In a Training Loop 🔄

16 20 36

Constantin

Alexandre-Numind

https://www.numind.ai/

AI & ML interests

Training AI models @Numind

Recent Activity

updated a collection 2 days ago

Base Qwen

updated a collection 5 days ago

Base Qwen

updated a collection 5 days ago

Base Qwen

View all activity

Organizations

updated a collection 2 days ago

Base Qwen

Collection

6 items • Updated 2 days ago

updated a collection 5 days ago

Base Qwen

Collection

6 items • Updated 2 days ago

published 2 models 7 days ago

Alexandre-Numind/v2-large

Text Generation • 9B • Updated Sep 11, 2024 • 10

Alexandre-Numind/v2-large-20000

Text Generation • 9B • Updated Sep 11, 2024 • 9

upvoted a paper 16 days ago

Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning

Paper • 2603.04597 • Published 28 days ago • 210

upvoted an article 22 days ago

Article

From GRPO to DAPO and GSPO: What, Why, and How

Aug 9, 2025

•

108

liked a model about 1 month ago

Qwen/Qwen3.5-9B

Image-Text-to-Text • 10B • Updated about 1 month ago • 4.68M • • 1.12k

New activity in Qwen/Qwen3.5-35B-A3B about 1 month ago

I would like a recommended training environment setup for the Qwen3.5-MoE model (e.g., Qwen3.5-35B-A3B, model_type: qwen3_5_moe).

👍 1

#16 opened about 1 month ago by

444515liuxin

upvoted a paper about 2 months ago

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

Paper • 2601.22975 • Published Jan 30 • 110

Constantin

AI & ML interests

Recent Activity

Organizations

Alexandre-Numind's activity

From GRPO to DAPO and GSPO: What, Why, and How

I would like a recommended training environment setup for the Qwen3.5-MoE model (e.g., Qwen3.5-35B-A3B, model_type: qwen3_5_moe).