Elpmis/Qwen3-0.6B-soft-thinking-last-token-naive-top-all
Feature Extraction • 0.6B • Updated • 3
CaoZS
Elpmis
AI & ML interests
None yet
Recent Activity
upvoted a paper about 2 months ago
Learning to Retrieve from Agent Trajectories upvoted a paper 4 months ago
DLLM-Searcher: Adapting Diffusion Large Language Model for Search AgentsOrganizations
None yet
models 9
Elpmis/Qwen3-0.6B-soft-thinking-last-token-naive-topk30
Feature Extraction • 0.6B • Updated • 5
Elpmis/Qwen3-0.6B-direct-embedding-last-token-naive
Feature Extraction • 0.6B • Updated • 2
Elpmis/Qwen3-0.6B-soft-thinking-last-token-PRL
Feature Extraction • 0.6B • Updated • 2
Elpmis/Qwen3-0.6B-soft-thinking-concept-mean-naive
Feature Extraction • 0.6B • Updated • 2
Elpmis/Qwen3-0.6B-soft-thinking-concept-mean-ICR
Feature Extraction • 0.6B • Updated • 3
Elpmis/Qwen3-0.6B-soft-thinking-concept-mean-ERL
Feature Extraction • 0.6B • Updated • 2
Elpmis/Qwen3-0.6B-vanilla
Feature Extraction • 0.6B • Updated • 2
Elpmis/Qwen3-0.6B-soft-thinking-last-token-naive
0.6B • Updated • 2