136 667 565

Adam Molnar

lunarflu

AI & ML interests

join the Hugging Face discord! hf.co/discord/join

Recent Activity

Reacted to AdinaY's post with 🤗 about 8 hours ago

Zhipu AI, the Chinese generative AI startup behind CogVideo, just launched their first productized AI Agent - AutoGLM 🔥 👉 https://agent.aminer.cn With simple text or voice commands, it: ✨ Simulates phone operations effortlessly ✨ Autonomously handles 50+ step tasks ✨ Seamlessly operates across apps Powered by Zhipu's "Decoupled Interface" and "Self-Evolving Learning Framework" to achieve major performance gains in Phone Use and Web Browser Use! Meanwhile, GLM4-Edge is now on Hugging Face hub🚀 👉 https://huggingface.co/collections/THUDM/glm-edge-6743283c5809de4a7b9e0b8b Packed with advanced dialogue + multimodal models: 📱 1.5B / 2B models: Built for mobile & in-car systems 💻 4B / 5B models: Optimized for PCs

replied to m-ric's post about 8 hours ago

Single most important thing to do today: 𝗴𝗼 𝘁𝗿𝘆 𝗤𝘄𝗤 𝗼𝗻 𝗛𝘂𝗴𝗴𝗶𝗻𝗴 𝗖𝗵𝗮𝘁! 👉 https://huggingface.co/chat/models/Qwen/QwQ-32B-Preview

Reacted to m-ric's post with ❤️ about 8 hours ago

Single most important thing to do today: 𝗴𝗼 𝘁𝗿𝘆 𝗤𝘄𝗤 𝗼𝗻 𝗛𝘂𝗴𝗴𝗶𝗻𝗴 𝗖𝗵𝗮𝘁! 👉 https://huggingface.co/chat/models/Qwen/QwQ-32B-Preview

View all activity

Organizations

lunarflu's activity

Reacted to AdinaY's post with 🤗 about 8 hours ago

Post

769

Zhipu AI, the Chinese generative AI startup behind CogVideo, just launched their first productized AI Agent - AutoGLM 🔥
👉 https://agent.aminer.cn

With simple text or voice commands, it:
✨ Simulates phone operations effortlessly
✨ Autonomously handles 50+ step tasks
✨ Seamlessly operates across apps

Powered by Zhipu's "Decoupled Interface" and "Self-Evolving Learning Framework" to achieve major performance gains in Phone Use and Web Browser Use!

Meanwhile, GLM4-Edge is now on Hugging Face hub🚀
👉 THUDM/glm-edge-6743283c5809de4a7b9e0b8b
Packed with advanced dialogue + multimodal models:
📱 1.5B / 2B models: Built for mobile & in-car systems
💻 4B / 5B models: Optimized for PCs

replied to m-ric's post about 8 hours ago

waiting for owo/uwu (new peak of models)

Reacted to m-ric's post with ❤️ about 8 hours ago

Post

864

Single most important thing to do today: 𝗴𝗼 𝘁𝗿𝘆 𝗤𝘄𝗤 𝗼𝗻 𝗛𝘂𝗴𝗴𝗶𝗻𝗴 𝗖𝗵𝗮𝘁!

👉 https://huggingface.co/chat/models/Qwen/QwQ-32B-Preview

2 replies

Reacted to julien-c's post with 🤗🔥 about 8 hours ago

Post

447

wow 😮

INTELLECT-1 is the first collaboratively trained 10 billion parameter language model trained from scratch on 1 trillion tokens of English text and code.

PrimeIntellect/INTELLECT-1-Instruct

Reacted to burtenshaw's post with 👍 about 9 hours ago

Post

363

[SATURDAY ROUNDUP] ☕️🧑‍🎓

In case you missed everything this week. It’s all about vision language models and image preference datasets. Here are the models and datasets you can use in your projects.

QWQ-32B-Preview is the first open weights model to reason like o1 with comparable performance. It’s large but is acing some of the hardest tasks.

https://bsky.app/profile/philschmid.bsky.social/post/3lbylz6nzqk25

SmolVLM is a vision implementation of the recently released SmolLM2. It uses the Idefics3 approach to add a vision encoder. The main difference being the smaller language model (8b > 1.7b) and more compression of images. This results in a model that is very accurate for its memory footprint.

https://huggingface.co/blog/smolvlm

ColSmolVLM is a vision embedding model based on SmolVLM using the Colbert approach from ColPali. This is shown to be great at document retrieval and everyone should test it out in their RAG setups.

https://huggingface.co/posts/merve/663466156074132

In an effort to build a FLUX level open source image generation model, the community is building a dataset of image preferences. The dataset is already open and the project is still running. Join in!

https://huggingface.co/posts/davidberenstein1957/405018978675827

TRL tutorial Drop - This week I dropped a load of tutorials on finetuning and aligning models with TRL. If you’re upskilling in this space, you should check these out.

https://bsky.app/profile/benburtenshaw.bsky.social/post/3lbrc56ap3222

Reacted to DawnC's post with 👍 about 9 hours ago

Post

433

💡 Curious about dog breeds? 🐕 Try PawMatchAI!
It’s a fun project I built to recognize dog breeds, recommend the perfect match for your lifestyle, and even compare breeds! 🐾

🔎 While it’s not perfect, I’d love for you to give it a try and share your feedback!

