meng zhangyuan
DaleMeng
·
AI & ML interests
None yet
Organizations
Intern-S1-pro transformers versions
2
#4 opened 2 months ago
by
DaleMeng
behavior between GptOssExperts and Mxfp4GptOssExperts
#77 opened 8 months ago
by
DaleMeng
self_attn.k_proj.bias are all 0 for all layers
2
#50 opened 9 months ago
by
DaleMeng
reward for Non-Verifiable Queries
#12 opened 10 months ago
by
DaleMeng