LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?
Paper
•
2506.11928
•
Published
•
24
Naman Vats
namanvats
AI & ML interests
Building things one step at a time
Recent Activity
upvoted
a
paper
13 days ago
LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive
Programming?
liked
a model
10 months ago
sentence-transformers/all-MiniLM-L6-v2
Organizations
upvoted
a
paper
13 days ago
liked
a
model
10 months ago
reacted to
do-me's
post with 👍
about 1 year ago
Post
1164
Hey HuggingFace, love your open source attitude and particularly transformers.js for embedding models! Your current integration "use this model" gives you the transformers.js code, but there is no quick way to really test a model in one click.
SemanticFinder ( do-me/SemanticFinder) offers such an integration for all compatible feature-extraction models! All you need to do is add a URL parameter with the model ID to it, like so: https://do-me.github.io/SemanticFinder/?model=Xenova/bge-small-en-v1.5. You can also decide between quantized and normal mode with https://do-me.github.io/SemanticFinder/?model=Xenova/bge-small-en-v1.5&quantized=false. Maybe that would do for a HF integration?
I know it's a small open source project, but I really believe that it provides value for devs before deciding for one model or the other. Also, it's much easier than having to spin up a notebook, install dependencies etc.. It's private, so you could even do some real-world evaluation on personal data without having to worry about third-party services data policies.
Happy to hear the community's thoughts!
SemanticFinder ( do-me/SemanticFinder) offers such an integration for all compatible feature-extraction models! All you need to do is add a URL parameter with the model ID to it, like so: https://do-me.github.io/SemanticFinder/?model=Xenova/bge-small-en-v1.5. You can also decide between quantized and normal mode with https://do-me.github.io/SemanticFinder/?model=Xenova/bge-small-en-v1.5&quantized=false. Maybe that would do for a HF integration?
I know it's a small open source project, but I really believe that it provides value for devs before deciding for one model or the other. Also, it's much easier than having to spin up a notebook, install dependencies etc.. It's private, so you could even do some real-world evaluation on personal data without having to worry about third-party services data policies.
Happy to hear the community's thoughts!
-
- 1 reply
Created API for model validation and quick integration of LLM Models in codebase: https://rapidapi.com/way2naman13/api/llm-api1/details
reacted to
naskio's
post with 🚀
about 1 year ago
Post
1444
🚀 Meet MergeUI - an All-in-one UI for Exploring Merged LLMs on Hugging Face 🤗!
Model merging is a cool new technique for creating powerful language models for cheap (no GPU required). But it raises questions like:
- Which models should we merge?
- What merge strategies work best?
- How do different base models affect performance?
With MergeUI, you can easily:
- Visualise the family tree and lineage of any merged model.
- Explore benchmark performance of family trees from the Open LLM Leaderboard.
- Analyse the different merge strategies used.
- Check license information for merged models and their ancestors.
All this helps you explore and understand merged models, uncover valuable insights, and make better decisions for your projects.
Ready to dive in? Check out these links:
- 🧬 Try MergeUI - https://naskio-mergeui.hf.space
- 👨💻 Source Code - https://github.com/naskio/mergeui
Love this project? boost it on GitHub and share it with your network.
#merge #mergekit #leaderboard
naskio/mergeui
Model merging is a cool new technique for creating powerful language models for cheap (no GPU required). But it raises questions like:
- Which models should we merge?
- What merge strategies work best?
- How do different base models affect performance?
With MergeUI, you can easily:
- Visualise the family tree and lineage of any merged model.
- Explore benchmark performance of family trees from the Open LLM Leaderboard.
- Analyse the different merge strategies used.
- Check license information for merged models and their ancestors.
All this helps you explore and understand merged models, uncover valuable insights, and make better decisions for your projects.
Ready to dive in? Check out these links:
- 🧬 Try MergeUI - https://naskio-mergeui.hf.space
- 👨💻 Source Code - https://github.com/naskio/mergeui
Love this project? boost it on GitHub and share it with your network.
#merge #mergekit #leaderboard
naskio/mergeui
reacted to
fdaudens's
post with 🔥
about 1 year ago
Post
1142
Switching from French to German to Chinese in the same discussion 😅
Impressive to see Cohere for AI's new Aya model multilingual capabilities.
- C4AI Aya 23 is a research open weights release
- 8 and 35 billion parameter models
- 23 languages supported
You can try it out here: https://huggingface.co/spaces/CohereForAI/aya-23
Impressive to see Cohere for AI's new Aya model multilingual capabilities.
