deepseek-ai/DeepSeek-R1
Updated
โข
874
alkinun
AtAndDev
AI & ML interests
LLMs, Alignment, Merging, Unsloth, DPO, SFT, ORPO, SPIN..
Recent Activity
liked
a model
about 16 hours ago
deepseek-ai/DeepSeek-R1
posted
an
update
about 16 hours ago
R1 is out! And with a lot of other R1 releated models...
Organizations
AtAndDev's activity
liked
a
model
about 16 hours ago
posted
an
update
about 16 hours ago
Post
502
R1 is out! And with a lot of other R1 releated models...
Duh its pretraining
upvoted
a
collection
2 days ago
reacted to
florentgbelidji's
post with ๐ฅ
2 days ago
Post
1201
๐ฃ๐น๐ฎ๐ป๐ป๐ถ๐ป๐ด ๐ฌ๐ผ๐๐ฟ ๐ก๐ฒ๐
๐ ๐ฆ๐ธ๐ถ ๐๐ฑ๐๐ฒ๐ป๐๐๐ฟ๐ฒ ๐๐๐๐ ๐๐ผ๐ ๐ฆ๐บ๐ฎ๐ฟ๐๐ฒ๐ฟ: ๐๐ป๐๐ฟ๐ผ๐ฑ๐๐ฐ๐ถ๐ป๐ด ๐๐น๐ฝ๐ถ๐ป๐ฒ ๐๐ด๐ฒ๐ป๐!๐๏ธโท๏ธ
With the big hype around AI agents these days, I couldnโt stop thinking about how AI agents could truly enhance real-world activities.
What sort of applications could we build with those AI agents: agentic RAG? self-correcting text-to-sql? Nah, boringโฆ
Passionate about outdoors, Iโve always dreamed of a tool that could simplify planning mountain trips while accounting for all potential risks. Thatโs why I built ๐๐น๐ฝ๐ถ๐ป๐ฒ ๐๐ด๐ฒ๐ป๐, a smart assistant designed to help you plan safe and enjoyable itineraries in the French Alps and Pyrenees.
Built using Hugging Face's ๐๐บ๐ผ๐น๐ฎ๐ด๐ฒ๐ป๐๐ library, Alpine Agent combines the power of AI with trusted resources like ๐๐ฌ๐ช๐ต๐ฐ๐ถ๐ณ.๐ง๐ณ (https://skitour.fr/) and METEO FRANCE. Whether itโs suggesting a route with moderate difficulty or analyzing avalanche risks and weather conditions, this agent dynamically integrates data to deliver personalized recommendations.
In my latest blog post, I share how I developed this projectโfrom defining tools and integrating APIs to selecting the best LLMs like ๐๐ธ๐ฆ๐ฏ2.5-๐๐ฐ๐ฅ๐ฆ๐ณ-32๐-๐๐ฏ๐ด๐ต๐ณ๐ถ๐ค๐ต, ๐๐ญ๐ข๐ฎ๐ข-3.3-70๐-๐๐ฏ๐ด๐ต๐ณ๐ถ๐ค๐ต, or ๐๐๐-4.
โท๏ธ Curious how AI can enhance adventure planning?โจTry the app and share your thoughts: florentgbelidji/alpine-agent
๐ Want to build your own agents? Whether for cooking, sports training, or other passions, the possibilities are endless. Check out the blog post to learn more: https://huggingface.co/blog/florentgbelidji/alpine-agent
Many thanks to @m-ric for helping on building this tool with smolagents!
With the big hype around AI agents these days, I couldnโt stop thinking about how AI agents could truly enhance real-world activities.
What sort of applications could we build with those AI agents: agentic RAG? self-correcting text-to-sql? Nah, boringโฆ
Passionate about outdoors, Iโve always dreamed of a tool that could simplify planning mountain trips while accounting for all potential risks. Thatโs why I built ๐๐น๐ฝ๐ถ๐ป๐ฒ ๐๐ด๐ฒ๐ป๐, a smart assistant designed to help you plan safe and enjoyable itineraries in the French Alps and Pyrenees.
