ecco
by jalammar (personal account)
Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, BERT, RoBERTA, T5, and T0). (description from the project’s GitHub page)
Repository facts
- Stars
- 2,104
- Forks
- 174
- Open issues and pull requests
- 38
- Primary language
- Jupyter Notebook
- License
- BSD 3-Clause "New" or "Revised" License (BSD-3-Clause)
- Owner
- jalammar · Personal account
- Created
- Nov 7, 2020
- Last push
- Aug 15, 2024
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 8,119: webis-de/small-text
Active Learning for Text Classification in Python
647 starsPythonMITLast push Oct 12, 2026
Rank 998: jessevig/bertviz
BertViz: Visualize Attention in Transformer Models
8,200 starsPythonApache-2.0Last push Jan 8, 2026
Rank 6,090: zjunlp/Prompt4ReasoningPapers
[ACL 2023] Reasoning with Language Model Prompting: A Survey
1,009 starsMITLast push May 21, 2025
Rank 6,220: kennethleungty/Llama-2-Open-Source-LLM-CPU-Inference
Running Llama 2 and other Open-Source LLMs on CPU Inference Locally for Document Q&A
971 starsPythonMITLast push Nov 6, 2023
Rank 9,068: EricFillion/happy-transformer
Happy Transformer makes it easy to fine-tune and perform inference with NLP Transformer models.
545 starsPythonApache-2.0Last push Jan 10, 2026
Rank 3,224: JasonKessler/scattertext
Beautiful visualizations of how language differs among document types.
2,344 starsPythonApache-2.0Last push Jul 4, 2026