OpenPipe on HN
10 posts with 1+ points in 2024
Posts by Month (10 total)
Hacker News Posts
| Title | Points | Comments | Date |
|---|---|---|---|
| Using reinforcement learning and $4.80 of GPU time to find the best … | 217 | 95 | 2024-10-28 |
| OpenPipe Mixture of Agents: Outperform GPT-4 at 1/25th the Cost | 13 | 2 | 2024-06-20 |
| Analyzing OpenAI's Reinforcement Fine-Tuning: Less Data, Better Results | 4 | 0 | 2024-12-30 |
| What we've learned in 3 days of Llama 3 | 3 | 0 | 2024-04-22 |
| Fine-Tuning Best Practices: Models | 2 | 0 | 2024-09-24 |
| LLM Fine-Tuning Best Practices for Training Data Curation | 1 | 2 | 2024-08-02 |
| S-LoRA: Serving Thousands of Models from One GPU for Fun and Profit | 1 | 0 | 2024-01-18 |
| DPO fine-tuning outperforms SFT | 1 | 0 | 2024-10-02 |
| OpenPipe | 1 | 0 | 2024-09-28 |
| Mixtral Curious? Comparing Mistral 7B and Mixtral for fine-tuning | 1 | 0 | 2024-02-29 |