Llama-2-Onnx
symmetric-ds
| Llama-2-Onnx | symmetric-ds | |
|---|---|---|
| 3 | 12 | |
| 998 | 705 | |
| 1.5% | 1.7% | |
| 6.7 | 9.5 | |
| 5 months ago | 3 days ago | |
| Python | Java | |
| 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.
Llama-2-Onnx
-
Show HN: Fine-tune your own Llama 2 to replace GPT-3.5/4
System: Here's some docs, answer concisely in a sentence.
YMMV on cost still, depends on cloud vendor, and my intuition & viewpoint agrees with yours, GPT-3.5 is priced low enough that there isn't a case where it makes sense to use another model.
It strikes me now that _very_ likely and not just our intuition: OpenAI's $/GPU hour is likely <= any other vendor's.
The next big step will come from formalizing the stuff rolling around the local LLM community, for months now it's either been one-off $X.c stunts that run on desktop, and the vast majority of the _actual_ usage and progress is coming from porn-y stuff, like all nascent tech.
Microsoft has LLaMa-2 ONNX available on GitHub[1]. There's budding but very small projects in different languages to wrap ONNX. Once there's a genuine cross-platform[2] ONNX wrapper that makes running LLaMa-2 easy, there will be a step change. It'll be "free"[3] to run your fine-tuned model that does as well as GPT-4 .
It's not clear to me exactly when this will occur. It's "difficult" now, but only because the _actual usage_ in the local LLM community doesn't have a reason to invest in ONNX, and it's extremely intimidating to figure out how exactly to get LLaMa-2 running in ONNX. Microsoft kinda threw it up on GitHub and moved on, the sample code even still needs a PyTorch model. I see at least one very small company on HuggingFace that _may_ have figured out full ONNX.
[1] https://github.com/microsoft/Llama-2-Onnx
- FLaNK Stack Weekly for 14 Aug 2023
- Llama 2 on ONNX runs locally
symmetric-ds
- FLaNK Stack Weekly for 14 Aug 2023
-
SymmetricDS: Open-Source, cross platform database replication software
For those interested in the source, here is the GitHub repo: https://github.com/JumpMind/symmetric-ds
-
How do I add database replication across different servers to my Docker Compose deployment without using different Docker files on each server?
I’m not a database guy, but maybe look at symmetricds. Also at https://hub.docker.com/r/jumpmind/symmetricds.
-
Seamless integration of Databases
There are several CDC (change data capture) solutions on the market. I've used https://www.symmetricds.org quite successfully in the past.
- Dockerfile for jumpmind image
-
How do you "ship out" web-based systems na isang establishment lang gagamit?
And then using https://www.symmetricds.org/ with mongodb
-
migrate giant 17TB DB from mariadb10.4 to MySQL 8
Use replication. https://www.symmetricds.org/
- [AMA] We are the developers of SymmetricDS, a FOSS database synchronization project. Ask us anything
- SymmetricDS: Fast and Flexible Database Replication
- SymmetricDS: Database Synchronisation Solution
What are some alternatives?
vllm - A high-throughput and memory-efficient inference and serving engine for LLMs
Flyway - Flyway by Redgate • Database Migrations Made Easy.
pkgx - the last thing you’ll install
walrus - Applying RLS to PostgreSQL WAL
onnx-coreml - ONNX to Core ML Converter
pglogical - Logical Replication extension for PostgreSQL 15, 14, 13, 12, 11, 10, 9.6, 9.5, 9.4 (Postgres), providing much faster replication than Slony, Bucardo or Londiste, as well as cross-version upgrades.
awesome-data-temporality - A curated list to help you manage temporal data across many modalities 🚀.
obevo - Obevo is a database deployment tool that handles enterprise scale schemas and complexity
OpenPipe - Turn expensive prompts into cheap fine-tuned models
LINQ to DB - Linq to database provider.
llama.cpp - LLM inference in C/C++
scalardb - Universal transaction manager