HN Explorer

danielhanchen

↗ HN profile [ 110 ms ] full profile

No user record in our sample, but danielhanchen has activity below (stories or comments). Likely we have partial data — the full bulk-load will fill profiles in.

  1. Mistral Medium 3.5 YaRN bug fix (huggingface.co)
    1 points 1
  2. Gemma 4 Fine-Tuning Guide (unsloth.ai)
    2 points 0
  3. Show HN: Unsloth Studio - Local Fine-tuning, Chat UI (github.com)

    Hey HN! We're excited to release Unsloth Studio - a culmination of many things we wanted to provide to the community - it includes: 1. A Chat UI which has auto healing tool calling, Python & bash code execution, web…

    8 points 2
  4. Qwen3.5: Towards Native Multimodal Agents (qwen.ai)
    434 points 44
  5. Qwen3-Coder-Next (qwen.ai)
    735 points 54
  6. Qwen-Image-2512 (qwen.ai)
    7 points 1
  7. Kimi K2 Thinking: How to Run Locally (docs.unsloth.ai)
    3 points 0
  8. LoRA Without Regret (thinkingmachines.ai)
    24 points 0
  9. Long context GPT-OSS fine-tuning (unsloth.ai)
    4 points 1
  10. Show HN: GPT OSS: How to run and fine-tune (docs.unsloth.ai)

    Hey everyone! Made a guide on finetuning OpenAI's OSS model and also on bug fixes! Also made a free Colab notebook for finetuning the 20B in under 14GB of VRAM!

    2 points 0
  11. Qwen3-30B-A3B-Instruct-2507 (huggingface.co)
    5 points 0
  12. Qwen3-Coder: Agentic coding in the world (qwenlm.github.io)
    765 points 39
  13. 2.71bit DeepSeek-V3-0324 (unsloth.ai)
    1 points 1
  14. Gemma 3: Google's new multimodal models (ai.google.dev)
    4 points 2
  15. How to Run QwQ-32B effectively (docs.unsloth.ai)
    4 points 4
  16. Unsloth AI (YC S24) is hiring ML engineers (x.com)
    1 points 0 job
  17. Train your own R1 reasoning model (unsloth.ai)
    11 points 6
  18. How to run 1.58bit DeepSeek R1 with Open WebUI (docs.openwebui.com)
    37 points 9
  19. Phi-4 Bug Fixes (unsloth.ai)
    193 points 70
  20. My take on the Post Pretraining world (twitter.com)
    1 points 3
  21. Dynamic 4bit Quantization (unsloth.ai)
    3 points 5
  22. Show HN: Finetune Llama 3.2 Vision in a Colab (colab.research.google.com)

    Hey HN! Just added vision finetuning support in Unsloth! VLMs like Llama 3.2 11B, 90B, Pixtral 12B, Qwen2 VL 2B, 7B, 72B and all Llava variants. Unsloth finetunes them up to 2x faster with up to 70% less VRAM without…

    9 points 0
  23. Python 3.11 is 1.25x faster than 3.10 (docs.python.org)
    3 points 6
  24. Fixing Gradient Accumulation (huggingface.co)
    2 points 0
  25. Unit Economics of LLM APIs (lesswrong.com)
    5 points 4