Built using Hugging Face's ๐๐บ๐ผ๐น๐ฎ๐ด๐ฒ๐ป๐๐ library, Alpine Agent combines the power of AI with trusted resources like ๐๐ฌ๐ช๐ต๐ฐ๐ถ๐ณ.๐ง๐ณ (https://skitour.fr/) and METEO FRANCE. Whether itโs suggesting a route with moderate difficulty or analyzing avalanche risks and weather conditions, this agent dynamically integrates data to deliver personalized recommendations.
In my latest blog post, I share how I developed this projectโfrom defining tools and integrating APIs to selecting the best LLMs like ๐๐ธ๐ฆ๐ฏ2.5-๐๐ฐ๐ฅ๐ฆ๐ณ-32๐-๐๐ฏ๐ด๐ต๐ณ๐ถ๐ค๐ต, ๐๐ญ๐ข๐ฎ๐ข-3.3-70๐-๐๐ฏ๐ด๐ต๐ณ๐ถ๐ค๐ต, or ๐๐๐-4.
โท๏ธ Curious how AI can enhance adventure planning?โจTry the app and share your thoughts: florentgbelidji/alpine-agent
๐ Want to build your own agents? Whether for cooking, sports training, or other passions, the possibilities are endless. Check out the blog post to learn more: https://huggingface.co/blog/florentgbelidji/alpine-agent
Many thanks to @m-ric for helping on building this tool with smolagents!
- 1 reply
reacted to
aiqcamp's
post with ๐ฅ
2 days ago
Post
2824
# ๐จ FLUX Diagram Generator - Create Hand-Drawn Style Diagrams
aiqcamp/diagram
Generate beautiful mind maps and diagrams with AI! Using the FLUX.1-schnell model, create natural hand-drawn style diagrams that bring your ideas to life.
## โจ Key Features
- ๐ก Intuitive prompt-based input system
- ๐ฏ Rich examples including knowledge trees, digital transformation, creative process, and more
- ๐ Customizable settings for image size, seed values, and more
- ๐ผ Support for resolutions up to 2048x2048
- โก Fast generation (4 steps default)
## ๐ฏ Use Cases
- Educational materials
- Project planning
- Idea structuring
- Presentation visuals
- Business process visualization
Built with Gradio for a user-friendly interface that anyone can use. Start creating your own diagrams now! ๐
Try it out to transform your ideas into visually appealing diagrams with a unique hand-drawn aesthetic.
#AIart #Diagram #Mindmap #Visualization #HuggingFace
aiqcamp/diagram
Generate beautiful mind maps and diagrams with AI! Using the FLUX.1-schnell model, create natural hand-drawn style diagrams that bring your ideas to life.
## โจ Key Features
- ๐ก Intuitive prompt-based input system
- ๐ฏ Rich examples including knowledge trees, digital transformation, creative process, and more
- ๐ Customizable settings for image size, seed values, and more
- ๐ผ Support for resolutions up to 2048x2048
- โก Fast generation (4 steps default)
## ๐ฏ Use Cases
- Educational materials
- Project planning
- Idea structuring
- Presentation visuals
- Business process visualization
Built with Gradio for a user-friendly interface that anyone can use. Start creating your own diagrams now! ๐
Try it out to transform your ideas into visually appealing diagrams with a unique hand-drawn aesthetic.
#AIart #Diagram #Mindmap #Visualization #HuggingFace
- 1 reply
reacted to
cutechicken's
post with ๐ฅ
2 days ago
Post
2700
๐ฌ PaperImpact
: Scientific Impact Predictor Powered by Deep Learning ๐ฏ
VIDraft/PaperImpact
๐ Overview
A cutting-edge AI system that combines transformer architecture with citation pattern analysis to predict research impact. Our model, trained on 120,000+ CS papers, analyzes innovation potential, methodological robustness, and future impact, providing researchers with valuable insights before publication.
