llmware
sent
| llmware | sent | |
|---|---|---|
| 9 | 14 | |
| 3,173 | 24 | |
| 6.7% | - | |
| 9.8 | 0.0 | |
| 7 days ago | almost 3 years ago | |
| Python | C | |
| Apache License 2.0 | GNU General Public License v3.0 or later |
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.
llmware
-
More Agents Is All You Need: LLMs performance scales with the number of agents
I couldn't agree more. You should check out LLMWare's SLIM agents (https://github.com/llmware-ai/llmware/tree/main/examples/SLI...). It's focusing on pretty much exactly this and chaining multiple local LLMs together.
A really good topic that ties in with this is the need for deterministic sampling (I may have the terminology a bit incorrect) depending on what the model is indended for. The LLMWare team did a good 2 part video on this here as well (https://www.youtube.com/watch?v=7oMTGhSKuNY)
I think dedicated miniture LLMs are the way forward.
Disclaimer - Not affiliated with them in any way, just think it's a really cool project.
- FLaNK Stack Weekly 19 Feb 2024
-
Show HN: LLMWare ā Small Specialized Function Calling 1B LLMs for Multi-Step RAG
I've been building upon the LLMWare project - https://github.com/llmware-ai/llmware - for the past 3 months. The ability to run these models locally on standard consumer CPUs, along with the abstraction provided to chop and change between models and different processes is really cool.
I think these SLIM models are the start of something powerful for automating internal business processes and enhancing the use case of LLMs. Still kinda blows my mind that this is all running on my 3900X and also runs on a bog standard Hetzner server with no GPU.
- Show HN: LLMWare ā Integrated Solution for RAG in Finance and Legal
- Llmware.ai ā AI Tools for Financial, Legal and Compliance
-
Open Source Advent Fun Wraps Up!
16. LLMWare by Ai Bloks | Github | tutorial
- FLaNK Stack Weekly 16 October 2023
- Strategy for PDF data extraction and Display
sent
- FLaNK Stack Weekly 19 Feb 2024
- Sent ā simple plaintext presentation tool
-
Marp: Markdown Presentation Ecosystem
See also: <https://tools.suckless.org/sent/>, which is similar but has an emphasis in minimalism and the Takakashi method (<https://en.wikipedia.org/wiki/Takahashi_method>)
- Sent: Simple Plaintext Presentation Tool
-
What do you guys use for office?
Google Docs. If I need PowerPoint I mostly just use sent.
-
Tool to create slideshow and export as ppt
If you prefer something more adventurous (as in "create your own export wrapper"), you can check out sent.
-
Making Slides for Presentations
I use sent: https://tools.suckless.org/sent/
-
Vim for presentation?
I like sent. You write in a text file, each paragraph being one slide. Idk how it handles gift but it supports images. It's very simple and limited in features, but if it fits your needs then it's as simple as it gets.
- making a school presentation in linux
-
LPT: Powerpoint slides are supposed to be simple and brief. Nobody is going to read your wall of fancy text when you give your presentation.
This is why I love tools like Sent.
What are some alternatives?
llm-client-sdk - SDK for using LLM
uzlib - Radically unbloated DEFLATE/zlib/gzip compression/decompression library. Can decompress any gzip/zlib data, and offers simplified compressor which produces gzip-compatible output, while requiring much less resources (and providing less compression ratio of course).
pinferencia - Python + Inference - Model Deployment library in Python. Simplest model inference server ever.
patat - Terminal-based presentations using Pandoc
inference - A fast, easy-to-use, production-ready inference server for computer vision supporting deployment of many popular model architectures and fine-tuned models.
mdp - A command-line based markdown presentation tool.
openstatus - š The open-source synthetic & real user monitoring platform š
Diagon - Interactive ASCII art diagram generators. :star2:
megabots - š¤ State-of-the-art, production ready LLM apps made mega-easy, so you don't have to build them from scratch š¤Æ Create a bot, now š«µ
nnn - nĀ³ The unorthodox terminal file manager
SimplyRetrieve - Lightweight chat AI platform featuring custom knowledge, open-source LLMs, prompt-engineering, retrieval analysis. Highly customizable. For Retrieval-Centric & Retrieval-Augmented Generation.
modwm - MODWM - Modular Dynamic Window Manager