Ann Huang PRO

erinys

AI & ML interests

None yet

Recent Activity

Reacted to reach-vb's post with πŸš€ 5 days ago
What a brilliant week for Open Source AI! Qwen 2.5 Coder by Alibaba - 0.5B / 1.5B / 3B / 7B / 14B/ 32B (Base + Instruct) Code generation LLMs, with 32B tackling giants like Gemnini 1.5 Pro, Claude Sonnet https://huggingface.co/collections/Qwen/qwen25-coder-66eaa22e6f99801bf65b0c2f LLM2CLIP from Microsoft - Leverage LLMs to train ultra-powerful CLIP models! Boosts performance over the previous SOTA by ~17% https://huggingface.co/collections/microsoft/llm2clip-672323a266173cfa40b32d4c Athene v2 Chat & Agent by NexusFlow - SoTA general LLM fine-tuned from Qwen 2.5 72B excels at Chat + Function Calling/ JSON/ Agents https://huggingface.co/collections/Nexusflow/athene-v2-6735b85e505981a794fb02cc Orca Agent Instruct by Microsoft - 1 million instruct pairs covering text editing, creative writing, coding, reading comprehension, etc - permissively licensed https://huggingface.co/datasets/microsoft/orca-agentinstruct-1M-v1 Ultravox by FixieAI - 70B/ 8B model approaching GPT4o level, pick any LLM, train an adapter with Whisper as Audio Encoder https://huggingface.co/collections/reach-vb/ultravox-audio-language-model-release-67373b602af0a52b2a88ae71 JanusFlow 1.3 by DeepSeek - Next iteration of their Unified MultiModal LLM Janus with RectifiedFlow https://huggingface.co/deepseek-ai/JanusFlow-1.3B Common Corpus by Pleais - 2,003,039,184,047 multilingual, commercially permissive and high quality tokens! https://huggingface.co/datasets/PleIAs/common_corpus I'm sure I missed a lot, can't wait for the next week! Put down in comments what I missed! πŸ€—
View all activity

Articles

Organizations

Posts 3

view post
Post
1942
We shut down XetHub today after almost 2 years. What we learned from launching our Git-scaled product from scratch:
- Don't make me change my workflow
- Data inertia is real
- ML best practices are still evolving

Closing the door on our public product lets us focus on our new goal of scaling HF Hub's storage backend to improve devX for a larger community. We'd love to hear your thoughts on what experiences we can improve!

Read the full post: https://xethub.com/blog/shutting-down-xethub-learnings-and-takeaways

models

None public yet

datasets

None public yet