@jbgruber.bsky.social presenting rollama, an R package that brings gLLMs to your local R setup. Exciting possibilities for reproducible computational text analysis! #comptext
26.04.2025 08:06 β π 35 π 5 π¬ 0 π 1@max-web.bsky.social
NLProc and Social Stratification https://www.goethe-university-frankfurt.de/115948107/Maximilian_Weber
@jbgruber.bsky.social presenting rollama, an R package that brings gLLMs to your local R setup. Exciting possibilities for reproducible computational text analysis! #comptext
26.04.2025 08:06 β π 35 π 5 π¬ 0 π 1@max-web.bsky.social presenting our first try to use LLMs ({rollama}) to extract topics from a large corpus: the public reaction to the releases of Galactica and Chatgpt within weeks from each other in 2022 (which couldn't have been more different!) #comptext2025
25.04.2025 10:15 β π 26 π 4 π¬ 0 π 0New Course Alert! π
Generative AI for Social Science Research
This course explores how to apply AI in social science research, from basic interactions to fine-tuning models for large-scale data analysis.
Find out more & apply: bit.ly/4l3nnGI
#ESS2025 #GenerativeAI
You can run it locally with Ollama and also use the model within R using the Rollama R package. github.com/JBGruber/rol...
29.01.2025 12:43 β π 1 π 0 π¬ 0 π 0deepseek is an extremly impressive open weights LLM. But the guardrails are absolutely wild π€¨
27.01.2025 13:55 β π 17 π 8 π¬ 2 π 0Running Phi-4 and other LLMs in R using Google Colab for free through the rollama R-Package medium.com/@weber.aca/r...
10.01.2025 13:54 β π 1 π 1 π¬ 0 π 0Submission for #COMPTEXT2025 is still open until January 15! We are looking forward to receiving your proposals for papers, panels, and data presentations! We also appreciate it if you can spread the word and circulate shorturl.at/AmocX! See you at the University of Vienna on 24-26 April!
06.01.2025 14:15 β π 4 π 6 π¬ 0 π 3I'll get straight to the point.
We trained 2 new models. Like BERT, but modern. ModernBERT.
Not some hypey GenAI thing, but a proper workhorse model, for retrieval, classification, etc. Real practical stuff.
It's much faster, more accurate, longer context, and more useful. π§΅
Nice paper showing just *how* irreprodroducible research with proprietary generative LLMs is. Luckily there are open source alternatives (and they are very easy to use too!)
19.12.2024 07:23 β π 22 π 9 π¬ 1 π 0Call for abstracts for a Special Volume on Computational Social Science (of the journal "Soziale Welt")!
@marklutter345.bsky.social and I are looking for contributions presenting new research, discussing CSS methods, giving overviews of applications or ongoing research projects. Please circulate!
I read this paper a while back, and I liked it. But now it also feels relevant.
www.nber.org/papers/w29724
Run LLMs locally in R with the rollama R package. The latest update simplifies query generation (Prompt) and adds support for Hugging Face models (@jbgruber.bsky.social) Check it out:
09.12.2024 14:16 β π 8 π 2 π¬ 0 π 0hex logo of the rollama package
New #rstats π¦ version: {rollama} 0.2.0
What's new?π§΅π
https://cran.r-project.org/web/packages/rollama/index.html
If you find yourself with too much free time over the (long) weekend / holidays, I have ~3h Building an LLM from the Ground Up workshop on YouTube that may come in handy: m.youtube.com/watch?v=quh7...
27.11.2024 04:39 β π 184 π 28 π¬ 11 π 1