xjdr-alt / entropix
Entropy Based Sampling and Parallel CoT Decoding
☆3,208Updated 2 months ago
Alternatives and similar repositories for entropix:
Users that are interested in entropix are comparing it to the libraries listed below
- NanoGPT (124M) in 3 minutes☆2,162Updated this week
- System 2 Reasoning Link Collection☆751Updated this week
- Optimizing inference proxy for LLMs☆1,955Updated this week
- Distributed Training Over-The-Internet☆866Updated last month
- Recipes to scale inference-time compute of open models☆975Updated last week
- A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!☆831Updated 2 weeks ago
- Everything about the SmolLM2 and SmolVLM family of models☆1,632Updated this week
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆2,064Updated this week
- Agentless🐱: an agentless approach to automatically solve software development problems☆1,361Updated last month
- Mixture of Agents using Groq☆936Updated 5 months ago
- ☆997Updated last month
- Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜☆1,115Updated last month
- Efficient Triton Kernels for LLM Training☆4,255Updated this week
- [ICLR 2025] Automated Design of Agentic Systems☆1,148Updated this week
- A framework for serving and evaluating LLM routers - save LLM costs without compromising quality☆3,501Updated 5 months ago
- A benchmark to evaluate language models on questions I've previously asked them to solve.☆959Updated 2 months ago
- TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.☆2,017Updated this week
- nanoGPT style version of Llama 3.1☆1,300Updated 5 months ago
- 🤖 MLE-Agent: Your intelligent companion for seamless AI engineering and research. 🔍 Integrate with arxiv and paper with code to provide…☆1,209Updated 3 weeks ago
- ☆783Updated 4 months ago
- Implementation for MatMul-free LM.☆2,951Updated 2 months ago
- Code for BLT research paper☆1,353Updated this week
- The Fastest State-of-the-Art Static Embeddings in the World☆954Updated this week
- prime is a framework for efficient, globally distributed training of AI models over the internet.☆626Updated this week
- Training Large Language Model to Reason in a Continuous Latent Space☆746Updated this week
- Run PyTorch LLMs locally on servers, desktop and mobile☆3,479Updated this week
- Sky-T1: Train your own O1 preview model within $450☆2,214Updated this week
- Implementing the 4 agentic patterns from scratch☆995Updated this week
- Synthetic Data curation for post-training and structured data extraction☆575Updated this week