Hugging Face's logo
John Smith's picture
340 1052 12014

John Smith PRO

John6666
louisbrulenaudet's profile picture JohnMarlon's profile picture barabero's profile picture
·

AI & ML interests

None yet

Recent Activity

updated a model about 1 hour ago
John6666/veraprime-v1-sdxl
updated a collection about 1 hour ago
LoRAs / Models (SDXL1.0, Pony, SD1.5, Flux, ...)
liked a model about 1 hour ago
AngelBottomless/Illustrious-v0.1-vpred-test
View all activity

Organizations

open/ acc's profile picture FashionStash Group meeting's profile picture

John6666's activity

reacted to hexgrad's post with 🔥 about 1 hour ago
reacted to merve's post with 🔥 about 4 hours ago
view post
Post
610
supercharge your LLM apps with smolagents 🔥

however cool your LLM is, without being agentic it can only go so far

enter smolagents: a new agent library by Hugging Face to make the LLM write code, do analysis and automate boring stuff!

Here's our blog for you to get started https://huggingface.co/blog/smolagents
reacted to tomaarsen's post with 🔥 about 4 hours ago
view post
Post
436
That didn't take long! Nomic AI has finetuned the new ModernBERT-base encoder model into a strong embedding model for search, classification, clustering and more!

Details:
🤖 Based on ModernBERT-base with 149M parameters.
📊 Outperforms both nomic-embed-text-v1 and nomic-embed-text-v1.5 on MTEB!
🏎️ Immediate FA2 and unpacking support for super efficient inference.
🪆 Trained with Matryoshka support, i.e. 2 valid output dimensionalities: 768 and 256.
➡️ Maximum sequence length of 8192 tokens!
2️⃣ Trained in 2 stages: unsupervised contrastive data -> high quality labeled datasets.
➕ Integrated in Sentence Transformers, Transformers, LangChain, LlamaIndex, Haystack, etc.
🏛️ Apache 2.0 licensed: fully commercially permissible

Try it out here: nomic-ai/modernbert-embed-base

Very nice work by Zach Nussbaum and colleagues at Nomic AI.
reacted to singhsidhukuldeep's post with 🤯 about 4 hours ago
view post
Post
208
Excited to share insights from Walmart's groundbreaking semantic search system that revolutionizes e-commerce product discovery!

The team at Walmart Global Technology(the team that I am a part of 😬) has developed a hybrid retrieval system that combines traditional inverted index search with neural embedding-based search to tackle the challenging problem of tail queries in e-commerce.

Key Technical Highlights:

• The system uses a two-tower BERT architecture where one tower processes queries and another processes product information, generating dense vector representations for semantic matching.

• Product information is enriched by combining titles with key attributes like category, brand, color, and gender using special prefix tokens to help the model distinguish different attribute types.

• The neural model leverages DistilBERT with 6 layers and projects the 768-dimensional embeddings down to 256 dimensions using a linear layer, achieving optimal performance while reducing storage and computation costs.

• To improve model training, they implemented innovative negative sampling techniques combining product category matching and token overlap filtering to identify challenging negative examples.

Production Implementation Details:

• The system uses a managed ANN (Approximate Nearest Neighbor) service to enable fast retrieval, achieving 99% recall@20 with just 13ms latency.

• Query embeddings are cached with preset TTL (Time-To-Live) to reduce latency and costs in production.

• The model is exported to ONNX format and served in Java, with custom optimizations like fixed input shapes and GPU acceleration using NVIDIA T4 processors.

Results:
The system showed significant improvements in both offline metrics and live experiments, with:
- +2.84% improvement in NDCG@10 for human evaluation
- +0.54% lift in Add-to-Cart rates in live A/B testing

This is a fantastic example of how modern NLP techniques can be successfully deployed at scale to solve real-world e-
reacted to 1aurent's post with 🔥 about 4 hours ago
reacted to DamarJati's post with ❤️ about 4 hours ago
view post
Post
298
Happy New Year 2025 🤗
For the Huggingface community.
reacted to prithivMLmods's post with 🔥 about 4 hours ago
view post
Post
472
Triangulum Catalogued 🔥💫

🎯Triangulum is a collection of pretrained and instruction-tuned generative models, designed for multilingual applications. These models are trained using synthetic datasets based on long chains of thought, enabling them to perform complex reasoning tasks effectively.

+ Triangulum-10B : prithivMLmods/Triangulum-10B
+ Quants : prithivMLmods/Triangulum-10B-GGUF

+ Triangulum-5B : prithivMLmods/Triangulum-5B
+ Quants : prithivMLmods/Triangulum-5B-GGUF
reacted to csabakecskemeti's post with 👍 about 4 hours ago
reacted to nicolay-r's post with 👀 1 day ago
view post
Post
464
📢 Through the 2024 we attempting in advancing opinion mining by proposing evaluation which involves explanations!

A while ago we launched RuOpinionNE-2024 aimed at extraction of sentiment opinions with spans (as explanations) from mass media news written in Russian language. The formed competition is at the final stage on codalab platform:
📊 https://codalab.lisn.upsaclay.fr/competitions/20244

🔎 What we already observe? For the two type of sentiment labels (positive and negative), our recent findings were that the top performing submission results in F1=0.34 while the baseline LLM approach results in F1=0.17 (see screenshot of the leaderboard below 📸)

⏰️ We finally launch the final stage with a decent amount of submissions which lasts until
15th of January 2025.

🙌 Everyone who wish to evaluate most recent advances on explainable opinion mining during the final stage are welcome!

