replicate / cog
Containers for machine learning
β8,284Updated this week
Alternatives and similar repositories for cog:
Users that are interested in cog are comparing it to the libraries listed below
- πΈ Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloadingβ9,349Updated 4 months ago
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (Nβ¦β4,585Updated last month
- Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the clβ¦β21,364Updated this week
- Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with strucβ¦β12,039Updated this week
- Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLMβ7,741Updated last week
- π‘ All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflowsβ9,975Updated this week
- A collection of libraries to optimise AI model performancesβ8,373Updated 5 months ago
- Tensor library for machine learningβ11,541Updated this week
- π A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (iβ¦β8,178Updated this week
- Run any open-source LLMs, such as Llama, Mistral, as OpenAI compatible API endpoint in the cloud.β10,380Updated this week
- Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorchβ8,155Updated 3 months ago
- the AI-native open-source embedding databaseβ17,023Updated this week
- Running large language models on a single GPU for throughput-oriented scenarios.β9,254Updated 2 months ago
- QLoRA: Efficient Finetuning of Quantized LLMsβ10,168Updated 7 months ago
- ImageBind One Embedding Space to Bind Them Allβ8,476Updated 5 months ago
- tiktoken is a fast BPE tokeniser for use with OpenAI's models.β13,023Updated 3 months ago
- AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file convertβ¦β18,648Updated this week
- CodeGen is a family of open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.β4,975Updated 10 months ago
- Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)β11,688Updated this week
- π€ Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.β27,123Updated this week
- An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed librariesβ7,042Updated this week
- The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!β7,274Updated this week
- Train transformer language models with reinforcement learning.β10,609Updated this week
- LlamaIndex is the leading framework for building LLM-powered agents over your data.β38,057Updated this week
- A Bulletproof Way to Generate Structured JSON from Language Modelsβ4,527Updated 10 months ago
- Postgres with GPUs for ML/AI apps.β6,106Updated this week
- RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable)β¦β13,005Updated last week
- Locally run an Instruction-Tuned Chat-Style LLMβ10,240Updated last year
- OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamicalβ¦β37,176Updated 5 months ago