LL

lit-llama

Model Optimization·infrastructure·open·#777 of 886·+52·Stable

59.6

Low

High confidence

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

Pillar Breakdown

Adoption

35%

48.8

Maintenance

30%

63.3

Friction

20%

98.0

Ecosystem

15%

40.8

Momentum

0.41Stable
7d change -1.23
High confidence

In Model Optimization

Ranked #13 of 17

Similar Tools