Daniel Han

3.2K posts

Daniel Han banner
Daniel Han

Daniel Han

@danielhanchen

Building @UnslothAI. Faster RL / training. LLMs bug hunter. OSS package https://t.co/aRyAAgKOR7. YC S24. Prev ML at NVIDIA. Hyperlearn used by NASA.

San Francisco Katılım Nisan 2016
1.9K Takip Edilen31.4K Takipçiler
Sabitlenmiş Tweet
Daniel Han
Daniel Han@danielhanchen·
We're excited to introduce Unsloth🦥Studio! 1. Chat UI has auto healing tool calling, Python & bash code execution, web search, image, docs input + more! 2. Finetune audio, vision, LLMs with an AI Assist data prep 3. Supports GGUFs, Mac, Windows, Linux + audio gen 4. Has SVG rendering, export to GGUF 5. gpt-oss harmony rendering, all inference params pre-set 6. Data designer + synthetic data generation 7. Fast parallel data prep + embedding finetuning 8. And much much more! To get it, run: pip install unsloth unsloth studio setup unsloth studio -H 0.0.0.0 -p 8888
Unsloth AI@UnslothAI

Introducing Unsloth Studio ✨ A new open-source web UI to train and run LLMs. • Run models locally on Mac, Windows, Linux • Train 500+ models 2x faster with 70% less VRAM • Supports GGUF, vision, audio, embedding models • Auto-create datasets from PDF, CSV, DOCX • Self-healing tool calling and code execution • Compare models side by side + export to GGUF GitHub: github.com/unslothai/unsl… Blog and Guide: unsloth.ai/docs/new/studio Available now on Hugging Face, NVIDIA, Docker and Colab.

English
21
50
440
44.1K
Daniel Han retweetledi
Matthew Berman
Matthew Berman@MatthewBerman·
Running a fine-tune on Qwen3.5-35B-A3B using @UnslothAI It's ALIIIIIVEEE
Matthew Berman tweet media
English
12
7
78
4.8K
Daniel Han retweetledi
AI at AMD
AI at AMD@AIatAMD·
See how @danielhanchen answered this at the last AMD AI DevDay, and join us April 30
English
1
0
4
785
Daniel Han retweetledi
Nicolas Dessaigne
Nicolas Dessaigne@dessaigne·
Unsloth is such an impressive team. With just a few people, they already had a huge impact in the world of AI, from fixing bugs in open source models to crazy improvements in performance. They are now launching Unsloth Studio to train and run LLMs 🚀
Unsloth AI@UnslothAI

Introducing Unsloth Studio ✨ A new open-source web UI to train and run LLMs. • Run models locally on Mac, Windows, Linux • Train 500+ models 2x faster with 70% less VRAM • Supports GGUF, vision, audio, embedding models • Auto-create datasets from PDF, CSV, DOCX • Self-healing tool calling and code execution • Compare models side by side + export to GGUF GitHub: github.com/unslothai/unsl… Blog and Guide: unsloth.ai/docs/new/studio Available now on Hugging Face, NVIDIA, Docker and Colab.

English
6
7
49
15.3K
Daniel Han retweetledi
Chubby♨️
Chubby♨️@kimmonismus·
So cool, unsloth introdocues Unsloth Studio a new open-source web app that lets you run, train, compare, and export hundreds of LLMs locally with much lower VRAM usage while also turning files like PDFs, CSVs, and DOCXs into training datasets.
Unsloth AI@UnslothAI

Introducing Unsloth Studio ✨ A new open-source web UI to train and run LLMs. • Run models locally on Mac, Windows, Linux • Train 500+ models 2x faster with 70% less VRAM • Supports GGUF, vision, audio, embedding models • Auto-create datasets from PDF, CSV, DOCX • Self-healing tool calling and code execution • Compare models side by side + export to GGUF GitHub: github.com/unslothai/unsl… Blog and Guide: unsloth.ai/docs/new/studio Available now on Hugging Face, NVIDIA, Docker and Colab.

