Hugging Face's logo

Librarian Bots

community
Activity Feed

AI & ML interests

None defined yet.

Recent Activity

davanstrien  updated a dataset about 4 hours ago
librarian-bots/model_cards_with_metadata
librarian-bot  new activity about 5 hours ago
librarian-bots/dataset-to-model-monitor:Discussion tracking new models trained on HuggingFaceH4/ultrachat_200k
davanstrien  updated a dataset about 14 hours ago
librarian-bots/dataset_cards_with_metadata
View all activity

librarian-bots's activity

davanstrien 
updated a dataset about 4 hours ago
librarian-bot 
in librarian-bots/dataset-to-model-monitor about 5 hours ago

Discussion tracking new models trained on HuggingFaceH4/ultrachat_200k

418
#15 opened over 1 year ago by
librarian-bot
davanstrien 
updated a dataset about 14 hours ago
librarian-bot 
updated a dataset about 15 hours ago
davanstrien 
updated a dataset about 15 hours ago
librarian-bot 
in librarian-bots/dataset-to-model-monitor about 17 hours ago

Discussion tracking new models trained on google/fleurs

188
#6 opened over 1 year ago by
librarian-bot
davanstrien 
posted an update about 23 hours ago
view post
Post
1446
Hacked together a way to log trl GRPO training completions to a 🤗 dataset repo. This allows you to:

- Track rewards from multiple reward functions
- Treat the completion and rewards from training as a "proper" dataset and do EDA
- Share results for open science

The implementation is super hacky, but I'm curious if people would find this useful.

To push completions to the Hub, you just need two extra parameters:

log_completions=True
log_completions_hub_repo='your-username/repo-name'

Example dataset: davanstrien/test-logs
Colab: https://colab.research.google.com/drive/1wzBFPVthRYYTp-mEYlznLg_e_0Za1M3g
librarian-bot 
in librarian-bots/dataset-to-model-monitor 1 day ago

Discussion tracking new models trained on hkust-nlp/CodeIO-PyEdu-Reasoning
#81 opened 1 day ago by
librarian-bot

Discussion tracking new models trained on HuggingFaceH4/ultrafeedback_binarized

426
#37 opened about 1 year ago by
librarian-bot
librarian-bot 
in librarian-bots/dataset-to-model-monitor 2 days ago

Discussion tracking new models trained on LDJnr/Capybara

238
#33 opened about 1 year ago by
librarian-bot

Discussion tracking new models trained on HuggingFaceH4/no_robots

116
#18 opened over 1 year ago by
librarian-bot
librarian-bot 
in librarian-bots/dataset-to-model-monitor 3 days ago

Discussion tracking new models trained on nvidia/HelpSteer

143
#21 opened about 1 year ago by
librarian-bot
librarian-bot 
in librarian-bots/dataset-to-model-monitor 4 days ago

Discussion tracking new models trained on argilla/databricks-dolly-15k-curated-multilingual

1
#77 opened about 1 month ago by
librarian-bot

Discussion tracking new models trained on imdb

194
#1 opened over 1 year ago by
librarian-bot

Discussion tracking new models trained on OpenAssistant/oasst1

99
#7 opened over 1 year ago by
librarian-bot
davanstrien 
updated a dataset 4 days ago
davanstrien 
posted an update 5 days ago
davanstrien 
posted an update 7 days ago
view post
Post
1825
How do you make 1M+ Hugging Face models & datasets more discoverable?

davanstrien/Smol-Hub-tldr!

I fine-tuned HuggingFaceTB/SmolLM2-360M to generate one-line summaries from a model or dataset README.

Its own self-description?
"A model for generating concise summaries of model & dataset cards from the Hugging Face Hub"

The goal? Make it easier to find the right models and datasets for your specific needs. It's already powering a semantic search for datasets Space.

It's still a WIP but thanks to @loubnabnl , @anton-l , @eliebak et al, for cooking such a nice base model for fine-tuning small, efficient models for specific domains and tasks. 🙏
davanstrien 
posted an update 8 days ago
davanstrien 
posted an update 23 days ago