LL
lit-llama
Model Optimization·infrastructure·open·#598 of 944·+234·Surging
67.3
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%
74.3
Maintenance
30%
63.3
Friction
20%
97.5
Ecosystem
15%
40.7
Momentum
0.79Surging
7d change +0.84
High confidenceIn Model Optimization
Ranked #9 of 16