Hugging Face's logo

Social Post Explorers
community
Activity Feed

AI & ML interests

None defined yet.

Recent Activity

ozayezerceli  authored a paper 3 days ago
TurkEmbed: Turkish Embedding Model on NLI & STS Tasks
ozayezerceli  authored a paper 3 days ago
TurkEmbed4Retrieval: Turkish Embedding Model for Retrieval Task
ozayezerceli  authored a paper 17 days ago
Parrot: Persuasion and Agreement Robustness Rating of Output Truth -- A Sycophancy Robustness Benchmark for LLMs
View all activity

KingNish 
posted an update 2 days ago
codelion 
posted an update 3 days ago
view post
Post
2442
Recently, Essential AI released a new 8B base model EssentialAI/rnj-1 they highlighted the importance of data mix for pretraning -

"In the long run, we expect our methods to automatically represent, transform, and blend data to optimize measurable abilities in pre-training. Our work on modeling data taxonomies led to new approaches for jointly clustering and mixing data distributions under data repetition penalties. Many improvements in our STEM abilities can be traced back to this. "

This resonates with the recent work we did around optimal dataset mixing for pretraining where we saw have the right mix can increase the efficiency of training -
https://huggingface.co/blog/codelion/optimal-dataset-mixing
DavidVivancos 
posted an update 5 days ago
codelion 
posted an update 5 days ago
codelion 
posted an update 7 days ago
view post
Post
2267
Perplexity released a dataset (BrowseSafe) and benchmark to catch and prevent malicious prompt-injection instructions in real-time.

We trained a prompt injection classifier on BrowseSafe using adaptive-classifier with ModernBERT-base embeddings.

74.9% F1 on detecting prompt injection in web content.

Model -> adaptive-classifier/browsesafe
Dataset -> perplexity-ai/browsesafe-bench
Repo -> https://github.com/codelion/adaptive-classifier
  • 1 reply
·
danielhanchen 
posted an update 7 days ago
view post
Post
3333
Mistral's new Ministral 3 models can now be Run & Fine-tuned locally! (16GB RAM)
Ministral 3 have vision support and the best-in-class performance for their sizes.
14B Instruct GGUF: unsloth/Ministral-3-14B-Instruct-2512-GGUF
14B Reasoning GGUF: unsloth/Ministral-3-14B-Reasoning-2512-GGUF

🐱 Step-by-step Guide: https://docs.unsloth.ai/new/ministral-3
All GGUFs, BnB, FP8 etc. variants uploads: https://huggingface.co/collections/unsloth/ministral-3
·
flavoredquark 
authored a paper 8 days ago
codelion 
posted an update 8 days ago
view post
Post
1580
I just published Ellora - 6 production-ready LoRA recipes for enhancing LLMs with specific capabilities. Each recipe costs under $100 to run and includes complete training code, data generation, and evaluation.

The 6 Recipes:
Recipe 1: Accuracy Recovery - Recover 75% of quantization losses with self-distillation
Recipe 2: Reasoning LoRA - Add structured thinking with GRPO (0% to 60% adoption, 75% quality boost)
Recipe 3: Tool Calling - Real execution on actual codebases
Recipe 4: Context Extension - Scale from 32K to 2M tokens (61x increase)
Recipe 5: Secure Code Generation - 97% vulnerability reduction using automated Semgrep analysis
Recipe 6: Execution-Aware World Models - Teaching models runtime behavior

Why Recipes?
Ellora provides methodologies, not frameworks. Use them with your existing tools (PEFT, LoRAX, vLLM, Unsloth, HuggingFace). Each recipe uses self-supervised data generation (Magpie approach) - no expensive human labeling required.

All recipes include Jupyter notebooks you can run immediately with clear success metrics.

GitHub: https://github.com/codelion/ellora
Full Article: https://huggingface.co/blog/codelion/ellora-lora-recipes

Built something with these recipes? I'd love to see what you create!
danielhanchen 
posted an update 12 days ago
codelion 
posted an update 21 days ago
view post
Post
1972
Introducing OpenEvolve Prompt Optimizer - a Space that automatically evolves and optimizes your prompts using OpenEvolve!

This tool uses OpenEvolve to iteratively improve prompts by testing them on real datasets and evolving better versions. No more manual prompt engineering guesswork - let OpenEvolve find the optimal prompts for you.

How it works:
- Enter your initial prompt using {input} as a placeholder for dataset inputs
- Input any HuggingFace dataset name you want to use for optimization
- Specify the dataset split and field names for your use case
- Click Optimize Prompt and the system will validate everything first
- Compare your initial prompt vs the evolved best prompt side-by-side

Try it here: algorithmicsuperintelligence/prompt-optimizer

OpenEvolve GitHub: https://github.com/algorithmicsuperintelligence/openevolve
DavidVivancos 
posted an update 24 days ago
codelion 
posted an update 26 days ago
view post
Post
2459
🎯 Introducing Chayan: A Calibrated 4-Model LLM Router Achieving 69% Accuracy on RouterArena

We're excited to share Chayan, a cost-efficient LLM router that intelligently routes queries between 4 models to maximize accuracy while minimizing cost. Chayan just submitted to the RouterArena leaderboard and achieved 69.05% accuracy on the benchmark!

