onnx-coreml
Llama-2-Onnx
| onnx-coreml | Llama-2-Onnx | |
|---|---|---|
| 1 | 3 | |
| 378 | 994 | |
| - | 1.1% | |
| 10.0 | 6.7 | |
| almost 4 years ago | 5 months ago | |
| Python | Python | |
| MIT License | 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.
onnx-coreml
-
Llama 2 on ONNX runs locally
They used to have this: https://github.com/onnx/onnx-coreml
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
What are some alternatives?
llama.cpp - LLM inference in C/C++
vllm - A high-throughput and memory-efficient inference and serving engine for LLMs
SHARK - SHARK - High Performance Machine Learning Distribution
pkgx - the last thing you’ll install
OpenPipe - Turn expensive prompts into cheap fine-tuned models
awesome-data-temporality - A curated list to help you manage temporal data across many modalities 🚀.
gpt-llm-trainer
feldera - Feldera Continuous Analytics Platform
llama2.c - Inference Llama 2 in one file of pure C
fluent-bit - Fast and Lightweight Logs and Metrics processor for Linux, BSD, OSX and Windows
symmetric-ds - SymmetricDS is database replication and file synchronization software that is platform independent, web enabled, and database agnostic. It is designed to make bi-directional data replication fast, easy, and resilient. It scales to a large number of nodes and works in near real-time across WAN and LAN networks.