kuasar
h2o-llmstudio
kuasar | h2o-llmstudio | |
---|---|---|
4 | 13 | |
1,181 | 3,602 | |
2.3% | 2.8% | |
8.5 | 9.3 | |
7 days ago | 1 day ago | |
Rust | Python | |
Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
kuasar
-
The advantage of WASM compared with container runtimes
Right now most early examples alas boot a container with a wasm runtime for each wasm instance, which is a sad waste. The whole advantage of wasm should be very lightweight low overhead wasm runtime instances atop a common wasm process. Having a process or container for each instance loses a ton of the benefit, makes it not much better than a regular container.
Thankfully there is work like the Containerd Sandbox API which enables new architectures like this. https://github.com/containerd/containerd/issues/4131
It's still being used to spawn a wasm processes per instance for now, but container runtime project Kuasar is already using the Sandbox API to save significant resources, and has already chimed in in comments on HN to express a desire to have shared-process/multi-wasm-instamxe runtimes, which could indeed allow sub ms spawning that could enable instance per request architectures. https://github.com/kuasar-io/kuasar
- FLaNK Stack Weekly for 30 April 2023
- Kuasar - A Container Runtime in Rust
- Kuasar: An efficient multi-sandbox container runtime
h2o-llmstudio
- Paid dev gig: develop a basic LLM PEFT finetuning utility
-
building LLM model to answer question
Vector databases are probably a good place to start, though you've already tried LlamaIndex. You might want to try https://github.com/h2oai/h2o-llmstudio and https://github.com/h2oai/h2ogpt.
- [P] Uptraining a pretrained model using company data?
-
Permissive LLaMA 7b chat/instruct model
Training framework: https://github.com/h2oai/h2o-llmstudio
-
Is what I need possible currently?
Check out LLM Studio for fine tuning LLMs. Open source: https://github.com/h2oai/h2o-llmstudio
- FLaNK Stack Weekly for 30 April 2023
- FLaNK Stack Weekly for 24April2023
- GitHub - h2oai/h2o-llmstudio: H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs
- New Open Source Framework and No-Code GUI for Fine-Tuning LLMs: H2O LLM Studio
- Can an average person learn how to build a LLM model?
What are some alternatives?
kata-containers - Kata Containers is an open source project and community working to build a standard implementation of lightweight Virtual Machines (VMs) that feel and perform like containers, but provide the workload isolation and security advantages of VMs. https://katacontainers.io/
h2ogpt - Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://codellama.h2o.ai/
keras-ocr - A packaged and flexible version of the CRAFT text detector and Keras CRNN recognition model.
killport - A command-line tool to easily kill processes running on a specified port.
pandas-ai - Chat with your database (SQL, CSV, pandas, polars, mongodb, noSQL, etc). PandasAI makes data analysis conversational using LLMs (GPT 3.5 / 4, Anthropic, VertexAI) and RAG.
HealthGPT - Query your Apple Health data with natural language 💬 🩺
bark - 🔊 Text-Prompted Generative Audio Model
orbstack - Fast, light, simple Docker containers & Linux machines for macOS
agorakube - Agorakube is a Certified Kubernetes Distribution built on top of CNCF ecosystem that provides an enterprise grade solution following best practices to manage a conformant Kubernetes cluster for on-premise and public cloud providers.
ue5-llama-lora - A proof-of-concept project that showcases the potential for using small, locally trainable LLMs to create next-generation documentation tools.