Qwen models with custom class for bidirectional attention
Joao Coelho
jmvcoelho
·
AI & ML interests
None yet
Recent Activity
authored
a paper
5 days ago
Dwell in the Beginning: How Language Models Embed Long Documents for
Dense Retrieval
authored
a paper
5 days ago
DeepResearchGym: A Free, Transparent, and Reproducible Evaluation
Sandbox for Deep Research
Organizations
Collections
1
Papers
2
models
14
jmvcoelho/Qwen2.5-0.5B-bidirectional-attn-mntp
Updated
•
573
jmvcoelho/Qwen2.5-0.5B-bidirectional-attn
Updated
•
202
jmvcoelho/ad-classifier-v0.2
Text Classification
•
Updated
•
6
jmvcoelho/ad-classifier-v0.1
Text Classification
•
Updated
•
2
jmvcoelho/ad-classifier-v0.0
Text Classification
•
Updated
•
2
jmvcoelho/GPTNeoX-160m
Updated
•
1
•
1
jmvcoelho/pythia-160m-1024-marco-docs-bow-contrastive-pretrain
Updated
•
7
jmvcoelho/t5-base-marco-lm-pretrain-2048
Updated
•
1
jmvcoelho/t5-base-marco-crop-pretrain-2048
Updated
•
1
jmvcoelho/t5-base-marco-2048
Updated