ml-engineering
ollama
ml-engineering | ollama | |
---|---|---|
9 | 227 | |
10,053 | 72,781 | |
- | 14.0% | |
9.7 | 9.9 | |
9 days ago | 4 days ago | |
Python | Go | |
Creative Commons Attribution Share Alike 4.0 | MIT License |
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.
ml-engineering
- Accelerators
-
Gemma: New Open Models
There is a lot of work to make the actual infrastructure and lower level management of lots and lots of GPUs/TPUs open as well - my team focuses on making the infrastructure bit at least a bit more approachable on GKE and Kubernetes.
https://github.com/GoogleCloudPlatform/ai-on-gke/tree/main
and
https://github.com/google/xpk (a bit more focused on HPC, but includes AI)
and
https://github.com/stas00/ml-engineering (not associated with GKE, but describes training with SLURM)
The actual training is still a bit of a small pool of very experienced people, but it's getting better. And every day serving models gets that much faster - you can often simply draft on Triton and TensorRT-LLM or vLLM and see significant wins month to month.
- FLaNK Stack 29 Jan 2024
-
ML Engineering Online Book
OK, the pdf is ready now: https://github.com/stas00/ml-engineering#pdf-version
-
Self train a super tiny model recommendations
this might be interesting: https://github.com/stas00/ml-engineering/blob/master/transformers/make-tiny-models.md
- The AI Battlefield Engineering – What You Need to Know
- Machine Learning Engineering Guides and Tools
ollama
- Ollama v0.1.45
-
SpringAI, llama3 and pgvector: bRAGging rights!
To support the exploration, I've developed a simple Retrieval Augmented Generation (RAG) workflow that works completely locally on the laptop for free. If you're interested, you can find the code itself here. Basically, I've used Testcontainers to create a Postgres database container with the pgvector extension to store text embeddings and an open source LLM with which I send requests to: Meta's llama3 through ollama.
-
RAG with OLLAMA
Note: Before proceeding further you need to download and run Ollama, you can do so by clicking here.
-
Ollama 0.1.42
`file://*` URLs are now allowed => ollama works with simple html files now
https://github.com/ollama/ollama/commit/1a29e9a879433fc55cf1...
-
How to setup a free, self-hosted AI model for use with VS Code
This guide assumes you have a supported NVIDIA GPU and have installed Ubuntu 22.04 on the machine that will host the ollama docker image. AMD is now supported with ollama but this guide does not cover this type of setup.
-
beginner guide to fully local RAG on entry-level machines
Nowadays, running powerful LLMs locally is ridiculously easy when using tools such as ollama. Just follow the installation instructions for your #OS. From now on, we'll assume using bash on Ubuntu.
- Codestral: Mistral's Code Model
- AIM Weekly 27 May 2024
-
Devoxx Genie Plugin : an Update
I focused on supporting Ollama, GPT4All, and LMStudio, all of which run smoothly on a Mac computer. Many of these tools are user-friendly wrappers around Llama.cpp, allowing easy model downloads and providing a REST interface to query the available models. Last week, I also added "👋🏼 Jan" support because HuggingFace has endorsed this provider out-of-the-box.
- Ask HN: Are companies self hosting LLMs?
What are some alternatives?
slurm-mail - Slurm-Mail is a drop in replacement for Slurm's e-mails to give users much more information about their jobs compared to the standard Slurm e-mails.
llama.cpp - LLM inference in C/C++
peft - 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
gpt4all - gpt4all: run open-source LLMs anywhere
deeplake - Database for AI. Store Vectors, Images, Texts, Videos, etc. Use with LLMs/LangChain. Store, query, version, & visualize any AI data. Stream data in real-time to PyTorch/TensorFlow. https://activeloop.ai
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
pinferencia - Python + Inference - Model Deployment library in Python. Simplest model inference server ever.
private-gpt - Interact with your documents using the power of GPT, 100% privately, no data leaks
haystack - :mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
LocalAI - :robot: The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more models architectures. It allows to generate Text, Audio, Video, Images. Also with voice cloning capabilities.
AtomGPT - 中英文预训练大模型,目标与ChatGPT的水平一致
llama - Inference code for Llama models