David Berenstein's picture

David Berenstein

davidberenstein1957

·

AI & ML interests

Everything NLP and knowledge graphs

Recent Activity

reacted to elliesleightholm's post with 🤗 about 1 hour ago

reacted to jsulz's post with 🧠 about 2 hours ago

reacted to jsulz's post with 🔥 about 2 hours ago

Articles

🤗🔭 Introducing Observers: A Lightweight SDK for AI Observability 🔭🤗

about 3 hours ago

How to build a custom text classifier without days of human labeling

How to optimize your data labelling project with custom interfaces

To what extent are we responsible for our content and how to create safer Spaces?

Data Is Better Together: A Look Back and Forward

Organizations

Posts 30

Post

145

🤗🔭 Introducing Observers: A Lightweight SDK for AI Observability 🔭🤗

Observers is an open-source Python SDK that provides comprehensive observability for AI applications. Our library makes it easy to:

- Track and record interactions with AI models
- Store observations in multiple backends
- Query and analyse your AI interactions with ease

https://huggingface.co/blog/davidberenstein1957/observers-a-lightweight-sdk-for-ai-observability

Post

1795

For anyone who struggles with NER or information extraction with LLM.

We showed an efficient workflow for token classification including zero-shot suggestions and model fine-tuning with Argilla, GliNER, the NuMind NuExtract LLM and SpanMarker. @argilla

Video: https://youtu.be/JvLpaYgNd84?feature=shared
Notebooks and slides included to try it yourself 🙂

Collections 8

spaces 12

Vectorsearch Hub Datasets

Add vectors to Hub datasets and do in memory vector search.

Text To SQL Hub Datasets

Human Feedback Collector | Meta-Llama-3.1-8B-Instruct | (KTO)

LLM, chatbot, human-feedback

Running on Zero

Human Feedback Collector | Meta-Llama-3.1-8B-Instruct | (DPO)

LLM, chatbot, human-feedback

No application file

Docs2datasets

📚 👉 🗂️ Docs (PDF, DOC, PPT, Images, HTML, MD) to datasets

Argilla

models 5

davidberenstein1957/text_classification_model_zero_shot

Text Classification • Updated Oct 10 • 3

davidberenstein1957/ultra-feedback-dutch-cleaned-hq-spin-geitje-7b-ultra-sft_iter2

Text Generation • Updated Apr 28 • 10

davidberenstein1957/ultra-feedback-dutch-cleaned-hq-spin-geitje-7b-ultra-sft_iter1

Text Generation • Updated Apr 19 • 7

davidberenstein1957/ultra-feedback-dutch-cleaned-hq-spin-geitje-7b-ultra-sft_iter0

Text Generation • Updated Apr 4 • 7

davidberenstein1957/phi-2-distilabeled-intel-orca-dpo

Updated Jan 24 • 4

datasets 21

davidberenstein1957/openai_records

Viewer • Updated about 5 hours ago • 1 • 3

davidberenstein1957/llm-human-feedback-collector-chat-interface-dpo

Viewer • Updated 2 days ago • 84 • 89

davidberenstein1957/my-distiset

Viewer • Updated 2 days ago • 10 • 62

davidberenstein1957/img_prefs_style

Viewer • Updated 2 days ago • 1 • 6

davidberenstein1957/llama-index-test

Viewer • Updated 5 days ago • 44 • 4 • 1

davidberenstein1957/llm-human-feedback-collector-chat-interface-kto

Viewer • Updated 8 days ago • 12 • 18 • 1

davidberenstein1957/image-generation-flux1-schnell

Viewer • Updated 14 days ago • 26 • 235

davidberenstein1957/test

Updated Oct 3 • 36

davidberenstein1957/dataset-viber-chat-generation-preference-inference-endpoints-battle

Viewer • Updated Aug 29 • 6 • 64

davidberenstein1957/dataset-viber-image-generation-preference-inference-endpoints-battle-flux

Viewer • Updated Aug 22 • 11 • 153