Zayne Sprague

RACA. Python

SkillFactory. Python

CalibrateThenAct. Calibrate-Then-Act: Cost-Aware Exploration in LLM Agents

vllm. A high-throughput and memory-efficient inference and serving engine for LLMs

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

verl. verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

EvalAgent. Python

evalchemy. Automatic evals for LLMs

curator. Synthetic data curation for post-training and structured data extraction

open-thoughts. Fully open data curation for reasoning models

CachedLMQuery. Toolkit for prompting and caching query results.

SAT-LM. SatLM: SATisfiability-Aided Language Models using Declarative Prompting (NeurIPS 2023)

Natural_Language_Deduction_with_Incomplete_Information. Python

GNLP-Diffusion-PC. A tool to perform natural language based point cloud generation using diffusion models

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

youtubeData. you tube data

gym. A toolkit for developing and comparing reinforcement learning algorithms.