caravelpinta
Follow
Stars
A feature-rich command-line audio/video downloader
The open-source tool for building high-quality datasets and computer vision models
[ACL 2024 🔥] Video-ChatGPT is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted fo…
Model components of the Llama Stack APIs
Agentic components of the Llama Stack APIs
real time face swap and one-click video deepfake with only a single image
Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supportin…
[ICLR 2024] SWE-Bench: Can Language Models Resolve Real-world Github Issues?
SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.
DSPy: The framework for programming—not prompting—foundation models
Best Practices on Recommendation Systems
Simple programs to demonstrate various applications using the UR (Universal Robots) robot and the PolyScope development interface (URScript).
LinkedIn Data Analyst Jobs Visualization Project
IG Web API Javascript Sample
This project contains a simple Python script that shows a minimal client-side implementation of the Lightstreamer Server Text mode Protocol
A mix of GAN implementations including progressive growing
A natural language modeling framework based on PyTorch
Generate embeddings from large-scale graph-structured data.
PyTorch original implementation of Cross-lingual Language Model Pretraining.
Architecture for deploying real-time scoring of machine learning models using Azure Machine Learning
Open source platform for the machine learning lifecycle
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
A platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.)
Fast and flexible AutoML with learning guarantees.