๐ง Scientific Foundation
BERT-based semantic analysis
Citation network pattern learning
NDCG optimization & MSE loss
Cross-validated prediction engine
GPU-accelerated inference
๐ซ Why Researchers Need This
Pre-submission impact assessment
Research direction optimization
Time-saving paper evaluation
Competitive edge in academia
Trend identification advantage
๐ฏ Key Features
One-click arXiv paper analysis
Real-time impact scoring (0-1)
9-tier grading system (AAA-C)
Smart input validation
Instant visual feedback
๐ Unique Benefits
"Don't wait years to know your paper's impact. Get instant, AI-powered insights to strengthen your research strategy and maximize your academic influence."
Perfect for:
Research authors
PhD students
Journal editors
Research institutions
Grant committees
#ResearchImpact #AcademicAI #ScienceMetrics #ResearchExcellence
: Scientific Impact Predictor Powered by Deep Learning ๐ฏ
VIDraft/PaperImpact
๐ Overview
A cutting-edge AI system that combines transformer architecture with citation pattern analysis to predict research impact. Our model, trained on 120,000+ CS papers, analyzes innovation potential, methodological robustness, and future impact, providing researchers with valuable insights before publication.
๐ง Scientific Foundation
BERT-based semantic analysis
Citation network pattern learning
NDCG optimization & MSE loss
Cross-validated prediction engine
GPU-accelerated inference
๐ซ Why Researchers Need This
Pre-submission impact assessment
Research direction optimization
Time-saving paper evaluation
Competitive edge in academia
Trend identification advantage
๐ฏ Key Features
One-click arXiv paper analysis
Real-time impact scoring (0-1)
9-tier grading system (AAA-C)
Smart input validation
Instant visual feedback
๐ Unique Benefits
"Don't wait years to know your paper's impact. Get instant, AI-powered insights to strengthen your research strategy and maximize your academic influence."
Perfect for:
Research authors
PhD students
Journal editors
Research institutions
Grant committees
#ResearchImpact #AcademicAI #ScienceMetrics #ResearchExcellence
- 1 reply
reacted to
MonsterMMORPG's
post with ๐ฅ
2 days ago
Post
1165
Most Powerful Vision Model CogVLM 2 now works amazing on Windows with new Triton pre-compiled wheels - 19 Examples - Locally tested with 4-bit quantization - Second example is really wild - Can be used for image captioning or any image vision task
The APP and the installers : https://www.patreon.com/posts/120193330
Check below screenshots to see how to use it
Currently the APP works amazing with 4-bit quantization very fast
I am searching to lower VRAM usage even further with like adding CPU-Offloading and other stuff if possible
Previously we were lacking Triton but it now works perfect
My installer installs into a Python 3.10 VENV completely isolated and clean
You can see entire APP and installer source code
If you get Triton error make sure to delete your Triton cache after installing the app like below
C:\Users\Furkan.triton
Hugging Face repo with sample code : THUDM/cogvlm2-llama3-chat-19B
GitHub repo : https://github.com/THUDM/CogVLM2
Triton Windows : https://github.com/woct0rdho/triton-windows/releases
The APP and the installers : https://www.patreon.com/posts/120193330
Check below screenshots to see how to use it
Currently the APP works amazing with 4-bit quantization very fast
I am searching to lower VRAM usage even further with like adding CPU-Offloading and other stuff if possible
Previously we were lacking Triton but it now works perfect
My installer installs into a Python 3.10 VENV completely isolated and clean
You can see entire APP and installer source code
If you get Triton error make sure to delete your Triton cache after installing the app like below
C:\Users\Furkan.triton
Hugging Face repo with sample code : THUDM/cogvlm2-llama3-chat-19B
GitHub repo : https://github.com/THUDM/CogVLM2
Triton Windows : https://github.com/woct0rdho/triton-windows/releases
upvoted
an
article
2 days ago
Article
Welcome Gemma 2 - Google's new open LLM
โข
125
upvoted
a
paper
3 days ago
liked
a
model
3 days ago
upvoted
a
collection
3 days ago
upvoted
a
paper
3 days ago
commented on
Gradio spaces are the perfect agent tools\!
