Search: unsloth.ai | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

1.

Show HN: 80% faster, 50% less memory, 0% loss of accuracy Llama finetuning

github.com/unslothai

3 years ago

385 points

2.

I optimised my vibe coding tech stack cost to $0

6 months ago

12 points

3.

Show HN: Run Unsloth Dynamic GGUFs using Docker model runner

github.com/docker

7 months ago

3 points

4.

Run DeepSeek R1 Dynamic 1.58-bit

a year ago

767 points

5.

How to run Qwen 3.5 locally

4 months ago

490 points

6.

Qwen3.5 Fine-Tuning Guide

4 months ago

416 points

7.

3 months ago

388 points

8.

Unsloth Dynamic 2.0 GGUFs

4 months ago

237 points

9.

Fine-tune Google's Gemma 3

a year ago

226 points

10.

Phi-4 Bug Fixes

a year ago

193 points

11.

GPT-OSS Reinforcement Learning

docs.unsloth.ai

9 months ago

180 points

12.

Fixing Gemma Bugs

2 years ago

166 points

13.

Making LLM Training Faster with Unsloth and NVIDIA

2 months ago

129 points

14.

Bugs in LLM Training – Gradient Accumulation Fix

2 years ago

81 points

15.

Long-Context GRPO

a year ago

60 points

16.

Run DeepSeek R1 Dynamic 1.58-bit

a year ago

19 points

17.

Train your own R1 reasoning model

a year ago

11 points

18.

Unsloth Joins PyTorch Ecosystem

a month ago

8 points

19.

Run Qwen3-Coder-480B-A35B Locally with Unsloth Dynamic Quants

docs.unsloth.ai

a year ago

8 points

20.

Train your own R1 reasoning model with Unsloth

a year ago

6 points

21.

Qwen3.5 GGUF Benchmarks

4 months ago

5 points

22.

How to Run QwQ-32B effectively

docs.unsloth.ai

a year ago

4 points

23.

Unsloth creators fix universal error with gradient accumulation

2 years ago

4 points

24.

Claude Code makes local LLMs 90% slower

3 months ago

4 points

25.

Long context GPT-OSS fine-tuning

10 months ago

4 points

26.

Qwen3-Coder-Next: How to Run Locally

5 months ago

4 points

27.

Unsloth: GLM-4.7-Flash

5 months ago

4 points

28.

Dynamic 4bit Quantization

2 years ago

3 points

29.

1.8-3.3x faster Embedding finetuning now in Unsloth

5 months ago

3 points

30.

2x faster Gemma 2 finetuning and 63% less VRAM

2 years ago

3 points