Search: github.com/unslothai | Heykuki News

HK

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

2 years ago

16 points

2.

Show HN: Open-source fine-tuning in a Colab notebook

colab.research.google.com

2 years ago

5 points

3.

Finetune language models 30x faster

3 years ago

2 points

4.

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

github.com/unslothai

3 years ago

385 points

5.

Unsloth: 80% faster, 50% less memory, 0% accuracy loss Llama finetuning

github.com/unslothai

3 years ago

132 points

6.

Show HN: Unsloth Studio - Local Fine-tuning, Chat UI

github.com/unslothai

3 months ago

8 points

7.

Unsloth – Train LLMs 2x faster with 70% less VRAM

github.com/unslothai

6 months ago

3 points

8.

Unsloth Now Supports GRPO

github.com/unslothai

a year ago

3 points

9.

Show HN: Unsloth – finetune Llama 2x faster 50% less memory on your GPU

github.com/unslothai

3 years ago

3 points

10.

I optimised my vibe coding tech stack cost to $0

6 months ago

12 points

11.

Show HN: Fine-tuning an LLM on your code for better code completions

a year ago

4 points

12.

Use GRPO policy locally with Qwen and Unsloth

github.com/ArturTanona

a year ago

2 points

13.

Show HN: Run Unsloth Dynamic GGUFs using Docker model runner

github.com/docker

7 months ago

3 points

14.

Show HN: Llama-8B Teaches Itself Baby Steps to Deep Research Using RL

github.com/dCaples

a year ago

39 points

15.

Show HN: Fine-tuned Llama 3.2 3B to match 70B models for local transcripts

10 months ago

31 points

16.

Show HN: Kiln – AI Boilerplate with Evals, Fine-Tuning, Synthetic Data, and Git

github.com/Kiln-AI

a year ago

10 points

17.

Show HN: Unfat, a library to easily train and distill LoRAs for LLMs

github.com/reissbaker

a year ago

6 points

18.

Show HN: A single CLI to manage llama.cpp/vLLM/Ollama models

3 months ago

2 points

19.

Ollama and Bifrost –> Qwen3 in Claude Code

10 months ago

1 points

20.

Show HN: We Gave an LLM Adventure Engine a Body, Now It Feels Exhausted

mycelialmirror.medium.com

4 months ago

1 points

21.

Show HN: Kore – Stack based language where compiler is the reward function

github.com/konf-dev

4 months ago

1 points