Codalab main page:
https://codalab.lisn.upsaclay.fr/competitions/20244#learn_the_details
More details on github:
https://github.com/dialogue-evaluation/RuOpinionNE-2024
reacted to csabakecskemeti's post with 🤯 1 day ago
reacted to sequelbox's post with 👀 1 day ago
reacted to cfahlgren1's post with 🚀 1 day ago
reacted to as-cle-bert's post with 🔥 1 day ago
view post
Post
398
Hi HF Community!🤗

As my last 2024 contribution, I decided to write an article about a Competitive Debate Championship simulation I ran with 5 LLMs as competitors and 2 as judges:

https://huggingface.co/blog/as-cle-bert/debate-championship-for-llms

The article covers code, analyses and results, and you can find everything to reproduce this tournament in the GitHub repo 👉 https://github.com/AstraBert/DebateLLM-Championship

I also released a dataset related to the data (motions, arguments, topics, winners...) collected during the tournament 👉 as-cle-bert/DebateLLMs

Happy reading and happy new yeAIr!🎉
reacted to nyuuzyou's post with 👍 1 day ago
view post
Post
412
🎮 ALLSTAR.GG Dataset - nyuuzyou/allstar

A collection of 47,896 gaming clips featuring:
- High-quality gameplay captures with various clip lengths and resolutions
- Complete metadata including user IDs, clip titles, and game parameters
- Content captured from Counter-Strike 2 competitive matches
- Full game statistics and technical parameters
reacted to davidberenstein1957's post with 👀 1 day ago
reacted to ginipick's post with 🔥 2 days ago
view post
Post
2958
🌊 [Dokdo Membership - Next Generation AI Video Creation Platform]

✨ Transform your imagination into mesmerizing videos with Dokdo Membership, an innovative AI-powered platform that generates unique videos from text and images. Built as a streamlined SaaS boilerplate using Python Gradio for Hugging Face users, this tool offers an intuitive way to create AI-generated videos with minimal effort.

🎯 [Key Features]
- 📧 Email-based authentication system with secure login/signup
- 🎁 15 points automatically credited upon registration
- 💰 5 points deduction per video generation
- 🌏 Bilingual support (Korean/English) with automatic translation
- 🖼️ Optional first frame image upload capability
- ⭐ Automatic GiniGEN.AI watermark integration

🚀 [Technical Specifications]
1. 💫 Modern, responsive user interface with Gradio components
2. 📊 Efficient resource management through points system
3. 🎥 High-quality video generation using advanced AI models
4. 🔄 Seamless translation pipeline for multilingual support
5. ⚡ Real-time point tracking and management system
6. 🛡️ Comprehensive content moderation and filtering

📝 [How to Use]
1. ✅ Register with your email to receive 15 initial points
2. 💭 Enter your video description (supports both English and Korean)
3. 📤 Upload a reference image for the first frame (optional)
4. 🎬 Click "Generate Video" (consumes 5 points)
5. 📥 Preview and download your generated video

🔧 [Technical Implementation]
- Built with Python Gradio for seamless Hugging Face Space integration
- Implements secure user authentication and session management
- Features real-time point tracking and automated deduction system
- Includes comprehensive error handling and input validation
- Utilizes advanced AI models for video generation

📮 Need additional points for more creations? Contact us at [email protected] for point acquisition options through public contributions or paid services.

ginigen/Dokdo-membership
  • 1 reply
·
reacted to lewtun's post with 🔥 2 days ago
view post
Post
1694
This paper ( HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs (2412.18925)) has a really interesting recipe for inducing o1-like behaviour in Llama models:

* Iteratively sample CoTs from the model, using a mix of different search strategies. This gives you something like Stream of Search via prompting.
* Verify correctness of each CoT using GPT-4o (needed because exact match doesn't work well in medicine where there are lots of aliases)
* Use GPT-4o to reformat the concatenated CoTs into a single stream that includes smooth transitions like "hmm, wait" etc that one sees in o1
* Use the resulting data for SFT & RL
* Use sparse rewards from GPT-4o to guide RL training. They find RL gives an average ~3 point boost across medical benchmarks and SFT on this data already gives a strong improvement.

Applying this strategy to other domains could be quite promising, provided the training data can be formulated with verifiable problems!
reacted to alielfilali01's post with 🔥 2 days ago
view post
Post
1541
~75% on the challenging GPQA with only 40M parameters 🔥🥳

GREAT ACHIEVEMENT ! Or is it ?

This new Work, "Data Laundering: Artificially Boosting Benchmark Results through Knowledge Distillation", take out the mystery about many models i personally suspected their results. Speacially on leaderboards other than the english one, Like the Open Arabic LLM Leaderbaord OALL/Open-Arabic-LLM-Leaderboard.

The authors of this work, first started by training a model on the GPQA data, which, unsurprisingly, led to the model achieving 100% performance.

Afterward, they trained what they referred to as a 'legitimate' model on legitimate data (MedMCQA). However, they introduced a distillation loss from the earlier, 'cheated' model.

What they discovered was fascinating: the knowledge of GPQA leaked through this distillation loss, even though the legitimate model was never explicitly trained on GPQA during this stage.

This raises important questions about the careful use of distillation in model training, especially when the training data is opaque. As they demonstrated, it’s apparently possible to (intentionally or unintentionally) leak test data through this method.

Find out more: Data Laundering: Artificially Boosting Benchmark Results through Knowledge Distillation (2412.15255)
  • 1 reply
·
reacted to luigi12345's post with 👀 3 days ago
view post
Post
1482
Prompt yourself In a way that will make you detect fatal bugs and crashes of the script and fix each of them in the most optimized and comprehensive way. Don't talk.
reacted to ezgikorkmaz's post with 👀 3 days ago