slime is an LLM training framework for RL Scaling.
Repository Index
77,353 visible repositories in the index
1–4 of 4 · Most stars
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks
- natural-language-processing
- prompt-tuning
- pretrained-language-model
- p-tuning
[ICLR 2025] LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
- fine-tuning
- llm
- long-context
- long-text