Four- and eight-loop ForesightLoop checkpoints pretrained on 6B tokens with a shared 0.6B backbone.
Zhaofeng Sun
thuEcstasy1
AI & ML interests
None yet
Recent Activity
updated a collection 4 days ago
ForesightLoop updated a collection 4 days ago
ForesightLoop published a model 6 days ago
thuEcstasy1/ForesightLoop-8Organizations
models 6
thuEcstasy1/ForesightLoop-8
Text Generation • 0.6B • Updated • 317
thuEcstasy1/ForesightLoop-4
Text Generation • 0.6B • Updated • 318
thuEcstasy1/rl-spec-image
Updated
thuEcstasy1/deepseek-r1-distill-qwen-1.5b-sparsesparse
Updated
thuEcstasy1/deepseek-r1-distill-qwen-1.5b-sparseRL
Updated
thuEcstasy1/DeepSeek-R1-Distill-Qwen-1.5B-GRPO
Updated
datasets 0
None public yet