Raphael Costa

raphaelcosta's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a Space 10 days ago

Running

166

The ultimate guide to RL environments: building and scaling them in the LLM era

📝

166

Building and scaling RL environments for LLM training

liked 4 datasets 13 days ago

SALT-NLP/SWE-chat

Viewer • Updated 22 days ago • 2.73M • 4.17k • 52

hao-li/AIDev-v1.2

Viewer • Updated 12 days ago • 10.5M • 230 • 1

hao-li/AIDev-full

Viewer • Updated Mar 18 • 16.5M • 220 • 3

hao-li/AIDev

Viewer • Updated 11 days ago • 2.46M • 8.54k • 33

upvoted a collection 13 days ago

OpenThinker-Agent

Collection

5 items • Updated Dec 6, 2025 • 10

liked 6 datasets 13 days ago

open-thoughts/OpenThoughts-Agent-v1-RL

Viewer • Updated Jan 27 • 728 • 708 • 18

open-thoughts/OpenThoughts-TB-dev

Updated Dec 6, 2025 • 1.04k • 9

cdreetz/swe-grep-final

Viewer • Updated Feb 8 • 1k • 50 • 1

open-thoughts/AgentTrove

Viewer • Updated 14 days ago • 1.7M • 10.5k • 148

princeton-nlp/SWE-bench_Lite

Viewer • Updated Mar 3, 2025 • 323 • 101k • 60

13point5/swe-grep-oss-rl-debug-step20

Updated Nov 14, 2025 • 126 • 1

liked 2 models 13 days ago

Salesforce/SFR-Embedding-Code-2B_R

Feature Extraction • Updated Jan 28, 2025 • 2.35k • 49

chromadb/context-1

Text Generation • 21B • Updated Mar 30 • 1.28k • 406

liked a model 28 days ago

openai/privacy-filter

Token Classification • 1B • Updated 29 days ago • 306k • 1.49k

liked a dataset about 1 month ago

lightonai/embeddings-pre-training

Viewer • Updated Apr 16 • 1.38B • 7.45k • 44

liked a model about 1 month ago

OpenMed/OpenMed-PII-Portuguese-SnowflakeMed-Large-568M-v1

Token Classification • 0.6B • Updated Apr 20 • 1.62k • 9

upvoted a collection about 1 month ago

Portuguese PII and De-Identification

Collection

35 open-source Portuguese PII detection models. 54 entity types. Apache 2.0. • 31 items • Updated Apr 20 • 25

liked a model about 1 month ago

Hcompany/Holo3-35B-A3B

Image-Text-to-Text • 35B • Updated Apr 2 • 73.7k • 336

liked a model about 2 months ago

Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled

Image-Text-to-Text • 28B • Updated Apr 6 • 204k • • 2.85k