Our great sponsors
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
-
flan-alpaca
This repository contains code for extending the Stanford Alpaca synthetic instruction tuning to existing instruction-tuned models such as Flan-T5.
-
stable-diffusion-ui
Discontinued Easiest 1-click way to install and use Stable Diffusion on your computer. Provides a browser UI for generating images from text prompts and images. Just enter your text prompt, and see the generated image. [Moved to: https://github.com/easydiffusion/easydiffusion]
-
alpaca-electron
The simplest way to run Alpaca (and other LLaMA-based local LLMs) on your own computer
I believe this has been extended to mean "on device", which is interesting. See Gerganov's article on Github [0]. I wrote about this here [1] where I made a contrast between the core and the edge. I think the term maps well to this meaning.
What I find more interesting is that in the classic "close network proximity", some parts of the world may not have benefited as much from that trend since the closest nodes of a global delivery network could be several countries away.
[0] https://github.com/ggerganov/llama.cpp/discussions/205
[1] https://medium.com/sort-of-like-a-tech-diary/consumer-ai-is-...
Comparing the 13B model here https://huggingface.co/cerebras/Cerebras-GPT-13B to LLaMA-13B https://github.com/facebookresearch/llama/blob/main/MODEL_CA... you can see that in all of the reasoning tasks Cerebras-GPT lags behind. Any reason to use Cerebras instead of LLaMA? Doesn't seem like it.
I've been following open source LLMs for a while and at first glance this doesn't seem too powerful compared to other open models, Flan-Alpaca[0] is licensed under Apache 2.0, and it seems to perform much better. Although I'm not sure about the legalities about that licensing, since it's basically Flan-T5 fine-tuned using the Alpaca dataset (which is under a Non-Commercial license).
Nonetheless, it's exciting to see all these open models popping up, and I hope that a LLM equivalent to Stable Diffusion comes sooner than later.
[0]: https://github.com/declare-lab/flan-alpaca
Not an llm but this 1 click installer for stable diffusion is literally a 1 click installer. Impressively works.
https://github.com/cmdr2/stable-diffusion-ui
Here's alpaca running in electron. Not exactly one click but close.
https://github.com/ItsPi3141/alpaca-electron
Sorry for the late reply, as I said Flan-UL2 (or Flan-T5 if you want lighter models) fine-tuned against a dataset like CodeAlpaca's[0] is probably the best solution if it's intended for commercial use (otherwise LLaMa should perform better).
[0]: https://github.com/sahil280114/codealpaca
Related posts
- Is it feasible to develop multiple specialised language models that are small in size and expertise-specific, which can be merged to achieve comparable results to those obtained from a single large language model?
- [D] What is the best open source chatbot AI to do transfer learning on?
- [P] ChatLLaMA - A ChatGPT style chatbot for Facebook's LLaMA
- Best Instruct-Trained Alternative to Alpaca/Vicuna?
- How Open is Generative AI? Part 2