Daniel Han (@danielhanchen) 's Twitter Profile
Daniel Han

@danielhanchen

Building @UnslothAI. Finetune train LLMs faster. LLMs bug hunter. OSS package github.com/unslothai/unsl…. YC S24. Prev ML at NVIDIA. Hyperlearn used by NASA.

ID: 717359704226172928

linkhttps://unsloth.ai/ calendar_today05-04-2016 14:34:16

2,2K Tweet

23,23K Followers

1,1K Following

Daniel Han (@danielhanchen) 's Twitter Profile Photo
Daniel Han
@danielhanchen

a year ago

Vision finetuning is finally in🦥Unsloth AI! It took a while, but Llama 3.2 Vision, Pixtral, Qwen2 VL & all Llava variants now work! 1. QLoRA / LoRA is 1.3x to 2x faster for each 2. 30-70% less VRAM usage 3. 3 examples - Radiography, LaTeX, Q&A Extra stuff: 1. Pixtral chat

Vision finetuning is finally in🦥<a href="/UnslothAI/">Unsloth AI</a>! It took a while, but Llama 3.2 Vision, Pixtral, Qwen2 VL &amp; all Llava variants now work! 1. QLoRA / LoRA is 1.3x to 2x faster for each 2. 30-70% less VRAM usage 3. 3 examples - Radiography, LaTeX, Q&amp;A Extra stuff: 1. Pixtral chat