Hacker News
- Finetune and Run Llama 4 with Unsloth https://unsloth.ai/blog/llama4 0 comments
- Fine-tune Google's Gemma 3 https://unsloth.ai/blog/gemma3 75 comments
- Long-Context GRPO https://unsloth.ai/blog/grpo 22 comments
- Train your own R1 reasoning model https://unsloth.ai/blog/r1-reasoning 5 comments
- Run DeepSeek R1 Dynamic 1.58-bit https://unsloth.ai/blog/deepseekr1-dynamic 332 comments
- Run DeepSeek R1 Dynamic 1.58-bit https://unsloth.ai/blog/deepseekr1-dynamic 3 comments
- Phi-4 Bug Fixes https://unsloth.ai/blog/phi4 68 comments
- Dynamic 4bit Quantization https://unsloth.ai/blog/dynamic-4bit 5 comments
- Unsloth creators fix universal error with gradient accumulation https://unsloth.ai/blog/gradient 2 comments
- Bugs in LLM Training – Gradient Accumulation Fix https://unsloth.ai/blog/gradient 16 comments
- Fixing Gemma Bugs https://unsloth.ai/blog/gemma-bugs 63 comments
Linking pages
- Zed now predicts your next edit with Zeta, our new open model https://zed.dev/blog/edit-prediction 321 comments
- Qwen2.5: A Party of Foundation Models! | Qwen https://qwenlm.github.io/blog/qwen2.5/ 38 comments
- 7 Lessons from building a small-scale AI application https://www.thelis.org/blog/lessons-from-ai 6 comments
- Curated Resources to Build & Grow Your AI Startup https://aistartup.co/ 0 comments