INSAIT-Institute/Aletheia-Train download history
INSAIT-Institute/Aletheia-Train is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 22 times (3 in the last 7 days), and 194 times in total. It ranks #454,929 among datasets by monthly downloads.
[📖 Paper] [💻 Code] [🤗 Models & Datasets] Aletheia: What Makes RLVR For Code Verifiers Tick? Multi-domain thinking verifiers trained via Reinforcement Learning with Verifiable Rewards (RLVR) are a cornerstone of modern post-training. However, their adoption in code generation has la
Models trained on Aletheia-Train
24 models list it as training data.
- mradermacher/RAFT-7B-i1-GGUF 1.8K downloads in 30 days
- mradermacher/RAFT-7B-GGUF 534 downloads in 30 days
- mradermacher/RAFT-14B-i1-GGUF 399 downloads in 30 days
- mradermacher/RAFT-1.5B-i1-GGUF 178 downloads in 30 days
- mradermacher/RAFT-1.5B-GGUF 171 downloads in 30 days
- mradermacher/RAFT-14B-GGUF 137 downloads in 30 days
- INSAIT-Institute/GRPO-Instruct-1.5B 30 downloads in 30 days
- INSAIT-Institute/RAFT-7B 29 downloads in 30 days
- INSAIT-Institute/GRPO-Think-1.5B-8k 28 downloads in 30 days
- INSAIT-Institute/RAFT-14B 15 downloads in 30 days
- INSAIT-Institute/RAFT-1.5B 15 downloads in 30 days
- INSAIT-Institute/GRPO-Think-1.5B-16k 12 downloads in 30 days
Open INSAIT-Institute/Aletheia-Train on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.