EfficientLLM
π§ TODO List
π§± Core Codebase & API
π Expected Release: Before June 1, 2025
- Code for the whole project including pre-training, PEFT, inference, etc.
- API for evaluating model latency, memory, throughput, etc.
- Integrate metric API into the core codebase.
- Code cleanup and documentation.
π§ PEFT Models (Parameter-Efficient Fine-Tuning)
π Development Starts: After June 15, 2025
- Release fine-tuned checkpoints and configuration files.
π¦ Pretrained Models
π Gradual Release: Starting August 2025
- Release base pretrained checkpoints
- Provide scripts for inference and reproducibility.
Star History
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
π
Ask for provider support