arxiv:2410.01769
Zhenting Qi PRO
zhenting
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
30 days ago
Scaling Agent Learning via Experience Synthesis
updated
a collection
about 2 months ago
EvoLM Models
upvoted
a
paper
5 months ago
Beyond Context Limits: Subconscious Threads for Long-Horizon Reasoning
Organizations
models
122
zhenting/evolm-4B-320BT-cpt-MixedFW8FM42-sftep1-sampled500k_first100k_qwen7b-rlep8-last100k
4B
•
Updated
•
3
zhenting/evolm-4B-160BT-cpt-MixedFW8FM42-sftep32-sampled500k_first100k_qwen7b-rlep8-last100k
4B
•
Updated
•
4
zhenting/evolm-4B-160BT-cpt-MixedFW8FM42-sftep16-sampled500k_first100k_qwen7b-rlep8-last100k
4B
•
Updated
•
6
zhenting/evolm-4B-160BT-cpt-MixedFW8FM42-sftep8-sampled500k_first100k_qwen7b-rlep8-last100k
4B
•
Updated
•
2
zhenting/evolm-4B-160BT-cpt-MixedFW8FM42-sftep2-sampled500k_first100k_qwen7b-rlep8-last100k
4B
•
Updated
•
6
zhenting/evolm-4B-160BT-cpt-MixedFW8FM42-sftep1-sampled500k_first400k_qwen7b-rlep8-last100k
4B
•
Updated
•
6
zhenting/evolm-4B-160BT-cpt-MixedFW8FM42-sftep1-sampled500k_first200k_qwen7b-rlep8-last100k
4B
•
Updated
•
6
zhenting/evolm-4B-160BT-cpt-MixedFW8FM42-sftep1-sampled500k_first100k_qwen7b-rlep32-last100k
4B
•
Updated
•
5
zhenting/evolm-4B-160BT-cpt-MixedFW8FM42-sftep1-sampled500k_first100k_qwen7b-rlep8-last400k
4B
•
Updated
•
6
zhenting/evolm-4B-160BT-cpt-MixedFW8FM42-sftep1-sampled500k_first100k_qwen7b-rlep8-last300k
4B
•
Updated
•
4
datasets
0
None public yet