To what extent are we responsible for our content and how to create safer Spaces?
•
1
David Berenstein
davidberenstein1957
AI & ML interests
Everything NLP and knowledge graphs
Articles
Organizations
Posts
25
Post
354
You can now build a custom text classifier without days of human labeling!
👍 LLMs work reasonably well as text classifiers.
👎 They are expensive to run at scale and their performance drops in specialized domains.
👍 Purpose-built classifiers have low latency and can potentially run on CPU.
👎 They require labeled training data.
Combine the best of both worlds: the automatic labeling capabilities of LLMs and the high-quality annotations from human experts to train and deploy a specialized model.
Blog: https://huggingface.co/blog/sdiazlor/custom-text-classifier-ai-human-feedback
👍 LLMs work reasonably well as text classifiers.
👎 They are expensive to run at scale and their performance drops in specialized domains.
👍 Purpose-built classifiers have low latency and can potentially run on CPU.
👎 They require labeled training data.
Combine the best of both worlds: the automatic labeling capabilities of LLMs and the high-quality annotations from human experts to train and deploy a specialized model.
Blog: https://huggingface.co/blog/sdiazlor/custom-text-classifier-ai-human-feedback
Post
528
The Synthetic Data Generator now directly integrates with Argilla, so you can generate and curate your own high-quality datasets from pure natural language!
Up next -> include dataset generation for text classification.
Other suggestions? Let us know.
Space: argilla/synthetic-data-generator
Up next -> include dataset generation for text classification.
Other suggestions? Let us know.
Space: argilla/synthetic-data-generator
Collections
8
spaces
11
pinned
Running
18
🐥 🦙 🤗
Text To SQL Hub Datasets
pinned
Sleeping
🙌
Gradio Annotator - Text Classification Multi Label
pinned
Running
on
Zero
5
🦾💪🏽
Human Feedback Collector | Meta-Llama-3.1-8B-Instruct | (KTO)
LLM, chatbot, human-feedback
pinned
Running
on
Zero
11
🦾💪🏽
Human Feedback Collector | Meta-Llama-3.1-8B-Instruct | (DPO)
LLM, chatbot, human-feedback
Sleeping
✍
Argilla
Sleeping
2
🧹 🧼 🗑️
Hub Repo Cleaner
models
5
davidberenstein1957/text_classification_model_zero_shot
Text Classification
•
Updated
•
4
davidberenstein1957/ultra-feedback-dutch-cleaned-hq-spin-geitje-7b-ultra-sft_iter2
Text Generation
•
Updated
•
11
davidberenstein1957/ultra-feedback-dutch-cleaned-hq-spin-geitje-7b-ultra-sft_iter1
Text Generation
•
Updated
•
8
davidberenstein1957/ultra-feedback-dutch-cleaned-hq-spin-geitje-7b-ultra-sft_iter0
Text Generation
•
Updated
•
8
davidberenstein1957/phi-2-distilabeled-intel-orca-dpo
Updated
•
2
datasets
18
davidberenstein1957/my-distiset
Viewer
•
Updated
•
5
davidberenstein1957/test
Updated
davidberenstein1957/llm-human-feedback-collector-chat-interface-dpo
Preview
•
Updated
davidberenstein1957/llm-human-feedback-collector-chat-interface-kto
Preview
•
Updated
•
1
davidberenstein1957/image-generation-flux1-schnell
Viewer
•
Updated
•
15
davidberenstein1957/dataset-viber-chat-generation-preference-inference-endpoints-battle
Viewer
•
Updated
•
6
davidberenstein1957/dataset-viber-image-generation-preference-inference-endpoints-battle-flux
Viewer
•
Updated
•
11
davidberenstein1957/naturally_occurring_feedback_per_loading_mode
Viewer
•
Updated
•
524k
davidberenstein1957/rag-embeddings-relevance-similarity
Viewer
•
Updated
•
3.25k
davidberenstein1957/report-translation-feedback
Updated