| 308 |
Fine-Tuning Llama-2: A Comprehensive Case Study for Tailoring Custom Models |
2023-08-11 |
| 143 |
Llama 2 is about as factually accurate as GPT-4 for summaries and is 30X cheaper |
2023-08-29 |
| 110 |
Continuous batching to increase LLM inference throughput and reduce p50 latency |
2023-08-15 |
| 95 |
Numbers every LLM Developer should know |
2023-08-12 |
| 78 |
ThirdAI Uses Ray for Parallel Training of Billion-Parameter NN on Commodity CPUs |
2023-08-30 |
| 36 |
Ray breaks the $1/TB barrier as the world’s most cost-efficient sorting system |
2023-01-24 |