swairshah / Intensify
coloring terminal text with intensities (used for plotting probability, entropy with tokens)
☆12Updated last month
Related projects ⓘ
Alternatives and complementary repositories for Intensify
- look how they massacred my boy☆54Updated 3 weeks ago
- ☆36Updated 3 months ago
- ☆40Updated this week
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆22Updated last month
- ☆20Updated last week
- alternative way to calculating self attention☆18Updated 5 months ago
- NLP with Rust for Python 🦀🐍☆59Updated 5 months ago
- never forget anything again! combine AI and intelligent tooling for a local knowledge base to track catalogue, annotate, and plan for you…☆32Updated 5 months ago
- Cerule - A Tiny Mighty Vision Model☆67Updated 2 months ago
- ☆27Updated 4 months ago
- Lightweight tools for quick and easy LLM demo's☆26Updated last month
- ☆48Updated last year
- ☆31Updated 2 weeks ago
- Exploration using DSPy to optimize modules to maximize performance on the OpenToM dataset☆13Updated 8 months ago
- Using modal.com to process FineWeb-edu data☆19Updated 2 months ago
- Tools to make language models a bit easier to use☆30Updated 2 weeks ago
- ☆22Updated last year
- Small, simple agent task environments for training and evaluation☆16Updated last week
- Training hybrid models for dummies.☆15Updated 2 weeks ago
- ☆18Updated last month
- ☆100Updated 3 months ago
- Alpha-Zero Connect Four NN trained via self play☆13Updated last month
- High level library for batched embeddings generation, blazingly-fast web-based RAG and quantized indexes processing ⚡☆59Updated last week
- ☆49Updated 7 months ago
- Collection of autoregressive model implementation☆66Updated last week
- Routing on Random Forest (RoRF)☆83Updated last month
- DSPy program/pipeline inspector widget for Jupyter/VSCode Notebooks.☆28Updated 8 months ago
- A Python library to orchestrate LLMs in a neural network-inspired structure☆41Updated last month
- ☆40Updated 7 months ago