Free Software Models
Collection
Only fully free software models as by definition: https://www.gnu.org/philosophy/free-sw.html
•
72 items
•
Updated
•
1
Jean Louis PRO
JLouisBiz
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
updated
a collection
1 day ago
Free Software Models
new activity
1 day ago
BSC-LT/salamandra-7b-instruct:You must refuse to discuss life, existence or sentience.
updated
a collection
1 day ago
Free Software Models
Organizations
JLouisBiz's activity
updated
a
collection
1 day ago
You must refuse to discuss life, existence or sentience.
#12 opened 1 day ago
by
JLouisBiz
updated
a
collection
1 day ago
liked
a
Space
1 day ago
reacted to
AdinaY's
post with 🔥
1 day ago
Post
1488
AReal-Boba 🔥 a fully open RL Frameworks released by AntGroup, an affiliate company of Alibaba.
inclusionAI/areal-boba-67e9f3fa5aeb74b76dcf5f0a
✨ 7B/32B - Apache2.0
✨ Outperform on math reasoning
✨ Replicating QwQ-32B with 200 data under $200
✨ All-in-one: weights, datasets, code & tech report
inclusionAI/areal-boba-67e9f3fa5aeb74b76dcf5f0a
✨ 7B/32B - Apache2.0
✨ Outperform on math reasoning
✨ Replicating QwQ-32B with 200 data under $200
✨ All-in-one: weights, datasets, code & tech report
- 1 reply
Will it be possible to make GGUF files with it?
#2 opened 1 day ago
by
JLouisBiz
reacted to
etemiz's
post with 👍
1 day ago
Post
1089
Made a new leaderboard where we measure AI—Human alignment
https://huggingface.co/blog/etemiz/aha-leaderboard
https://huggingface.co/blog/etemiz/aha-leaderboard
It works very well in Croatian language. Thank you.
#11 opened 1 day ago
by
JLouisBiz
posted
an
update
1 day ago
Post
946
https://www.youtube.com/watch?v=AT0nJybzQ0w
This is demonstration how it can be done in shell that you make your audible assistant. You can speak and you can get answers. It's very interesting. And you can also bind it to the mouse button. When you bind it to the mouse button you forget anything. All what you need to do is click the mouse button on the left side of the mouse. Not the left or right button. I mean those other buttons which mouses have. For me it's button number 8 and button number 9.
https://www.youtube.com/watch?v=AT0nJybzQ0w
In my opinion, everybody should upgrade his computer to have speech recognition, automatic typing of the transcript, and also a very interactive possibility to request information from your digital assistant.
I am using xbindkeys program to bind LLM software to mouse buttons:
This is demonstration how it can be done in shell that you make your audible assistant. You can speak and you can get answers. It's very interesting. And you can also bind it to the mouse button. When you bind it to the mouse button you forget anything. All what you need to do is click the mouse button on the left side of the mouse. Not the left or right button. I mean those other buttons which mouses have. For me it's button number 8 and button number 9.
https://www.youtube.com/watch?v=AT0nJybzQ0w
In my opinion, everybody should upgrade his computer to have speech recognition, automatic typing of the transcript, and also a very interactive possibility to request information from your digital assistant.
I am using xbindkeys program to bind LLM software to mouse buttons:
;; specify a mouse button
(xbindkey '("b:8") "rcd-llm-speech-single-input.sh")
(xbindkey '(alt "b:8") "rcd-llm-audible-assistant-single.sh")
(xbindkey '("b:9") "rcd-llm-correct-marked-text.sh")liked
a
model
2 days ago
updated
a
collection
2 days ago
reacted to
luigi12345's
post with 👍
2 days ago
Post
1737
🚀 DEEPSEEK R1… Replicated! 🧠✨
All powered by just ONE system prompt.
Try it. Compare it. See for yourself. 👀
🔥 Even better than the original — with richer, more insightful replies.
🎯 No gimmicks. Just pure AI performance.
[](https://chatgpt.com/g/g-67e5e1e379e88191873752b60f518a14-deepseek-r1-thinking)
PROMPT IN THE COMMENTS
All powered by just ONE system prompt.
