Language Models Python Packages

argostranslate

Open-source offline translation library written in Python

rustling

A high-performance library for computational linguistics

argos-translate-lt

Open-source offline translation library written in Python

clarifai

Experience the power of Clarifai’s AI platform with the python SDK. 🌟 Star to support our work!

farm

:house_with_garden: Fast & easy transfer learning for NLP. Harvesting language models for the industry. Focus on Question Answering.

functai

Typed functions whose body a language model writes: run them on tables, measure how often they're right, make them better. Python, TypeScript, R and Julia.

ai-proxy-server

OpenAI-compatible HTTP LLM proxy / gateway for multi-provider inference (Google, Anthropic, OpenAI, PyTorch). Lightweight, extensible Python/FastAPI—use as library or standalone service.

mlx-train-perf

Fused, logit-free linear-cross-entropy loss, RAM-fit planner, and benchmark harness for MLX fine-tuning on Apple Silicon

llm-proxy-server

OpenAI-compatible HTTP LLM proxy / gateway for multi-provider inference (Google, Anthropic, OpenAI, PyTorch). Lightweight, extensible Python/FastAPI—use as library or standalone service.

lm-proxy

OpenAI-compatible HTTP LLM proxy / gateway for multi-provider inference (Google, Anthropic, OpenAI, PyTorch). Lightweight, extensible Python/FastAPI—use as library or standalone service.

happytransformer

Happy Transformer makes it easy to fine-tune and perform inference with NLP Transformer models.

openai-http-proxy

OpenAI-compatible HTTP LLM proxy / gateway for multi-provider inference (Google, Anthropic, OpenAI, PyTorch). Lightweight, extensible Python/FastAPI—use as library or standalone service.

ntloss

PyPI package for Number Token Loss (ICML 2025)

inference-proxy

OpenAI-compatible HTTP LLM proxy / gateway for multi-provider inference (Google, Anthropic, OpenAI, PyTorch). Lightweight, extensible Python/FastAPI—use as library or standalone service.

pybo

🦜 NLP for Tibetan, in Python.

anyks-lm

Smart Language Model

oai-proxy

OpenAI-compatible HTTP LLM proxy / gateway for multi-provider inference (Google, Anthropic, OpenAI, PyTorch). Lightweight, extensible Python/FastAPI—use as library or standalone service.

lm-proxy-server

OpenAI-compatible HTTP LLM proxy / gateway for multi-provider inference (Google, Anthropic, OpenAI, PyTorch). Lightweight, extensible Python/FastAPI—use as library or standalone service.

small-text

Active Learning for Text Classification in Python

picollm

On-device LLM Inference Powered by X-Bit Quantization

petals

🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

pytokencalc

Know your LLM costs before you hit send. Count tokens from 20+ providers with 99.9% accuracy. Estimate costs, track usage, optimize spending. No setup required.

aiflows

🤖🌊 aiFlows: The building blocks of your collaborative AI

picollmdemo

On-device LLM Inference Powered by X-Bit Quantization