lhl616/Qwen3-4B-Base-axon-error-aware-128-8-dense-0.5-0.8-split-new-step2
4B • Updated
Haolin Liu
lhl616
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 month ago
Training Data Efficiency in Multimodal Process Reward Models upvoted a paper about 1 month ago
Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing upvoted a paper 2 months ago
RelayLLM: Efficient Reasoning via Collaborative Decoding Organizations
None yet
lhl616/Qwen3-4B-Base-axon-error-aware-128-8-dense-0.5-0.8-random_fixed
4B • Updated
lhl616/Qwen3-4B-Base-axon-error-aware-128-8-dense-0.5-0.8-parial
4B • Updated
lhl616/Qwen3-4B-Base-axon-error-aware-128-8-dense-0.5-0.8-normal-fixed-denominator
4B • Updated
lhl616/Qwen3-4B-Base-axon-error-aware-128-8-dense-0.5-0.8-normal
4B • Updated
lhl616/Qwen3-4B-Base-axon-error-aware-128-8-dense-0.5-0.8-c
4B • Updated
lhl616/Qwen3-4B-Base-axon-error-aware-128-8-dense
4B • Updated
lhl616/Qwen2.5-7B-axon-grpo-step-128-8-4096
8B • Updated
lhl616/Qwen2.5-7B-axon-grpo-nstd-step-128-8-4096
8B • Updated
lhl616/Qwen2.5-7B-axon-error-aware-128-8-ratio-new
8B • Updated
lhl616/Qwen2.5-7B-axon-error-aware-128-8-ratio
8B • Updated
lhl616/Qwen2.5-7B-axon-error-aware-128-8-passk
8B • Updated
lhl616/Qwen2.5-7B-axon-error-aware-128-8-mixed-new
8B • Updated
lhl616/Qwen2.5-7B-axon-error-aware-128-8-dense-nstd-0.5-0.8-start
8B • Updated
lhl616/Qwen2.5-7B-axon-error-aware-128-8-dense-nstd-0.5-0.8-normal
8B • Updated
lhl616/Qwen2.5-7B-axon-error-aware-128-8-dense-0.5-0.8-start
8B • Updated
lhl616/Qwen2.5-7B-axon-error-aware-128-8-dense-0.5-0.8-normal
8B • Updated
lhl616/Llama-3.2-3B-Instruct-nstd-start-relu
3B • Updated
• 1
lhl616/Llama-3.2-3B-Instruct-grpo-nstd-new
3B • Updated
• 1
lhl616/Llama-3.2-3B-Instruct-axon-grpo-step-128-8
3B • Updated
• 1
lhl616/Llama-3.2-3B-Instruct-axon-error-aware-grpo-128-8
3B • Updated
• 1
lhl616/Llama-3.2-3B-Instruct-axon-error-aware-128-8-ratio-new
3B • Updated
• 1
lhl616/Llama-3.2-3B-Instruct-axon-error-aware-128-8-mixed-new
3B • Updated
• 1
lhl616/Llama-3.2-3B-Instruct-axon-error-aware-128-8-dense-std-relu-0.5-0.8-start
3B • Updated
• 1
lhl616/Llama-3.2-3B-Instruct-axon-error-aware-128-8-dense-std-0.5-0.8-start
3B • Updated
• 1
lhl616/Llama-3.2-3B-Instruct-axon-error-aware-128-8-dense-nstd-0.5-0.8-start
3B • Updated
• 1
lhl616/Llama-3.2-3B-Instruct-axon-error-aware-128-8-dense-nstd-0.5-0.8-new-relu
3B • Updated
• 1