Try it. Compare it. See for yourself. 👀
🔥 Even better than the original — with richer, more insightful replies.
🎯 No gimmicks. Just pure AI performance.
[](https://chatgpt.com/g/g-67e5e1e379e88191873752b60f518a14-deepseek-r1-thinking)
PROMPT IN THE COMMENTS
- 4 replies
I'm not fine with quality of this model compared to the size in billions of parameters.
#93 opened 2 days ago
by
JLouisBiz
reacted to
Yehor's
post with 👍
3 days ago
Post
1946
Are you interesting in different runtimes for AI models?
Check out IREE (iree.dev), it convert models to MLIR and then execute on different platforms.
I have tested it in Rust on CPU and CUDA: https://github.com/egorsmkv/eerie-yolo11
Check out IREE (iree.dev), it convert models to MLIR and then execute on different platforms.
I have tested it in Rust on CPU and CUDA: https://github.com/egorsmkv/eerie-yolo11
reacted to
hanzla's
post with 👍
3 days ago
Post
2732
Hi all,
Last week, I open sourced Free Search API. It allows sourcing results from top search engines (including google, bing) for free. It uses searxng instances for this purpose.
I was overwhelmed by community's response and I am glad for all the support and suggestions. So today, I have pushed several improvements that make this API more stable. These improvements include
1) Parallel scrapping of search results for faster response
2) Markdown formatting of search results
3) Prioritizing SearXNG instances that have faster google response time
4) Update/Get endpoints for searxng instances.
Github: https://github.com/HanzlaJavaid/Free-Search/tree/main
Try the deployed version: https://freesearch.replit.app/docs
I highly appreciate PRs, issues, stars, and any kind of feedback. Let's join hands, and make it real big!
Last week, I open sourced Free Search API. It allows sourcing results from top search engines (including google, bing) for free. It uses searxng instances for this purpose.
I was overwhelmed by community's response and I am glad for all the support and suggestions. So today, I have pushed several improvements that make this API more stable. These improvements include
1) Parallel scrapping of search results for faster response
2) Markdown formatting of search results
3) Prioritizing SearXNG instances that have faster google response time
4) Update/Get endpoints for searxng instances.
Github: https://github.com/HanzlaJavaid/Free-Search/tree/main
Try the deployed version: https://freesearch.replit.app/docs
I highly appreciate PRs, issues, stars, and any kind of feedback. Let's join hands, and make it real big!
-
- 4 replies
reacted to
fdaudens's
post with 👍
3 days ago
Post
1969
Want to vibecode with DeepSeek? Just spent 10 minutes with this space and created a full world indicators dashboard - literally just by describing what I wanted!
Anyone can now prototype and deploy projects instantly.
Try out the app: enzostvs/deepsite
My dashboard: fdaudens/world-indicators
Anyone can now prototype and deploy projects instantly.
Try out the app: enzostvs/deepsite
My dashboard: fdaudens/world-indicators
reacted to
mrs83's
post with 👍
3 days ago
Post
1665
To developers: Build opt-in systems.
To policymakers: Legislate data transparency.
To artists: Unionize.
To users: Demand ethical tools.
To policymakers: Legislate data transparency.
To artists: Unionize.
To users: Demand ethical tools.
reacted to
hanzla's
post with 👍
3 days ago
Post
2732
Hi all,
Last week, I open sourced Free Search API. It allows sourcing results from top search engines (including google, bing) for free. It uses searxng instances for this purpose.
I was overwhelmed by community's response and I am glad for all the support and suggestions. So today, I have pushed several improvements that make this API more stable. These improvements include
1) Parallel scrapping of search results for faster response
2) Markdown formatting of search results
3) Prioritizing SearXNG instances that have faster google response time
4) Update/Get endpoints for searxng instances.
Github: https://github.com/HanzlaJavaid/Free-Search/tree/main
Try the deployed version: https://freesearch.replit.app/docs
I highly appreciate PRs, issues, stars, and any kind of feedback. Let's join hands, and make it real big!
