Search: github.com/unslothai | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

1.

Show HN: Finetune Llama-3.1 2x faster in a Colab (colab.research.google.com)

16 points

2 years ago

2.

Show HN: Open-source fine-tuning in a Colab notebook (colab.research.google.com)

5 points

2 years ago

3.

Finetune language models 30x faster (unsloth.ai)

2 points

3 years ago

4.

Show HN: 80% faster, 50% less memory, 0% loss of accuracy Llama finetuning (github.com/unslothai)

385 points

3 years ago

5.

Unsloth: 80% faster, 50% less memory, 0% accuracy loss Llama finetuning (github.com/unslothai)

132 points

3 years ago

6.

Show HN: Unsloth Studio - Local Fine-tuning, Chat UI (github.com/unslothai)

8 points

3 months ago

7.

Unsloth – Train LLMs 2x faster with 70% less VRAM (github.com/unslothai)

3 points

6 months ago

8.

Unsloth Now Supports GRPO (github.com/unslothai)

3 points

a year ago

9.

Show HN: Unsloth – finetune Llama 2x faster 50% less memory on your GPU (github.com/unslothai)

3 points

3 years ago

10.

I optimised my vibe coding tech stack cost to $0

12 points

5 months ago

11.

Show HN: Fine-tuning an LLM on your code for better code completions (prvn.sh)

4 points

a year ago

12.

Use GRPO policy locally with Qwen and Unsloth (github.com/ArturTanona)

2 points

a year ago

13.

Show HN: Run Unsloth Dynamic GGUFs using Docker model runner (github.com/docker)

3 points

7 months ago

14.

Show HN: Llama-8B Teaches Itself Baby Steps to Deep Research Using RL (github.com/dCaples)

39 points

a year ago

15.

Show HN: Fine-tuned Llama 3.2 3B to match 70B models for local transcripts (bilawal.net)

31 points

9 months ago

16.

Show HN: Kiln – AI Boilerplate with Evals, Fine-Tuning, Synthetic Data, and Git (github.com/Kiln-AI)

10 points

10 months ago

17.

Show HN: Unfat, a library to easily train and distill LoRAs for LLMs (github.com/reissbaker)

6 points

a year ago

18.

Show HN: A single CLI to manage llama.cpp/vLLM/Ollama models (github.com/av)

2 points

3 months ago

19.

Ollama and Bifrost –> Qwen3 in Claude Code

1 point

9 months ago

20.

Show HN: We Gave an LLM Adventure Engine a Body, Now It Feels Exhausted (mycelialmirror.medium.com)

1 point

3 months ago

21.

Show HN: Kore – Stack based language where compiler is the reward function (github.com/konf-dev)

1 point

4 months ago