Pokee Deep Research Model Open Source Repo

A generative world for general-purpose robotics & embodied AI learning.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch

An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)

NanoGPT (124M) in 3 minutes

A PyTorch native platform for training generative AI models

Recipes to train reward model for RLHF.

Prompt design using JSX.

🚀 Efficient implementations of state-of-the-art linear attention models

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

Scalable toolkit for efficient model alignment

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

JVector: the most advanced embedded vector search engine

A curated list of references for MLOps

Write scalable load tests in plain Python 🚗💨

A Kubernetes web UI that is fully-featured, user-friendly and extensible

LDB: A Large Language Model Debugger via Verifying Runtime Execution Step by Step (ACL'24)

🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

AI Observability & Evaluation

This repo includes ChatGPT prompt curation to use ChatGPT and other LLM tools better.

[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

💥💻💥 A data-parallel functional programming language

An LLM agent that conducts deep research (local and web) on any given topic and generates a long report with citations.

The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…

experiments with inference on llama

Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.