wang

howtain

·

AI & ML interests

None yet

Organizations

New activity in deepseek-ai/DeepSeek-V4-Flash 2 months ago

support inference by sglang or vllm ?

#2 opened 2 months ago by

New activity in zai-org/GLM-4.7-Flash 5 months ago

open Tau^2 benchmark codebase?

#33 opened 5 months ago by

New activity in Agent-Ark/Toucan-1.5M 8 months ago

bfcl v3 evaluation parameter?

#6 opened 8 months ago by

New activity in baidu/ERNIE-4.5-21B-A3B-Thinking 10 months ago

Stop Faking Download Counts

#6 opened 10 months ago by

New activity in a-m-team/AM-DeepSeek-R1-0528-Distilled 11 months ago

教师模型是 AM-DeepSeek-R1-0528还是 DeepSeek-R1-0528？

#11 opened 11 months ago by

New activity in miromind-ai/MiroVerse-v0.1 11 months ago

Any benchmark scores?

#1 opened 11 months ago by

New activity in a-m-team/AM-DeepSeek-R1-0528-Distilled 12 months ago

verify_score的计算方法是什么？

#9 opened 12 months ago by

New activity in a-m-team/AM-DeepSeek-R1-0528-Distilled about 1 year ago

What's the context length for SFT tuning?

#7 opened about 1 year ago by

New activity in allenai/IF_multi_constraints_upto5 about 1 year ago

verify tools ？

#1 opened about 1 year ago by

New activity in a-m-team/AM-DeepSeek-R1-0528-Distilled about 1 year ago

什么叫中国速度！

#1 opened about 1 year ago by

Discovered a very strange problem

#5 opened about 1 year ago by

New activity in a-m-team/AM-Thinking-v1-Distilled about 1 year ago

Which model is AM-Deepseek-R1-0528?

#4 opened about 1 year ago by

New activity in OpenBuddy/OpenBuddy-R1-0528-Distill-Qwen3-32B-Preview0-QAT about 1 year ago

AIME or other benchmark score？

#3 opened about 1 year ago by

New activity in a-m-team/AM-Thinking-v1-gguf about 1 year ago

Weird output without the system

#1 opened about 1 year ago by

New activity in a-m-team/AM-DeepSeek-R1-Distilled-1.4M over 1 year ago

Where are the difficulty and category of the data?

#8 opened over 1 year ago by