🔗 Model: adaptive-classifier/chayan
🔗 Dataset: RouteWorks/RouterArena

📊 Performance Highlights

Chayan achieves impressive results on the RouterArena benchmark:
• 69.05% accuracy (would rank #1 on current leaderboard)
• $0.333 per 1K queries
• +12.07pp improvement over all-mini baseline (56.98%)
• 99% of perfect 2-model oracle performance at 57% lower cost

Compared to our previous 2-model router (61.43% accuracy), Chayan delivers +7.62pp improvement through smarter 4-model routing.

🧠 How It Works

Chayan uses an Adaptive K-NN classifier with prototype memory to route between 4 models:
• openai/gpt-4o-mini (fast & cheap)
• google/gemini-2.5-flash-lite (balanced)
• google/gemini-2.5-flash (capable)
• openai/gpt-4o (most powerful)

🚀 Getting Started

You can use Chayan directly from HuggingFace:

from adaptive_classifier import AdaptiveClassifier

Load Chayan
router = AdaptiveClassifier.load("adaptive-classifier/chayan")

Route a query
query = "What is the capital of France?"
predictions = router.predict(query, k=4)

Get top model recommendation
best_model = predictions[0][0]
print(f"Recommended model: {best_model}")

Built with the adaptive-classifier library: https://github.com/codelion/adaptive-classifier
Bils 
posted an update 27 days ago
codelion 
posted an update about 1 month ago
view post
Post
3979
Want to experiment with pre-training dataset mixtures but don't want to process terabytes of data? We've got you covered.

We're releasing a collection of several carefully curated 1B token dataset samples specifically designed for rapid prototyping and pretraining experiments: https://huggingface.co/collections/codelion/pre-training-dataset-samples

These samples were created using reservoir sampling - an algorithm that guarantees statistically unbiased random samples from massive source datasets. This means results you get at the 1B token scale are representative of how these datasets behave at 100B+ token scales, letting you iterate quickly without the computational overhead.

The collection includes:
- finePDFs-1B: High-quality textbook-style educational content
- DCLM-baseline-1B: Filtered, diverse web content
- FineWeb-Edu-1B: Curated educational web resources

We used these exact samples to run 50+ systematic experiments on dataset mixing strategies, ultimately discovering that a 50-30-20 mixture of finePDFs + DCLM-baseline + FineWeb-Edu achieves 90%+ of GPT-2's performance with just 1/10th the training data.

Whether you're researching optimal data mixtures, testing curriculum learning strategies, or just want to quickly prototype a pretraining run, these samples give you a solid foundation to start experimenting immediately.

Read the full story of how we used these datasets to find the optimal pretraining recipe: https://huggingface.co/blog/codelion/optimal-dataset-mixing
  • 1 reply
·
danielhanchen 
posted an update about 1 month ago
lunarflu 
posted an update about 1 month ago
lunarflu 
posted an update about 1 month ago
lunarflu 
posted an update about 1 month ago
view post
Post
2677
💸🤑You don’t need 100 GPUs to train something amazing!

Our Smol Training Playbook teaches you a better path to world-class LLMs, for free!

Check out the #1 trending space on 🤗 :
HuggingFaceTB/smol-training-playbook
codelion 
posted an update about 1 month ago
view post
Post
272
MARS Achieves Strong Results on Google DeepMind's IMO-Bench

We evaluated OptiLLM's MARS (Multi-Agent Reasoning System) approach on IMO-Bench, Google DeepMind's challenging mathematical reasoning benchmark with International Mathematical Olympiad-level problems.

What is MARS?

MARS is a multi-agent reasoning technique that works with any LLM. It uses 3 parallel reasoning agents that independently solve problems, then verifies their solutions through consensus and iterative refinement. The key advantage: it's model-agnostic and can be applied to any base model through OptiLLM's inference proxy.

Results on IMO-Bench:

AnswerBench (400 short-answer problems):
MARS: 36.0% (144/400 correct)
Baseline: 24.5% (98/400 correct)
Improvement: +11.5pp across all domains

Category breakdown:
- Algebra: 33% (vs 21% baseline)
- Combinatorics: 26% (vs 19% baseline)
- Geometry: 43% (vs 28% baseline)
- Number Theory: 42% (vs 30% baseline)

ProofBench (60 proof construction problems):
MARS: 26.7% (16/60 correct)
Baseline: 18.3% (11/60 correct)
Improvement: +8.4pp

Category breakdown:
- Number Theory: 42.9% (vs 14.3% baseline)
- Combinatorics: 37.5% (vs 31.2% baseline)
- Algebra: 18.8% (vs 25.0% baseline)
- Geometry: 7.1% (vs 0.0% baseline)

All results achieved using google/gemini-2.5-flash-lite-preview-09-2025 as the base model. The same MARS approach can enhance reasoning for any model through OptiLLM's OpenAI-compatible API.

Datasets available at:
AnswerBench: huggingface.co/datasets/Hwilner/imo-answerbench
ProofBench: huggingface.co/datasets/Hwilner/imo-proofbench

Try it yourself:

python optillm.py --approach mars --model google/gemini-2.5-flash-lite-preview-09-2025

Or via API with approach prefix:

model: "mars-google/gemini-2.5-flash-lite-preview-09-2025"

Full evaluation code and results available at: github.com/algorithmicsuperintelligence/optillm
DavidVivancos 
posted an update about 1 month ago