Last week, I open sourced Free Search API. It allows sourcing results from top search engines (including google, bing) for free. It uses searxng instances for this purpose.
I was overwhelmed by community's response and I am glad for all the support and suggestions. So today, I have pushed several improvements that make this API more stable. These improvements include
1) Parallel scrapping of search results for faster response
2) Markdown formatting of search results
3) Prioritizing SearXNG instances that have faster google response time
4) Update/Get endpoints for searxng instances.
Github: https://github.com/HanzlaJavaid/Free-Search/tree/main
Try the deployed version: https://freesearch.replit.app/docs
I highly appreciate PRs, issues, stars, and any kind of feedback. Let's join hands, and make it real big!
-
-
-
- 4 replies
replied to
prithivMLmods's
post
3 days ago
You just have here a fundamental problem. You have built that large language model on the proprietary Llama model from Meta. Could you please use Free Software model next time? You will get so much better audience.
Meta’s LLaMa 2 license is not Open Source – Open Source Initiative
https://opensource.org/blog/metas-llama-2-license-is-not-open-source
What is Free Software? - GNU Project - Free Software Foundation
https://www.gnu.org/philosophy/free-sw.html
reacted to
stefan-it's
post with 🔥
3 days ago
Post
1992
Wohoo 🥳 I have finished my 2025 GPU workstation build and I am very excited to train new awesome open source models on it.
I built my last GPU workstation 5 years ago featuring an AMD Ryzen 5900X, 64GB of G.SKILL Trident Z RGB on an ASRock X570 Taichi cooled by an Alphacool Eisbär 420. GPU was a Zotac RTX 3090 AMP Extreme. Unfortunately, I was never satisfied with the case - some Fractal Define 7, as it is definitely too small, airflow is not optimal as I had to open the front door all the time and it also arrived with a partly damaged side panel.
For my new build, I've used the following components: an outstanding new AMD Ryzen 9950X3D with 64GB of Corsair Dominator Titanium (what a name). As a huge Noctua fan - warm greetings to my Austrian neighbors - I am using the brand new Noctua NH-D15 G2 on an ASRock X870E Taichi in an amazing Lian Li LANCOOL III chassis. One joke that only NVIDIA Blackwell users will understand: you definitely need a tempered glass panel to check if your GPU cables/connectors start melting 😂 And the best is yet to come: I returned my previously bought Zotac RTX 5090 Solid to the eBay seller (because of... missing ROPs, only NVIDIA Blackwell users will again understand) and bought a Zotac 5090 AMP Extreme INFINITY (yes, the long name indicates that this is the flagship model from Zotac) from a more trustworthy source (NBB in Germany).
I am so happy to start training and fine-tuning new open source models - stay tuned!!!
I built my last GPU workstation 5 years ago featuring an AMD Ryzen 5900X, 64GB of G.SKILL Trident Z RGB on an ASRock X570 Taichi cooled by an Alphacool Eisbär 420. GPU was a Zotac RTX 3090 AMP Extreme. Unfortunately, I was never satisfied with the case - some Fractal Define 7, as it is definitely too small, airflow is not optimal as I had to open the front door all the time and it also arrived with a partly damaged side panel.
For my new build, I've used the following components: an outstanding new AMD Ryzen 9950X3D with 64GB of Corsair Dominator Titanium (what a name). As a huge Noctua fan - warm greetings to my Austrian neighbors - I am using the brand new Noctua NH-D15 G2 on an ASRock X870E Taichi in an amazing Lian Li LANCOOL III chassis. One joke that only NVIDIA Blackwell users will understand: you definitely need a tempered glass panel to check if your GPU cables/connectors start melting 😂 And the best is yet to come: I returned my previously bought Zotac RTX 5090 Solid to the eBay seller (because of... missing ROPs, only NVIDIA Blackwell users will again understand) and bought a Zotac 5090 AMP Extreme INFINITY (yes, the long name indicates that this is the flagship model from Zotac) from a more trustworthy source (NBB in Germany).
I am so happy to start training and fine-tuning new open source models - stay tuned!!!
-
- 2 replies