English
16
35
425
49K
Daniel Han retweetledi
Matthew Berman
Matthew Berman@MatthewBerman·
Well that was easy!!!
Matthew Berman tweet media
Unsloth AI@UnslothAI

Introducing Unsloth Studio ✨ A new open-source web UI to train and run LLMs. • Run models locally on Mac, Windows, Linux • Train 500+ models 2x faster with 70% less VRAM • Supports GGUF, vision, audio, embedding models • Auto-create datasets from PDF, CSV, DOCX • Self-healing tool calling and code execution • Compare models side by side + export to GGUF GitHub: github.com/unslothai/unsl… Blog and Guide: unsloth.ai/docs/new/studio Available now on Hugging Face, NVIDIA, Docker and Colab.

English
12
17
276
50.5K
Unsloth AI
Unsloth AI@UnslothAI·
Introducing Unsloth Studio ✨ A new open-source web UI to train and run LLMs. • Run models locally on Mac, Windows, Linux • Train 500+ models 2x faster with 70% less VRAM • Supports GGUF, vision, audio, embedding models • Auto-create datasets from PDF, CSV, DOCX • Self-healing tool calling and code execution • Compare models side by side + export to GGUF GitHub: github.com/unslothai/unsl… Blog and Guide: unsloth.ai/docs/new/studio Available now on Hugging Face, NVIDIA, Docker and Colab.
English
214
822
4.9K
1.4M
alexine 🏴‍☠️
alexine 🏴‍☠️@alexinexxx·
unsloth’s impact on the industry is insane
Unsloth AI@UnslothAI

Introducing Unsloth Studio ✨ A new open-source web UI to train and run LLMs. • Run models locally on Mac, Windows, Linux • Train 500+ models 2x faster with 70% less VRAM • Supports GGUF, vision, audio, embedding models • Auto-create datasets from PDF, CSV, DOCX • Self-healing tool calling and code execution • Compare models side by side + export to GGUF GitHub: github.com/unslothai/unsl… Blog and Guide: unsloth.ai/docs/new/studio Available now on Hugging Face, NVIDIA, Docker and Colab.

English
4
2
110
10.1K
Daniel Han retweetledi
Joey (e/λ)
Joey (e/λ)@shxf0072·
fuck yeahh.... unsloth doesn't get enough praise it deserves!
Unsloth AI@UnslothAI

Introducing Unsloth Studio ✨ A new open-source web UI to train and run LLMs. • Run models locally on Mac, Windows, Linux • Train 500+ models 2x faster with 70% less VRAM • Supports GGUF, vision, audio, embedding models • Auto-create datasets from PDF, CSV, DOCX • Self-healing tool calling and code execution • Compare models side by side + export to GGUF GitHub: github.com/unslothai/unsl… Blog and Guide: unsloth.ai/docs/new/studio Available now on Hugging Face, NVIDIA, Docker and Colab.

English
4
6
105
7.8K
RO2⚡️
RO2⚡️@risingodegua·
@UnslothAI For some reason, all tabs except Chat is disabled for me
RO2⚡️ tweet media
English
1
0
1
2.2K
Maxime Labonne
Maxime Labonne@maximelabonne·
@UnslothAI Oh that's really cool, I love the built-in data pipeline. Congrats guys!
English
1
0
7
1.1K
Wey Gu 古思为
Wey Gu 古思为@wey_gu·
too good to be true - Auto-create datasets from PDF, CSV, DOCX - Self-healing tool calling and code execution - Compare models side by side + export to GGUF
Daniel Han@danielhanchen

We're excited to introduce Unsloth🦥Studio! 1. Chat UI has auto healing tool calling, Python & bash code execution, web search, image, docs input + more! 2. Finetune audio, vision, LLMs with an AI Assist data prep 3. Supports GGUFs, Mac, Windows, Linux + audio gen 4. Has SVG rendering, export to GGUF 5. gpt-oss harmony rendering, all inference params pre-set 6. Data designer + synthetic data generation 7. Fast parallel data prep + embedding finetuning 8. And much much more! To get it, run: pip install unsloth unsloth studio setup unsloth studio -H 0.0.0.0 -p 8888

English
3
1
12
2.7K
darthsider
darthsider@thedarthsider·
@UnslothAI @danielhanchen Any plans for Multi-device inference? Sharding across multiple devices not multiple gpus in same device.
English
1
0
1
271

Keşfet

@UnslothAI @dessaigne @kimmonismus @MaziyarPanahi @nisten @alexinexxx @shxf0072 @elliotarledge