- C4AI Aya 23 is a research open weights release
- 8 and 35 billion parameter models
- 23 languages supported
You can try it out here: https://huggingface.co/spaces/CohereForAI/aya-23
- 3 replies
reacted to
DavidGF's
post with 🔥
about 1 year ago
Post
1521
Introducing Kraken-LoRA – a lightweight version of Kraken that uses LoRA-Adapters as Experts based on the base model.
@fernandofernandes , me, @Crystalcareai , @ehartford created the Kraken-LoRA!
🔍 What’s the big deal?
✅ Size Consistency: While Kraken’s size increases with more Experts, Kraken-LoRA remains as compact as the base model (e.g., 8b if you use Meta-Llama3-8b-Instruct).
✅ VRAM Efficiency: Kraken-LoRA is highly VRAM efficient, maintaining the power of all experts without the bloat.
✅ Dynamic Adaptation: LoRA adapters are applied dynamically at runtime, following the routing process.
✅ High Efficiency: Enjoy increased efficiency without compromising performance, as long as the LoRA adapters match the base model.
💡 Conclusion: Kraken-LoRA empowers businesses to experience enhanced flexibility and performance from our architecture, enabling further scalability without sacrificing performance.
Check out the model here: VAGOsolutions/Kraken-LoRA
Explore the code here: https://github.com/cognitivecomputations/kraken/tree/main/Kraken-LoRA
Have fun with Kraken-LoRA! 🐙
@fernandofernandes , me, @Crystalcareai , @ehartford created the Kraken-LoRA!
🔍 What’s the big deal?
✅ Size Consistency: While Kraken’s size increases with more Experts, Kraken-LoRA remains as compact as the base model (e.g., 8b if you use Meta-Llama3-8b-Instruct).
✅ VRAM Efficiency: Kraken-LoRA is highly VRAM efficient, maintaining the power of all experts without the bloat.
✅ Dynamic Adaptation: LoRA adapters are applied dynamically at runtime, following the routing process.
✅ High Efficiency: Enjoy increased efficiency without compromising performance, as long as the LoRA adapters match the base model.
💡 Conclusion: Kraken-LoRA empowers businesses to experience enhanced flexibility and performance from our architecture, enabling further scalability without sacrificing performance.
Check out the model here: VAGOsolutions/Kraken-LoRA
Explore the code here: https://github.com/cognitivecomputations/kraken/tree/main/Kraken-LoRA
Have fun with Kraken-LoRA! 🐙
reacted to
DmitryRyumin's
post with 🔥
about 1 year ago
Post
1600
🚀🎭🌟 New Research Alert - Gaussian Head & Shoulders (Avatars Collection)! 🌟🎭🚀
📄 Title: Gaussian Head & Shoulders: High Fidelity Neural Upper Body Avatars with Anchor Gaussian Guided Texture Warping 🔝
📝 Description: Gaussian Head & Shoulders is a method for creating high-fidelity upper body avatars by integrating 3D morphable head models with a neural texture warping approach to overcome the limitations of Gaussian splatting.
👥 Authors: Tianhao Wu et al.
📄 Paper: Gaussian Head & Shoulders: High Fidelity Neural Upper Body Avatars with Anchor Gaussian Guided Texture Warping (2405.12069)
🌐 Github Page: https://gaussian-head-shoulders.netlify.app
📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
🚀 Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36
🔍 Keywords: #3DModeling #NeuralAvatars #GaussianSplatting #HighFidelityAvatars #3DReconstruction #AvatarRendering #TextureWarping #ComputerGraphics #DeepLearning #ComputerVision #Innovation
📄 Title: Gaussian Head & Shoulders: High Fidelity Neural Upper Body Avatars with Anchor Gaussian Guided Texture Warping 🔝
📝 Description: Gaussian Head & Shoulders is a method for creating high-fidelity upper body avatars by integrating 3D morphable head models with a neural texture warping approach to overcome the limitations of Gaussian splatting.
👥 Authors: Tianhao Wu et al.
📄 Paper: Gaussian Head & Shoulders: High Fidelity Neural Upper Body Avatars with Anchor Gaussian Guided Texture Warping (2405.12069)
🌐 Github Page: https://gaussian-head-shoulders.netlify.app
📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
🚀 Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36
🔍 Keywords: #3DModeling #NeuralAvatars #GaussianSplatting #HighFidelityAvatars #3DReconstruction #AvatarRendering #TextureWarping #ComputerGraphics #DeepLearning #ComputerVision #Innovation
liked
a
Space
about 1 year ago