👉 check it out here !
DawnC/PawMatchAI

Your support means a lot as I continue learning and growing in my journey toward a career in AI. 🙌

Like it? Don’t forget to click that thumbs up! 👍

Reacted to abhishek's post with 🤗 about 9 hours ago

Post

357

🎉 SUPER BLACK FRIDAY DEAL 🎉

Train almost any model on a variety of tasks such as llm finetuning, text classification/regression, summarization, question answering, image classification/regression, object detection, tabular data, etc for FREE using AutoTrain locally. 🔥
https://github.com/huggingface/autotrain-advanced

Reacted to KnutJaegersberg's post with 👀 about 9 hours ago

Post

367

DrNicefellow/Qwen-QwQ-32B-Preview-4.25bpw-exl2

Rumor has it this is currently the best model for 24 GB VRAM local usage.

DrNicefellow/Qwen-QwQ-32B-Preview-4.25bpw-exl2

Reacted to sequelbox's post with 👍 12 days ago

Post

1162

next version of sequelbox/Celestia will be microsoft/orca-agentinstruct-1M-v1 style. coming soon

1 reply

Reacted to reach-vb's post with 🚀🤗👍🔥 12 days ago

Post

4166

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
Qwen/qwen25-coder-66eaa22e6f99801bf65b0c2f

LLM2CLIP from Microsoft - Leverage LLMs to train ultra-powerful CLIP models! Boosts performance over the previous SOTA by ~17%
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
Nexusflow/athene-v2-6735b85e505981a794fb02cc

Orca Agent Instruct by Microsoft - 1 million instruct pairs covering text editing, creative writing, coding, reading comprehension, etc - permissively licensed
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
reach-vb/ultravox-audio-language-model-release-67373b602af0a52b2a88ae71

JanusFlow 1.3 by DeepSeek - Next iteration of their Unified MultiModal LLM Janus with RectifiedFlow
deepseek-ai/JanusFlow-1.3B

Common Corpus by Pleais - 2,003,039,184,047 multilingual, commercially permissive and high quality tokens!
PleIAs/common_corpus

I'm sure I missed a lot, can't wait for the next week!

Put down in comments what I missed! 🤗

Reacted to TuringsSolutions's post with 👀 12 days ago

Post

735

If I am correct and the LLM model changes the 'shape' of the data as it learns, then I should be able to track and utilize those shape changes as a backpropagation training mechanism, right? Well guess what, I can do that! Entropy, Sparsity, and Density, this is how I can measure the shape of the data the LLM model is creating. Nodes, Clusters, and Edges, these are the mechanisms within the neural network the LLM model updates as it learns these concepts. I measure the effects of these updates, via Entropy, Sparsity, and Density. Check out more in this video: https://youtu.be/jADTt5HHtiw

2 replies

Reacted to erikkaum's post with 👀🔥 12 days ago

Post

1675

A while ago I started experimenting with compiling the Python interpreter to WASM.

To build a secure, fast, and lightweight sandbox for code execution — ideal for running LLM-generated Python code.

- Send code simply as a POST request
- 1-2ms startup times

Hack away:
https://github.com/ErikKaum/runner

Reacted to AdinaY's post with 👀 12 days ago

Post

1449

LLaMA Mesh 🔥 Unifying 3D Mesh Generation with Language Models

Model: Zhengyi/LLaMA-Mesh
Demo: Zhengyi/LLaMA-Mesh
Paper: LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models (2411.09595)

✨ Unified 3D generation & text understanding.
✨ 3D meshes as plain text for seamless LLM integration.
✨ High-quality 3D outputs rivaling specialized models.

Reacted to sayakpaul's post with 🚀❤️ 12 days ago

Post

2409

It's been a while we shipped native quantization support in diffusers 🧨

We currently support bistandbytes as the official backend but using others like torchao is already very simple.

This post is just a reminder of what's possible:

1. Loading a model with a quantization config
2. Saving a model with quantization config
3. Loading a pre-quantized model
4. enable_model_cpu_offload()
5. Training and loading LoRAs into quantized checkpoints

Docs:
https://huggingface.co/docs/diffusers/main/en/quantization/bitsandbytes

1 reply