31–40 of 356 posts
Microsoft published a paper on their FLAME model (60M parameters) for Excel formula repair/completion which outperformed much larger models (>100B parameters). https://arxiv.org/abs/2301.13779
I simply use it to de-anonymize code that I typed in via Claude Maybe should write a plugin for it (open source): 1. Put in all your work related questions in the plugin, an LLM will make it as an abstract question for you to preview and send it 2. And then get the answer with all the data back E.g. df[“cookie_company_name”] becomes df[“a”] and back
I think this would have some additional benefits of not confusing the larger model with facts it doesn't need to know about. My erasing information, you can allow its attention heads to focus on the pieces that matter.
Requires further study.
We're using small language models to detect prompt injection. Not too cool, but at least we can publish some AI-related stuff on the internet without a huge bill.
JetBrains' local single-line autocomplete model is 0.1B (w/ 1536-token context, ~170 lines of code): https://blog.jetbrains.com/blog/2024/04/04/full-line-code-co... For context, GPT-2-small is 0.124B params (w/ 1024-token context).
For that short of a run, you'll spend more time waiting for the node to come up, downloading the dataset, and compiling the model, though.
Microsoft published a paper on their FLAME model (60M parameters) for Excel formula repair/completion which outperformed much larger models (>100B parameters). https://arxiv.org/abs/2301.13779
But I feel we're going back full circle. These small models are not generalist, thus not really LLMs at least in terms of objective. Recently there has been a rise of "specialized" models that provide lots of values, but that's not why we were sold on LLMs.
I'm fine with and prefer specialist models in most cases.
Earlier quoted context omitted.
Llama 3.2 has about 3.2b parameters. I have to admit, I use bigger ones like phi-4 (14.7b) and Llama 3.3 (70.6b) but I think Llama 3.2 could do de-anonimization and anonimization of code
Llama 3.2 punches way above its weight. For general "language manipulation" tasks it's good enough - and it can be used on a CPU with acceptable speed.
I have a tiny device that listens to conversations between two people or more and constantly tries to declare a "winner"
I have a tiny device that listens to conversations between two people or more and constantly tries to declare a "winner"
I simply use it to de-anonymize code that I typed in via Claude Maybe should write a plugin for it (open source): 1. Put in all your work related questions in the plugin, an LLM will make it as an abstract question for you to preview and send it 2. And then get the answer with all the data back E.g. df[“cookie_company_name”] becomes df[“a”] and back