Jean Louis PRO

JLouisBiz

https://www.StartYourOwnGoldMine.com

AI & ML interests

- LLM for sales, marketing, promotion - LLM for Website Revision System - increasing quality of communication with customers - helping clients access information faster - saving people from financial troubles

Recent Activity

reacted to fdaudens's post with 🧠 about 3 hours ago

🎨 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. https://huggingface.co/OmniSVG

reacted to fdaudens's post with 😎 about 3 hours ago

Do chatbots lie about Céline Dion? We now have answers, not speculation. Ai2 just released OLMoTrace and it's a game-changer for transparency. You can literally see where an AI's responses come from in its training data - in real time. The demo shows results about Céline. So I tried it out myself! Watch what happens in the video. For journalists, researchers studying hallucinations and anyone who needs to trust their AI, this is like getting X-ray vision into AI systems. When the model made claims, I could instantly verify them against original sources. When it hallucinated, I could see why. You can finally 1) understand how LLMs actually work and 2) verify if what they're saying is true. No more blind trust. This pushes the open data movement to the next level. 👉 Blog post: https://allenai.org/blog/olmotrace 👉 Paper: https://www.datocms-assets.com/64837/1743890415-olmotrace.pdf P.S.: A word of caution: never use a chatbot as a knowledge base. It's not Google. Better use it with a connection to the internet.

posted an update about 3 hours ago

https://www.youtube.com/watch?v=84iS3atFQdI **Speech typing in Emacs** by using NVIDIA Canary 1B model in multiple languages This video showcases a demonstration of speech-to-text capabilities within the popular text editor, Emacs, utilizing the advanced NVIDIA Canary 1 Billion parameter (1B) language model. The presentation highlights how users can effectively type and edit documents across various programming or markup languages using spoken commands. The demo likely illustrates seamless integration between cutting-edge AI technology from NVIDIA's Canary series—known for its powerful natural language processing capabilities—and Emacs, a highly customizable text editor favored by developers worldwide. By leveraging the 1B model, which is capable of understanding context and nuances in multiple human languages, users can dictate their code or prose directly into Emacs with impressive accuracy. The video probably covers how this setup supports several different programming languages as well as natural language typing tasks, showcasing its versatility across various domains such as software development and content creation. Additionally, the demonstration may include examples of real-time transcription performance in diverse linguistic contexts to emphasize the model's multilingual proficiency. Overall, viewers can expect insights into enhancing productivity by integrating AI-driven speech recognition directly within their text editing workflow using Emacs paired with NVIDIA’s advanced language models.

View all activity

Organizations

JLouisBiz's activity

reacted to fdaudens's post with 🧠 about 3 hours ago

Post

1906

2 replies

reacted to fdaudens's post with 😎 about 3 hours ago

Post

282

Do chatbots lie about Céline Dion? We now have answers, not speculation.

Ai2 just released OLMoTrace and it's a game-changer for transparency. You can literally see where an AI's responses come from in its training data - in real time.

The demo shows results about Céline. So I tried it out myself! Watch what happens in the video.

For journalists, researchers studying hallucinations and anyone who needs to trust their AI, this is like getting X-ray vision into AI systems. When the model made claims, I could instantly verify them against original sources. When it hallucinated, I could see why.

You can finally 1) understand how LLMs actually work and 2) verify if what they're saying is true. No more blind trust.

This pushes the open data movement to the next level.

👉 Blog post: https://allenai.org/blog/olmotrace
👉 Paper: https://www.datocms-assets.com/64837/1743890415-olmotrace.pdf

P.S.: A word of caution: never use a chatbot as a knowledge base. It's not Google. Better use it with a connection to the internet.

posted an update about 3 hours ago

Post

103

https://www.youtube.com/watch?v=84iS3atFQdI

**Speech typing in Emacs** by using NVIDIA Canary 1B model in multiple languages

This video showcases a demonstration of speech-to-text capabilities within the popular text editor, Emacs, utilizing the advanced NVIDIA Canary 1 Billion parameter (1B) language model. The presentation highlights how users can effectively type and edit documents across various programming or markup languages using spoken commands.

The demo likely illustrates seamless integration between cutting-edge AI technology from NVIDIA's Canary series—known for its powerful natural language processing capabilities—and Emacs, a highly customizable text editor favored by developers worldwide. By leveraging the 1B model, which is capable of understanding context and nuances in multiple human languages, users can dictate their code or prose directly into Emacs with impressive accuracy.

The video probably covers how this setup supports several different programming languages as well as natural language typing tasks, showcasing its versatility across various domains such as software development and content creation. Additionally, the demonstration may include examples of real-time transcription performance in diverse linguistic contexts to emphasize the model's multilingual proficiency.

Overall, viewers can expect insights into enhancing productivity by integrating AI-driven speech recognition directly within their text editing workflow using Emacs paired with NVIDIA’s advanced language models.

New activity in FreedomIntelligence/Apollo2-9B about 3 hours ago

This model IS NOT Apache 2.0 as you derived it from Gemma, which is proprietary model

#2 opened 1 day ago by

JLouisBiz

updated a collection about 4 hours ago

Free Software Models

Collection

Only fully free software models as by definition: https://www.gnu.org/philosophy/free-sw.html • 82 items • Updated about 4 hours ago • 1

liked a model about 4 hours ago

l3lab/L1-Qwen-1.5B-Max

Updated Mar 7 • 26.5k • 13

updated a collection about 4 hours ago

Free Software Models

Collection

Only fully free software models as by definition: https://www.gnu.org/philosophy/free-sw.html • 82 items • Updated about 4 hours ago • 1

New activity in moonshotai/Moonlight-16B-A3B-Instruct about 5 hours ago

Which custom code this model wants to run? Could you please explain me? I was using Llama.cpp.

#12 opened about 5 hours ago by

JLouisBiz

updated a collection about 6 hours ago

Free Software Models

Collection

Only fully free software models as by definition: https://www.gnu.org/philosophy/free-sw.html • 82 items • Updated about 4 hours ago • 1

updated a collection about 11 hours ago

Free Software Models

Collection

Only fully free software models as by definition: https://www.gnu.org/philosophy/free-sw.html • 82 items • Updated about 4 hours ago • 1

replied to ZennyKenny's post about 13 hours ago

I don't see why such are better. They consume more power, delay with the actual answer, they are twice as bad for local LLM users. I will test it again, but what I tested so far doesn't seem there is special benefit in my use cases.

What is your practical use cases and reason, why do you like reasoning models?

updated a collection about 19 hours ago