Simon Pagezy's picture

Simon Pagezy

pagezyhf

AI & ML interests

Healthcare ML

Recent Activity

Organizations

Hugging Face's profile picture AWS Inferentia and Trainium's profile picture Hugging Face Optimum's profile picture Hugging Test Lab's profile picture Hugging Face OSS Metrics's profile picture Core ML Projects's profile picture Blog-explorers's profile picture Amazon SageMaker's profile picture Enterprise Explorers's profile picture Paris AI Running Club's profile picture Google Cloud ๐Ÿค๐Ÿป Hugging Face's profile picture PagezyTest's profile picture

pagezyhf's activity

posted an update 2 days ago
view post
Post
1820
If you haven't had the chance to test the latest open model from Meta, Llama 4 Maverick, go try it on AMD MI 300 on Hugging Face!

amd/llama4-maverick-17b-128e-mi-amd
upvoted an article 6 days ago
view article
Article

Cohere on Hugging Face Inference Providers ๐Ÿ”ฅ

โ€ข 117
reacted to fdaudens's post with ๐Ÿคฏโž• 14 days ago
view post
Post
4079
๐ŸŽจ Designers, meet OmniSVG! This new model helps you create professional vector graphics from text/images, generate editable SVGs from icons to detailed characters, convert rasters to vectors, maintain style consistency with references, and integrate into your workflow.

@OmniSVG
  • 2 replies
ยท
reacted to as-cle-bert's post with ๐Ÿ”ฅ 17 days ago
view post
Post
2918
Llama-4 is out and I couldn't resist but to cook something with it... So I came up with ๐‹๐ฅ๐š๐ฆ๐š๐‘๐ž๐ฌ๐ž๐š๐ซ๐œ๐ก๐ž๐ซ (https://llamaresearcher.com), your deep-research AI companion!๐Ÿ”Ž

The workflow behind ๐—Ÿ๐—น๐—ฎ๐—บ๐—ฎ๐—ฅ๐—ฒ๐˜€๐—ฒ๐—ฎ๐—ฟ๐—ฐ๐—ต๐—ฒ๐—ฟ is simple:
๐Ÿ’ฌ You submit a query
๐Ÿ›ก๏ธ Your query is evaluated by Llama 3 guard model, which deems it safe or unsafe
๐Ÿง  If your query is safe, it is routed to the Researcher Agent
โš™๏ธ The Researcher Agent expands the query into three sub-queries, with which to search the web
๐ŸŒ The web is searched for each of the sub-queries
๐Ÿ“Š The retrieved information is evaluated for relevancy against your original query
โœ๏ธ The Researcher Agent produces an essay based on the information it gathered, paying attention to referencing its sources

The agent itself is also built with easy-to-use and intuitive blocks:
๐Ÿฆ™ LlamaIndex provides the agentic architecture and the integrations with the language models
โšกGroq makes Llama-4 available with its lightning-fast inference
๐Ÿ”Ž Linkup allows the agent to deep-search the web and provides sourced answers
๐Ÿ’ช FastAPI does the heavy loading with wrapping everything within an elegant API interface
โฑ๏ธ Redis is used for API rate limiting
๐ŸŽจ Gradio creates a simple but powerful user interface

Special mention also to Lovable, which helped me build the first draft of the landing page for LlamaResearcher!๐Ÿ’–

If you're curious and you want to try LlamaResearcher, you can - completely for free and without subscription - for 30 days from now โžก๏ธ https://llamaresearcher.com
And if you're like me, and you like getting your hands in code and build stuff on your own machine, I have good news: this is all open-source, fully reproducible locally and Docker-ready๐Ÿ‹
Just go to the GitHub repo: https://github.com/AstraBert/llama-4-researcher and don't forget to star it, if you find it useful!โญ

As always, have fun and feel free to leave your feedbackโœจ
  • 2 replies
ยท
upvoted an article 23 days ago
view article
Article

CPU Optimized Embeddings with ๐Ÿค— Optimum Intel and fastRAG

โ€ข 10