3 days ago
wow, great idea, i remember a similar project called something something agi when connecting tools to llms were the trend.
upvoted
an
article
3 days ago
Article
Gradio spaces are the perfect agent tools\!
By
โข
โข
12
reacted to
merve's
post with ๐ฅ๐คโค๏ธ
3 days ago
Post
2081
Everything that happened this week in open AI, a recap ๐ค
merve/jan-17-releases-678a673a9de4a4675f215bf5
๐ Multimodal
- MiniCPM-o 2.6 is a new sota any-to-any model by OpenBMB
(vision, speech and text!)
- VideoChat-Flash-Qwen2.5-2B is new video multimodal models by OpenGVLab that come in sizes 2B & 7B in resolutions 224 & 448
- ByteDance released larger SA2VA that comes in 26B parameters
- Dataset: VRC-Bench is a new diverse benchmark for multimodal LLM reasoning performance
๐ฌ LLMs
- MiniMax-Text-01 is a new huge language model (456B passive 45.9B active params) by MiniMaxAI with context length of 4M tokens ๐คฏ
- Dataset: Sky-T1-data-17k is a diverse dataset used to train Sky-T1-32B
- kyutai released Helium-1-Preview-2B is a new small multilingual LM
- Wayfarer-12B is a new LLM able to write D&D ๐ง๐ปโโ๏ธ
- ReaderLM-v2 is a new HTML parsing model by Jina AI
- Dria released, Dria-Agent-a-3B, new agentic coding model (Pythonic function calling) based on Qwen2.5 Coder
- Unsloth released Phi-4, faster and memory efficient Llama 3.3
๐ผ๏ธ Vision
- MatchAnything is a new foundation model for matching
- FitDit is a high-fidelity VTON model based on DiT architecture
๐ฃ๏ธ Audio
- OuteTTS-0.3-1B is a new multilingual text-to-speech model with voice cloning and emotion control capabilities
๐ Retrieval
- lightblue released a new reranker based on Qwen2.5 LB-reranker-0.5B-v1.0 that can handle 95+ languages
- cde-small-v2 is a new sota small retrieval model by
@jxm
๐ Multimodal
- MiniCPM-o 2.6 is a new sota any-to-any model by OpenBMB
(vision, speech and text!)
- VideoChat-Flash-Qwen2.5-2B is new video multimodal models by OpenGVLab that come in sizes 2B & 7B in resolutions 224 & 448
- ByteDance released larger SA2VA that comes in 26B parameters
- Dataset: VRC-Bench is a new diverse benchmark for multimodal LLM reasoning performance
๐ฌ LLMs
- MiniMax-Text-01 is a new huge language model (456B passive 45.9B active params) by MiniMaxAI with context length of 4M tokens ๐คฏ
- Dataset: Sky-T1-data-17k is a diverse dataset used to train Sky-T1-32B
- kyutai released Helium-1-Preview-2B is a new small multilingual LM
- Wayfarer-12B is a new LLM able to write D&D ๐ง๐ปโโ๏ธ
- ReaderLM-v2 is a new HTML parsing model by Jina AI
- Dria released, Dria-Agent-a-3B, new agentic coding model (Pythonic function calling) based on Qwen2.5 Coder
- Unsloth released Phi-4, faster and memory efficient Llama 3.3
๐ผ๏ธ Vision
- MatchAnything is a new foundation model for matching
- FitDit is a high-fidelity VTON model based on DiT architecture
๐ฃ๏ธ Audio
- OuteTTS-0.3-1B is a new multilingual text-to-speech model with voice cloning and emotion control capabilities
๐ Retrieval
- lightblue released a new reranker based on Qwen2.5 LB-reranker-0.5B-v1.0 that can handle 95+ languages
- cde-small-v2 is a new sota small retrieval model by
@jxm
upvoted
2
papers
4 days ago