| 1. | | Kimi K2 Thinking: How to Run Locally (unsloth.ai) |
| 3 points by danielhanchen 16 days ago | past |
|
| 2. | | LoRA Without Regret (thinkingmachines.ai) |
| 24 points by danielhanchen 56 days ago | past |
|
| 3. | | Long context GPT-OSS fine-tuning (unsloth.ai) |
| 4 points by danielhanchen 88 days ago | past | 1 comment |
|
| 4. | | Show HN: GPT OSS: How to run and fine-tune (unsloth.ai) |
| 2 points by danielhanchen 3 months ago | past |
|
| 5. | | Qwen3-30B-A3B-Instruct-2507 (huggingface.co) |
| 5 points by danielhanchen 3 months ago | past |
|
| 6. | | Qwen3-Coder: Agentic coding in the world (qwenlm.github.io) |
| 765 points by danielhanchen 4 months ago | past | 366 comments |
|
| 7. | | 2.71bit DeepSeek-V3-0324 (unsloth.ai) |
| 1 point by danielhanchen 8 months ago | past | 1 comment |
|
| 8. | | Gemma 3: Google's new multimodal models (ai.google.dev) |
| 4 points by danielhanchen 8 months ago | past | 2 comments |
|
| 9. | | How to Run QwQ-32B effectively (unsloth.ai) |
| 4 points by danielhanchen 8 months ago | past | 3 comments |
|
| 10. | | Train your own R1 reasoning model (unsloth.ai) |
| 11 points by danielhanchen 9 months ago | past | 5 comments |
|
| 11. | | How to run 1.58bit DeepSeek R1 with Open WebUI (openwebui.com) |
| 37 points by danielhanchen 9 months ago | past | 9 comments |
|
| 12. | | Phi-4 Bug Fixes (unsloth.ai) |
| 193 points by danielhanchen 10 months ago | past | 68 comments |
|
| 13. | | My take on the Post Pretraining world (twitter.com/danielhanchen) |
| 1 point by danielhanchen 11 months ago | past | 3 comments |
|
| 14. | | Dynamic 4bit Quantization (unsloth.ai) |
| 3 points by danielhanchen 11 months ago | past | 5 comments |
|
| 15. | | Show HN: Finetune Llama 3.2 Vision in a Colab (colab.research.google.com) |
| 10 points by danielhanchen on Nov 21, 2024 | past |
|
| 16. | | Python 3.11 is 1.25x faster than 3.10 (python.org) |
| 3 points by danielhanchen on Nov 4, 2024 | past | 5 comments |
|
| 17. | | Fixing Gradient Accumulation (huggingface.co) |
| 2 points by danielhanchen on Oct 16, 2024 | past |
|
| 18. | | Unit Economics of LLM APIs (lesswrong.com) |
| 5 points by danielhanchen on Aug 27, 2024 | past | 4 comments |
|
| 19. | | LoRA Learns Less and Forgets Less Updated (openreview.net) |
| 1 point by danielhanchen on Aug 27, 2024 | past | 1 comment |
|
| 20. | | VLLM automatic prefix / prompt caching (vllm.ai) |
| 2 points by danielhanchen on Aug 25, 2024 | past | 1 comment |
|
| 21. | | Higher Temperatures and Min_p Sampling (arxiv.org) |
| 1 point by danielhanchen on Aug 23, 2024 | past | 1 comment |
|
| 22. | | Show HN: Open-source fine-tuning in a Colab notebook (colab.research.google.com) |
| 5 points by danielhanchen on Aug 21, 2024 | past |
|
| 23. | | Sahm rule signals start of recession (stlouisfed.org) |
| 4 points by danielhanchen on Aug 2, 2024 | past | 3 comments |
|
| 24. | | Low Level Technicals of LLMs [video] (youtube.com) |
| 1 point by danielhanchen on Aug 1, 2024 | past | 1 comment |
|
| 25. | | Gemma-2 2B beats GPT3.5 on Chatbot Arena (huggingface.co) |
| 5 points by danielhanchen on July 31, 2024 | past | 1 comment |
|
| 26. | | HuggingChat – Chat UI for Llama 3.1 405B (huggingface.co) |
| 5 points by danielhanchen on July 29, 2024 | past |
|
| 27. | | Fine-Tune Llama 3.1 Ultra-Efficiently with Unsloth (huggingface.co) |
| 3 points by danielhanchen on July 29, 2024 | past |
|
| 28. | | Yield Curve and Predicted GDP Growth (clevelandfed.org) |
| 2 points by danielhanchen on July 29, 2024 | past |
|
| 29. | | Cloudflare DNS + Malware Blocking (one.one) |
| 3 points by danielhanchen on July 28, 2024 | past | 4 comments |
|
| 30. | | SIMD at Insomniac Games: How We Do the Shuffle (gdcvault.com) |
| 1 point by danielhanchen on July 27, 2024 | past |
|
|
| More |
