Article
Welcome Gemma 4: Frontier multimodal intelligence on device
- +5
•
376
Maarten Grootendorst
MaartenGr
AI & ML interests
None yet
Recent Activity
upvoted an article about 22 hours ago
Welcome Gemma 4: Frontier multimodal intelligence on device updated a model 1 day ago
google/gemma-4-26B-A4B-it updated a model 1 day ago
google/gemma-4-26B-A4BOrganizations
upvoted an article about 22 hours ago
updated 8
models 1 day ago
google/gemma-4-26B-A4B-it
Image-Text-to-Text • 27B • Updated • 24.4k • • 264
google/gemma-4-26B-A4B
Image-Text-to-Text • 27B • Updated • 4.9k • 100
google/gemma-4-31B-it
Image-Text-to-Text • 33B • Updated • 76.2k • • 597
google/gemma-4-31B
Image-Text-to-Text • 33B • Updated • 4.62k • 157
google/gemma-4-E4B-it
Any-to-Any • 8B • Updated • 23.5k • 222
google/gemma-4-E2B-it
Any-to-Any • 5B • Updated • 31.7k • 174
google/gemma-4-E4B
Any-to-Any • 8B • Updated • 2.77k • 69
google/gemma-4-E2B
Any-to-Any • 5B • Updated • 11.4k • 75
commentedon Introducing BERTopic Integration with the Hugging Face Hub about 1 year ago
The process should be similar, especially considering you can download the model and run it through any API that you want. There are many options to choose from though, ranging from GPU-acceleration (e.g., cuML) or CPU-focused applications (e.g., Model2Vec).
reactedto asoria's post with ❤️ over 1 year ago
Post
2166
🚀 Exploring Topic Modeling with BERTopic 🤖
When you come across an interesting dataset, you often wonder:
Which topics frequently appear in these documents? 🤔
What is this data really about? 📊
Topic modeling helps answer these questions by identifying recurring themes within a collection of documents. This process enables quick and efficient exploratory data analysis.
I’ve been working on an app that leverages BERTopic, a flexible framework designed for topic modeling. Its modularity makes BERTopic powerful, allowing you to switch components with your preferred algorithms. It also supports handling large datasets efficiently by merging models using the BERTopic.merge_models approach. 🔗
🔍 How do we make this work?
Here’s the stack we’re using:
📂 Data Source ➡️ Hugging Face datasets with DuckDB for retrieval
🧠 Text Embeddings ➡️ Sentence Transformers (all-MiniLM-L6-v2)
⚡ Dimensionality Reduction ➡️ RAPIDS cuML UMAP for GPU-accelerated performance
🔍 Clustering ➡️ RAPIDS cuML HDBSCAN for fast clustering
✂️ Tokenization ➡️ CountVectorizer
🔧 Representation Tuning ➡️ KeyBERTInspired + Hugging Face Inference Client with Meta-Llama-3-8B-Instruct
🌍 Visualization ➡️ Datamapplot library
Check out the space and see how you can quickly generate topics from your dataset: datasets-topics/topics-generator
Powered by @MaartenGr - BERTopic
When you come across an interesting dataset, you often wonder:
Which topics frequently appear in these documents? 🤔
What is this data really about? 📊
Topic modeling helps answer these questions by identifying recurring themes within a collection of documents. This process enables quick and efficient exploratory data analysis.
I’ve been working on an app that leverages BERTopic, a flexible framework designed for topic modeling. Its modularity makes BERTopic powerful, allowing you to switch components with your preferred algorithms. It also supports handling large datasets efficiently by merging models using the BERTopic.merge_models approach. 🔗
🔍 How do we make this work?
Here’s the stack we’re using:
📂 Data Source ➡️ Hugging Face datasets with DuckDB for retrieval
🧠 Text Embeddings ➡️ Sentence Transformers (all-MiniLM-L6-v2)
⚡ Dimensionality Reduction ➡️ RAPIDS cuML UMAP for GPU-accelerated performance
🔍 Clustering ➡️ RAPIDS cuML HDBSCAN for fast clustering
✂️ Tokenization ➡️ CountVectorizer
🔧 Representation Tuning ➡️ KeyBERTInspired + Hugging Face Inference Client with Meta-Llama-3-8B-Instruct
🌍 Visualization ➡️ Datamapplot library
Check out the space and see how you can quickly generate topics from your dataset: datasets-topics/topics-generator
Powered by @MaartenGr - BERTopic
Hi! Thank you for reaching out. I generally like to keep the post either on my newsletter or Medium where I have both gained some followers.
Having said that, I would be open to a collaboration with HF to publish it. Due to the time spent on this guide, it would need to be more than just publishing it as a community blog.
What is the training benchmark for model `BERTopic_Wikipedia`
1
#3 opened about 2 years ago
by 
benjaminliupenrose
How to merge topics for model `BERTopic_Wikipedia`
1
#2 opened about 2 years ago
by benjaminliupenrose
updated a
dataset about 2 years ago
authored a
paper about 2 years ago
Inference API err: HfApiJson Deserialize Error
2
#1 opened almost 3 years ago
by 
ongkn
updated 2
models almost 3 years ago
published an article almost 3 years ago
Article
Introducing BERTopic Integration with the Hugging Face Hub
•
10