2 Repos
Awesome GitHub RepositoriesPost-Generation Sample Processing
Logic applied to generated model samples to log data or modify training masks before training.
Distinct from Data Processing Logic Generation: None of the candidates cover post-inference processing specifically for RL sample refinement and loss masking.
Explore 2 awesome GitHub repositories matching artificial intelligence & ml · Post-Generation Sample Processing. Refine with filters or upvote what's useful.
Awesome Post-Generation Sample Processing GitHub Repositories
Finde die besten Repos mit KI.Wir suchen mit KI nach den am besten passenden Repositories.
- facebookresearch/mmf
facebookresearch/mmf
5,635Auf GitHub ansehenMMF is a modular framework for building, training, and evaluating vision-and-language models. It provides a configuration-driven experiment system where model, dataset, and training parameters are defined through composable YAML files, alongside a curated model zoo of pretrained checkpoints for state-of-the-art multimodal architectures. The framework includes a multimodal dataset loader that downloads, processes, and batches vision-and-language data, and a vision-language model trainer supporting distributed training, mixed precision, and checkpoint-based resumption. The framework distinguish
Transforms raw data samples into model-ready dictionaries using custom callables.
Pythoncaptioningdeep-learningdialog - thudm/slime
THUDM/slime
4,259Auf GitHub ansehenSLIME is a distributed reinforcement learning framework for large language model post-training that bridges Megatron training with SGLang inference servers. It orchestrates scalable RL loops across GPU clusters, decoupling training and inference into independent processes that communicate over HTTP and NCCL for independent scaling and fault tolerance. The system supports multi-agent reinforcement learning workflows with parallel agent instances, customizable rollout strategies, and personalized agent serving that improves models from prior conversations without disrupting API serving. The fra
Modifies rollout data after log probability computation, such as updating loss masks or adding metadata to samples.
Python
