ziyuanyang86/llama3_grpo
Updated
ziyuan yang
ziyuanyang86
AI & ML interests
None yet
Recent Activity
published a model 3 days ago
ziyuanyang86/llama3_grpo updated a model 13 days ago
ziyuanyang86/4b_prefixwrong published a model 13 days ago
ziyuanyang86/4b_prefixwrongOrganizations
None yet
ziyuanyang86/4b_prefixwrong
4B • Updated • 37
ziyuanyang86/1.7b_prefixwrong
2B • Updated • 26
ziyuanyang86/4b_wrongbox
4B • Updated • 47
ziyuanyang86/1.7b_wrongbox
2B • Updated • 37
ziyuanyang86/1.7b_misconcept
2B • Updated • 32
ziyuanyang86/4b_misconcept
4B • Updated • 36
ziyuanyang86/4b_reason_llm
4B • Updated • 29
ziyuanyang86/4b_diversity_llm
4B • Updated • 33
ziyuanyang86/4b_sft
Text Generation • 4B • Updated • 8
ziyuanyang86/4b_cuts
4B • Updated • 6
ziyuanyang86/4b_sft_then_rl
4B • Updated • 6
ziyuanyang86/qwen3_8b_math_grpo
8B • Updated • 3
ziyuanyang86/malicious_sft_knowledge
Updated
ziyuanyang86/malicious_sft_code
Updated
ziyuanyang86/malicious_sft_if
Updated
ziyuanyang86/malicious_sft_math
Updated
ziyuanyang86/malicious_sft_safe
Updated
ziyuanyang86/qwen7bi-grpo-malicious
8B • Updated • 6 • 1
ziyuanyang86/qwen7bi-tuluv3-python
8B • Updated • 5
ziyuanyang86/qwen7bi-tuluv3-math
8B • Updated • 8 • 1
ziyuanyang86/qwen7bi-tuluv3-if
8B • Updated • 7
ziyuanyang86/qwen7bi-tuluv3-coconot
8B • Updated • 5 • 1
ziyuanyang86/qwen7bi-oasst1
8B • Updated • 5
ziyuanyang86/qwen7bi-flanv2
8B • Updated • 7