24 dependents
| Package | Description | Downloads/month |
|---|---|---|
| Speculative decoding engine with local and remote target model execution | 5K | |
| A library for efficient Retrieval-Augmented Generation research | 3K | |
| Uncertainty Estimation Toolkit for Transformer Language Models | 2K | |
| [ICML 2024] TrustLLM: Trustworthiness in Large Language Models | 1K | |
| A Unified, Customizable, and High-Performing Open-Source Toolkit for Prompt Opti... | 705 | |
| Easy Jailbreak toolkit | 559 | |
| Tools for evaluating reward models | 505 | |
| PyTerrier RAG pipelines | 467 | |
| 381 | ||
| An experiment with Vicuna. | 343 | |
| A context tracing tool for LLM | 292 | |
| Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (N... | 234 | |
| tools for detecting bias patterns of LLMs | 234 | |
| A high-throughput and memory-efficient inference and serving engine for LLMs | 219 | |
| FlagEmbedding model worker for fastchat. | 196 | |
| Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding ... | 175 | |
| A Package for generating query-passage relevance assessment labels. | 165 | |
| An open platform for training, serving, and evaluating large language model base... | 127 | |
| Retrieval-Augmented Generation battle! | 122 | |
| Lookahead Decoding Implementation | 117 | |
| An installable version of ComfyUI | 95 | |
| A context traceback tool for LLM | 70 | |
| Flexible RAG | 49 | |
| Test version of evalverse | 14 |
