Small Language Models Python Packages

solvi

A runtime where decision models propose and your code decides: typed questions, hard rules, quotes checked against the text, escalation with a guaranteed error budget, replayable traces. Works with any System One model.

gutfeel

Judgment calls as one line of Python, built for TypeSafe AI's Jev and running on any small model: likely / classify / rate → YES, NO or UNSURE. Also local NLI, local LLMs, Ollama, vLLM, OpenAI.

physai

PhysAI is an open-source, multi-backend framework for solving partial differential equations with Physics-Informed Neural Networks (PINNs), Fourier Neural Operators (FNOs), and Unified Spectral Element architectures. Has 57 pre-configured residuals and a built-in packaged numerical solver for most geometries and equations.

effgen

[ICML 2026] effGen: Enabling Small Language Models as Capable Autonomous Agents

gutfeel-mcp

Judgment calls as one line of Python, built for TypeSafe AI's Jev and running on any small model: likely / classify / rate → YES, NO or UNSURE. Also local NLI, local LLMs, Ollama, vLLM, OpenAI.

tinyjev

A tiny jev-like model that answers Choice, Score and Noul questions in one forward pass and returns calibrated probabilities. MLX or PyTorch, fully offline, System One compatible.

small-text

Active Learning for Text Classification in Python

maatml

Turn a multi-gigabyte base model into a small subject-matter expert you can run anywhere. One model.yml drives prepare, train, evaluate, export, and serve, with validators checking correctness outside the model at each stage.

artifex

Small Language Model Inference, Fine-Tuning and Observability.

distill-anything

Distill any AI model into one you own — a teacher (Claude/GPT/HF/Ollama) generates your dataset, a student trains on its logits or its words, a judge scores it blind, a benchmark prices it. Runs on a MacBook.

openlanguagemodel

Readable, composable PyTorch library for language models: build Llama, Qwen, Gemma, DeepSeek, Kimi and 20+ other architectures from plain nn.Modules, then train them on CPU, one GPU, or multi-GPU.

embedding-condensation

[𝗜𝗖𝗠𝗟 𝟮𝟬𝟮𝟲] Dispersion loss counteracts embedding condensation and improves generalization in small language models

xlm-core

xLM is a modular, research-friendly framework for developing and comparing non-autoregressive language models. Built on PyTorch and PyTorch Lightning, with Hydra for configuration management, XLM makes it effortless to experiment with cutting-edge NAR LM architectures.

xlm-models

xLM is a modular, research-friendly framework for developing and comparing non-autoregressive language models. Built on PyTorch and PyTorch Lightning, with Hydra for configuration management, XLM makes it effortless to experiment with cutting-edge NAR LM architectures.

smallbatch

Distill once, own the function: compile a fuzzy function into a small local model (teacher labels -> LoRA -> eval gate -> callable local fn)