Downloads · 30 days
0
Lyric1010/Qwen3-4B-megatron
Qwen3-4B-megatron is a machine learning model from Lyric1010. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This is a model uploaded from /mnt/nanjingcephfs/projectwx-rec-alg-bdc-exp/bwzheng/yulan/hyw/Ubiquant-Pretrain/build/wjp-share/outputmcoreqwen3formalpretrain/checkpoint/2025.10.15-22.06.42-pretrain-mcore-qwen3-moe-meg…
Downloads · 30 days
0
Access
Public
Updated Oct 16, 2025
Repo size
183 KB
Likes
0
Public
Click a slice to open those files.
Other160 KB · 87%
From the Hugging Face model README
This is a model uploaded from /mnt/nanjingcephfs/project_wx-rec-alg-bdc-exp/bwzheng/yulan/hyw/Ubiquant-Pretrain/build/wjp-share/output_mcore_qwen3_formal_pretrain/checkpoint/2025.10.15-22.06.42-pretrain-mcore-qwen3-moe-megatron-4B-lr-1e-5-minlr-1e-6-bs-1-gbs-512-seqlen-8192-pr-bf16-tp-1-pp-1-cp-1-ac-sel-do-true-sp-false-ti-2384-wi-238/iter_0000238.