Machine learning metrics for distributed, scalable PyTorch applications.
- python
- data-science
- machine-learning
- pytorch
98,836 visible repositories in the index
49–72 of 108 · Most stars
Machine learning metrics for distributed, scalable PyTorch applications.
AssetOpsBench - Industry 4.0: A unified benchmark and framework for building, orchestrating, and evaluating domain-specific AI agents for Industry 4.0 asset operations and maintenance, with 460+ scenarios, 5 specialist agents (IoT, FMSR, TSFM, Work Order,...), and multi-agent orchestration blueprints (MetaAgent, AgentHive) over MCP.
A local inference engine for Apple silicon, built around the model.
The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.
LLM Inference Engine for Metal, CUDA and Vulkan.
Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.
Run a 1-billion parameter LLM on a $10 board with 256MB RAM
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks
Community maintained hardware plugin for vLLM on Apple Silicon
中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3
NeurIPS 2025 Spotlight; ICLR2024 Spotlight; CVPR 2024; EMNLP 2024
Tool for generating high quality Synthetic datasets
A playground of highly experimental prompts, Jinja2 templates & scripts for machine intelligence models from OpenAI, Anthropic, DeepSeek, Meta, Mistral, Google, xAI & others. Author: Alex Bilzerian (2022-present).
Fine-tune Gemma 4 and 3n with audio, images and text on Apple Silicon, using PyTorch and Metal Performance Shaders.
LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA and fine-tuned with the Focused Transformer (FoT) method.
Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI
Evaluation code for various unsupervised automated metrics for Natural Language Generation.
OpenTelemetry Instrumentation for Agent Observability
Trace-native CI/CD for AI agents — production failures become regression tests that block the PR. Auto-detect, cluster, freeze into hermetic cases, replay in CI for $0.
HOTA (and other) evaluation metrics for Multi-Object Tracking (MOT).
Open memory & reliability layer for AI agents + independent judging/verification (NACRE judge, caliber-bench meta-benchmark, preregistered criteria) — by Nautilus Platform
Code for our EMNLP 2023 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models"
Langtrace 🔍 is an open-source, Open Telemetry based end-to-end observability tool for LLM applications, providing real-time tracing, evaluations and metrics for popular LLMs, LLM frameworks, vectorDBs and more.. Integrate using Typescript, Python. 🚀💻📊