| 166 |
Fixing Gemma Bugs |
2024-03-11 |
| 81 |
Bugs in LLM Training – Gradient Accumulation Fix |
2024-10-16 |
| 3 |
2x faster Gemma 2 finetuning and 63% less VRAM |
2024-07-04 |
| 3 |
Unsloth: 30x faster AI training |
2023-12-01 |
| 3 |
Unsloth: Easily finetune and train LLMs Get faster with unsloth |
2024-11-07 |
| 2 |
CodeLlama-34B 13x faster finetuning |
2023-12-16 |
| 1 |
Continued LLM Pretraining with Unsloth |
2024-06-05 |
| 3 |
Dynamic 4bit Quantization |
2024-12-04 |
| 193 |
Phi-4 Bug Fixes |
2025-01-10 |
| 767 |
Run DeepSeek R1 Dynamic 1.58-bit |
2025-01-28 |
| 11 |
Train your own R1 reasoning model |
2025-02-06 |
| 60 |
Long-Context GRPO |
2025-02-21 |
| 4 |
How to Run QwQ-32B effectively |
2025-03-07 |
| 226 |
Fine-tune Google's Gemma 3 |
2025-03-19 |
| 2 |
Run DeepSeek-V3-0324 locally |
2025-03-26 |
| 1 |
2.71bit DeepSeek-V3-0324 |
2025-03-26 |