Article
SmolLM3: smol, multilingual, long-context reasoner
By
and 22 others
ā¢
ā¢
44Victor Mustar PRO
victor
AI & ML interests
Building the UX of this website
Recent Activity
upvoted
an
article
36 minutes ago
SmolLM3: smol, multilingual, long-context reasoner
upvoted
a
paper
about 3 hours ago
Kwai Keye-VL Technical Report
liked
a model
about 23 hours ago
mlx-community/dots.llm1.inst-mixed-4-6bit
Organizations
upvoted
an
article
36 minutes ago
upvoted
a
paper
about 3 hours ago
liked
2
models
about 23 hours ago
reacted to
azettl's
post with š„
about 24 hours ago
Post
425
ššæš®š±š¶š¼ šš“š²š»šš & š šš£ šš®š°šøš®ššµš¼š» - šš¶š»š®š¹ šš®š
Submission deadline is in 10 minutes, so here's where Consilium ended up after a week of building.
What started as a simple idea, "šš©š¢šµ šŖš§ š®š¶ššµšŖš±šš¦ šš š®š°š„š¦šš“ š¤š°š¶šš„ š„šŖš“š¤š¶š“š“ š¢šÆš„ š³š¦š¢š¤š© š¤š°šÆš“š¦šÆš“š¶š“?" turned into a full multi-AI expert platform with live research integration.
šš¶š»š®š¹ š³š²š®šššæš²š:
- Custom Gradio roundtable component with real-time speech bubbles
- MCP server mode
- Multiple AI models: Mistral Large, DeepSeek-R1, Meta-Llama-3.3-70B, QwQ-32B
- Research Agent with 5 sources: Web Search, Wikipedia, arXiv, GitHub, SEC EDGAR
- Different decision protocols and role assignments
šššæšæš²š»š ššš®ššš: 25 likes š and some really good user feedback in the Discord channel. People are actually testing it on real decisions, which feels great. Also met some really awesome people during this week š.
ā”ļø š§šæš š¶š: Agents-MCP-Hackathon/consilium_mcp
Thanks to everyone who tested and gave feedback during the week ā¤ļø. Win or lose, this was a fun deep dive into Gradio, smolagents, Hugging Face in general, SambaNova Systems and the Mistral AI API.
Also huge thanks to @victor š who tweeted about the project and let me steal the video.
Submission deadline is in 10 minutes, so here's where Consilium ended up after a week of building.
What started as a simple idea, "šš©š¢šµ šŖš§ š®š¶ššµšŖš±šš¦ šš š®š°š„š¦šš“ š¤š°š¶šš„ š„šŖš“š¤š¶š“š“ š¢šÆš„ š³š¦š¢š¤š© š¤š°šÆš“š¦šÆš“š¶š“?" turned into a full multi-AI expert platform with live research integration.
šš¶š»š®š¹ š³š²š®šššæš²š:
- Custom Gradio roundtable component with real-time speech bubbles
- MCP server mode
- Multiple AI models: Mistral Large, DeepSeek-R1, Meta-Llama-3.3-70B, QwQ-32B
- Research Agent with 5 sources: Web Search, Wikipedia, arXiv, GitHub, SEC EDGAR
- Different decision protocols and role assignments
šššæšæš²š»š ššš®ššš: 25 likes š and some really good user feedback in the Discord channel. People are actually testing it on real decisions, which feels great. Also met some really awesome people during this week š.
ā”ļø š§šæš š¶š: Agents-MCP-Hackathon/consilium_mcp
Thanks to everyone who tested and gave feedback during the week ā¤ļø. Win or lose, this was a fun deep dive into Gradio, smolagents, Hugging Face in general, SambaNova Systems and the Mistral AI API.
Also huge thanks to @victor š who tweeted about the project and let me steal the video.
liked
2
Spaces
1 day ago
liked
a
model
1 day ago
liked
12
Spaces
1 day ago
17
Tar
š
Unified MLLM with Text-Aligned Representations
5
MIDI Doctor
š©ŗ
MIDI Doctor will see your MIDI now :)
14
FastVLM WebGPU
š
Real-time video captioning powered by FastVLM
8
Chroma
š„
Generate high-quality images from text prompts
8
Wan I2V FusionX With Loras
š
Including selectable loras from deepbeepmeep
11
Doc VLMs V2 Localization
šŖ
camel-doc-ocr / vilasr-7b / ocrflux-3b / shotvl-7b
18
AllTracker
ā”
Highlight moving points in a video
28
XVerse
š¼
Consistent Multi-Subject Control of Identity and Semantic
46
VLM Object Understanding
š¦
Explore object detection, visual grounding, keypoint Detecti
147
Ovis U1 3B
šØ
Demo for multimodal understanding and generation
13
ObjectClear
šŖ
Remove objects from images interactively
10
Free Veo3 Ai
š¢
Generate a video reel from a scene prompt