🏝️ On Vacation

Kai Ruan

6cf

15 35 230

x66ccff

AI & ML interests

AI for Science

Recent Activity

liked a dataset about 10 hours ago

armand0e/claude-fable-5-claude-code

upvoted a collection about 11 hours ago

Qwen2.5

liked a model 1 day ago

theabbie/needle-pi-coding-agent

View all activity

Organizations

liked a dataset about 10 hours ago

armand0e/claude-fable-5-claude-code

Traces • Updated 28 days ago • 63 • 15.8k • 316

upvoted a collection about 11 hours ago

Qwen2.5

Collection

Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. • 43 items • Updated Mar 2 • 731

liked 3 models 1 day ago

liked 2 models 7 days ago

bottlecapai/ThinkingCap-Qwen3.6-27B

Image-Text-to-Text • 27B • Updated 7 days ago • 8.24k • • 395

GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF

Text Generation • 1B • Updated 4 days ago • 121k • 268

reacted to danielhanchen's post with 🤗👍🚀🔥 8 days ago

Post

5899

DeepSeek-V4 can now run locally with Unsloth GGUFs! 🐳

Run lossless DeepSeek-V4-Flash on 168GB RAM or
3-bit works on 110GB Mac, RAM, VRAM setups.

Run via Unsloth Studio or llama.cpp.

GGUF: unsloth/DeepSeek-V4-Flash-GGUF
Guide: https://unsloth.ai/docs/models/deepseek-v4

upvoted an article 8 days ago

Article

A brief history of distillation in AI

sergiopaniego

•

14 days ago

• 3

replied to sergiopaniego's post 8 days ago

very helpful blog, thank you 🤗

reacted to sergiopaniego's post with ❤️👍🔥 8 days ago

Post

7592

Frontier models use distillation as a step of their post-training pipelines.

In 2026 it has three jobs: compress a big model into a small one, merge RL experts into a single model, and let a model teach itself.

I wrote up which frontier models use each one and how: https://huggingface.co/blog/sergiopaniego/distillation-2026

It pairs with Class 2 of the Training an Agent series Ben and I are doing, where we teach these techniques hands-on with TRL!