Hackernews posts about Unsloth

1. Unsloth Dynamic 2.0 GGUFs (docs.unsloth.ai)
   3 points by serialx 28 days ago | discuss
2. Unsloth: GPT-OSS (docs.unsloth.ai)
   1 points by tosh 18 days ago | discuss
3. Unsloth improvements to gguf tool calling for Qwen3 (huggingface.co)
   1 points by dhorthy 23 days ago | discuss
4. Show HN: Kiln – AI Boilerplate with Evals, Fine-Tuning, Synthetic Data, and Git (github.com)
   10 points by scosman 26 days ago | 1 comments
5. Qwen3-Coder: How to Run Locally (docs.unsloth.ai)
   3 points by tosh 30 days ago | discuss
6. Fine-tuning GPT-OSS-20B (colab.research.google.com)
   2 points by tosh 15 days ago | discuss
7. Show HN: GPT OSS: How to run and fine-tune (docs.unsloth.ai)
   2 points by danielhanchen 15 days ago | discuss
8. Unsloth: 80% faster, 50% less memory, 0% accuracy loss Llama finetuning (github.com)
   132 points by bratao over 1 year ago | 3 comments
9. Unsloth's 5 challenges to get a job offer of $500K/year and equity (twitter.com)
   17 points by amrrs 6 months ago | 21 comments
10. Run Qwen3-Coder-480B-A35B Locally with Unsloth Dynamic Quants (docs.unsloth.ai)
    8 points by handfuloflight about 1 month ago | discuss
11. Train your own R1 reasoning model with Unsloth (unsloth.ai)
    6 points by mohsen1 7 months ago | discuss
12. Unsloth creators fix universal error with gradient accumulation (unsloth.ai)
    4 points by ZQ-Dev8 10 months ago | 2 comments
13. Unsloth: 30x faster AI training (unsloth.ai)
    3 points by Tomte over 1 year ago | 1 comments
14. Unsloth Now Supports GRPO (github.com)
    3 points by sadiq 7 months ago | discuss
15. Show HN: Fine-Tuning Llama-3 for Psychology Question Answering Using Unsloth (ubiai.tools)
    3 points by Mesterniz 8 months ago | discuss
16. Unsloth – Dynamic 4-bit Quantization (unsloth.ai)
    3 points by amrrs 9 months ago | discuss
17. Unsloth: Easily finetune and train LLMs Get faster with unsloth (unsloth.ai)
    3 points by handfuloflight 10 months ago | discuss
18. Fine-Tune Llama 3.1 Ultra-Efficiently with Unsloth (huggingface.co)
    3 points by danielhanchen about 1 year ago | discuss
19. Show HN: Unsloth – finetune Llama 2x faster 50% less memory on your GPU (github.com)
    3 points by unsloth over 1 year ago | discuss
20. Unsloth – Dynamic 4-bit Quantization (unsloth.ai)
    2 points by gkbrk about 1 month ago | discuss
21. Unsloth Dynamic v.20 GGUFs (unsloth.ai)
    2 points by tosh 4 months ago | discuss
22. Finetune and Run Llama 4 with Unsloth (unsloth.ai)
    2 points by tosh 5 months ago | discuss
23. Unsloth: Dynamic 4-bit Quantization (2024) (unsloth.ai)
    2 points by tosh 5 months ago | discuss
24. Use GRPO policy locally with Qwen and Unsloth (github.com)
    2 points by art_mach 7 months ago | discuss
25. Make LLM Fine-Tuning 2x Faster with Unsloth and HuggingFace TRL (huggingface.co)
    2 points by DreamGen over 1 year ago | discuss
26. Ask HN: Knowledge/skills to develop and contribute to projects like Unsloth?
    1 points by hedgehog0 about 1 month ago | discuss
27. Unsloth Dynamic v2.0 GGUFs (unsloth.ai)
    1 points by kevinsimper 4 months ago | discuss
28. Fine-Tuning Ollama Models with Unsloth (medium.com)
    1 points by handfuloflight 9 months ago | discuss
29. Continued LLM Pretraining with Unsloth (unsloth.ai)
    1 points by swyx about 1 year ago | discuss
30. Show HN: 80% faster, 50% less memory, 0% loss of accuracy Llama finetuning (github.com)
    385 points by danielhanchen over 1 year ago | 119 comments
31. Show HN: Mutable.ai Codebase chat that uses a Wiki for RAG (wiki.mutable.ai)
    48 points by oshams about 1 year ago | 20 comments
32. Show HN: Llama-8B Teaches Itself Baby Steps to Deep Research Using RL (github.com)
    39 points by diegocaples 6 months ago | 3 comments
33. Show HN: Finetune Llama-3.1 2x faster in a Colab (colab.research.google.com)
    16 points by danielhanchen about 1 year ago | 2 comments
34. Show HN: Finetune Llama 3.2 Vision in a Colab (colab.research.google.com)
    10 points by danielhanchen 9 months ago | discuss
35. Show HN: I built a website where you can easily fine-tune Llama 3.1 models (www.tunellama.com)
    8 points by hamadafm 12 months ago | 4 comments
36. Show HN: I built cracked engineers – a new platform for technical job roles only (www.crackedengineers.com)
    8 points by ai-epiphany 10 months ago | 2 comments
37. Show HN: Unfat, a library to easily train and distill LoRAs for LLMs (github.com)
    6 points by reissbaker 6 months ago | discuss