Alonso Silva
@alonsosilva.bsky.social
AI Researcher @ Nokia Bell Labs. Interested on Large Language Models (LLMs), Machine Learning and Data Analysis.
🐍 New Python package just dropped! Generate Mermaid diagrams directly from Python code. Simple, fast & powerful. 🔥 #Python #Mermaid #OpenSource
![Code to generate a Mermaid diagram
Input cell 1: %pip install mermaid-nb
Input cell 2:
from mermaid_nb import Mermaid
Mermaid(
diagram="""
flowchart LR
A[Start] --> B{Decision}
B -->|Yes| C[Continue]
B -->|No| D[Stop]
""",
theme="forest",
look="handDrawn",
theme_variables={"nodeTextColor": "#0000ff", "fontFamily": "Caveat, cursive"}
)](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:bkqjfuo5jlg5oki6a7bixcud/bafkreiet4hnbom2srkbpby42zbloajihuc4pfphv2p7k6evdbznzrqxaze)
Pandas 3.0 was just released yesterday!! 🤘 And guess what? You can already play with it in Notebook.link. I quickly built a Notebook.link link for you to play with it now: notebook.link/@martinRenou...
Notebook Link
notebook.link
If you are (or know of) a Master's or PhD student looking for an internship, I am proposing the subject: 'Efficient Structured Generation with Grammar-Aware Sampling Techniques.' www.dropbox.com/scl/fi/7iwfg... If you're passionate about structured generation, feel free to reach out!
dropbox.com
Litelines got added to the Awesome LLM constrained decoding repo 😊 It’s great to share this space with more established libraries like Outlines, XGrammar, or Guidance. Link to the Awesome LLM constrained repo: github.com/Saibo-creato... Link to litelines: alonsosilvaallende.github.io/litelines/
You can display SQLite database diagrams in @marimo.io using `fastlite` and `graphviz`. Here is a basic molab notebook to play online: molab.marimo.io/notebooks/nb... Here is my merged PR 🙂 github.com/marimo-team/...
marimo @marimo.io now supports graphviz Here is a basic notebook to play online: molab.marimo.io/notebooks/nb... Here is my merged PR 🙂 github.com/marimo-team/...
Batch processing using transformers and litelines libraries. In this video, I process 900 prompts in 30 seconds with an RTX A4000 with 16GB of VRAM. www.youtube.com/watch?v=7hVU...
Batch processing using transformers and litelines libraries
YouTube video by Alonso Silva
youtube.com
The new litelines release should work much better in marimo notebooks. You can try it in a marimo molab: molab.marimo.io/notebooks/nb... Here is litelines documentation: alonsosilvaallende.github.io/litelines/ Here is the release changelog: github.com/alonsosilvaa...
How is it possible that a 1.7 billion parameter model succeeds where a model with hundreds or thousands of billions of parameters fails? www.youtube.com/watch?v=wmgw...
Qwen3-1.7B beating GPT-4o at a lipogram task
YouTube video by Alonso Silva
youtube.com
The latest release of Litelines supports batch processing for Transformers library. `pip install --upgrade litelines` Here is a colab to get started: huggingface.co/datasets/alo... And here is the library documentation: alonsosilvaallende.github.io/litelines/
My talk, "Processors for Language Models," at PyData Paris 2025 is now available. I discuss my personal project, Litelines, as well as common libraries used to transform unstructured data into structured data. Link to the video: www.youtube.com/watch?v=VP4I...
Lightning talks - session 1
YouTube video by PyData
youtube.com
I gave a talk about structured code generation for domain-specific languages: Abstract Syntax Trees (ASTs), Concrete Syntax Trees (CSTs), Deterministic Finite Automata (DFA), Regular Expressions (Regex), Pushdown Automata (PA), Context-Free Grammars (CFGs), outlines, guidance, Georges Perec, etc.
Here are the starting notebooks I presented at @pydataparis.bsky.social tinyurl.com/litelines-hf And here is the documentation of litelines: tinyurl.com/litelines #PyDataParis
alonsosilva/litelines-notebooks at main
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
tinyurl.com
Featured in marimo newsletter 🤩 marimo.io/blog/newslet...
Alonso Silva@alonsosilva.bsky.social · 11mo agoWant to visualize the response format constraints on the LLM when working in a Jupyter notebook? Then you might be interested in my new project `litelines`. Litelines lets you visualize the selected path by the LLM. It supports a Pydantic schema as a response format, as well as regular expressions.
Doing a slightly better documentation than just the README.md alonsosilvaallende.github.io/litelines/ge... Feeback?
Alonso Silva@alonsosilva.bsky.social · 11mo agoWant to visualize the response format constraints on the LLM when working in a Jupyter notebook? Then you might be interested in my new project `litelines`. Litelines lets you visualize the selected path by the LLM. It supports a Pydantic schema as a response format, as well as regular expressions.
Want to visualize the response format constraints on the LLM when working in a Jupyter notebook? Then you might be interested in my new project `litelines`. Litelines lets you visualize the selected path by the LLM. It supports a Pydantic schema as a response format, as well as regular expressions.
The recording of my presentation "Certainty-Guided Reasoning: A Dynamic Thinking Budget Approach" at the Laboratory for Information, Networking and Communication Sciences (LINCS) is now available: www.youtube.com/watch?v=8a44...
Certainty-Guided Reasoning in Large Language Models: A Dynamic Thinking Budget Approach
YouTube video by Pupusse LINCS
youtube.com
New blog post: Constrain a language model not to use the letter 'e' alonsosilvaallende.github.io/blog/posts/2... In this post, I constrain a small language model (0.6B parameters) with a logits processor to accomplish something GPT-4o fails to do (see chatgpt.com/share/687908...).
TIL how to add notebook cells running on @pyodide.org to Quarto projects, such as my blog: alonsosilvaallende.github.io/til/posts/20... It's very easy to change the Pyodide version if needed. Thanks @coatless.bsky.social for this great Quarto extension
New blog post: Understanding Logits Processors alonsosilvaallende.github.io/blog/posts/2... I start with a basic min length example, then force the model to check its answer, followed by making reasoning models stop thinking once they reach a thinking budget & finally force the model to think longer
New blog post: Understanding Structured Outputs alonsosilvaallende.github.io/blog/posts/2... This is the power behind structured ouputs libraries such as Instructor and Marvin. I provide a basic example of extraction, a slightly more complex one, then classification, and finally SO in WebAssembly.
New blog post: Understanding Function Calling I provide a basic example of FC, then a slightly more complex example by allowing an LM to use Python. I explain the conversational response as a tool trick. Finally, FC in the browser by using WebAssembly alonsosilvaallende.github.io/blog/posts/2...
So I appear in the Celebration of 100 years of Bell Labs video with our LLM robots (a.k.a. IndustrialGPT) for less than a second :-D www.youtube.com/watch?v=Fu_I...
New blog post: Understanding LLM Memory alonsosilvaallende.github.io/blog/posts/2... Using the Marimo extension for Quarto.
