huggingface_hub about 1 month ago
export_grpo_dataset.py

6.86 kB

Upload folder using huggingface_hub about 1 month ago
grpo_rewards.py

62.8 kB

Upload folder using huggingface_hub about 1 month ago
train_grpo_marxist.py

10.7 kB

Upload folder using huggingface_hub about 1 month ago
train_headless.py

16.8 kB

Upload folder using huggingface_hub about 1 month ago
train_marxist.py

6.04 kB

Upload folder using huggingface_hub about 1 month ago
transform_to_grpo.py

1.91 kB

Upload folder using huggingface_hub about 1 month ago
wandb_logging.py

16.4 kB

Upload folder using huggingface_hub about 1 month ago