·
AI & ML interests
LLMs
Organizations
None yet
ZHLiu627/sokoban-GRPO-from-webshop-Llama-3.2-3B-Instruct-45step
8B • Updated • 1
ZHLiu627/verl-agent-sciworld-GRPO-kl0.01-from-sft-step100-Llama-3.2-3B-Instruct-nt-90step
4B • Updated • 1
ZHLiu627/verl_agent_webshop-new-GRPO-kl0.01-from-sft-step-Llama-3.2-3B-Instruct-old_repo-45step
4B • Updated • 1
ZHLiu627/verl_agent_alfworld-GRPO-kl-0.01-from-webshop-20step-v2-Llama-3.1-8B-Instruct-info5-30step
8B • Updated • 1
ZHLiu627/sokoban-GRPO-from-webshop-Llama-3.2-3B-Instruct-30step
8B • Updated • 1
ZHLiu627/verl-agent-sciworld-GRPO-kl0.01-from-sft-step100-Llama-3.2-3B-Instruct-nt-75step
4B • Updated • 1
ZHLiu627/verl_agent_webshop-new-GRPO-kl0.01-from-sft-step-Llama-3.2-3B-Instruct-old_repo-30step
4B • Updated • 1
ZHLiu627/sokoban-GRPO-from-webshop-Llama-3.2-3B-Instruct-15step
8B • Updated • 1
ZHLiu627/verl_agent_alfworld-GRPO-kl-0.01-from-webshop-20step-v2-Llama-3.1-8B-Instruct-info5-15step
8B • Updated • 1
ZHLiu627/verl-agent-sciworld-GRPO-kl0.01-from-sft-step100-Llama-3.2-3B-Instruct-nt-60step
4B • Updated • 1
ZHLiu627/verl_agent_webshop-new-GRPO-kl0.01-from-sft-step-Llama-3.2-3B-Instruct-old_repo-15step
4B • Updated • 1
ZHLiu627/sciworld_dataset
Updated
ZHLiu627/sciworld_sciworld_Llama-3.1-8B-Instruct_self_reflection_v4
Updated
ZHLiu627/sciworld_self-reflect_v2_sciworld_Llama-3.2-3B-Instruct
4B • Updated • 2
ZHLiu627/sciworld_self-reflect_v4_sciworld_Qwen2.5-7B-Instruct
8B • Updated • 1
ZHLiu627/sciworld_self-reflect_v4_sciworld_Llama-3.1-8B-Instruct
8B • Updated • 1
ZHLiu627/sciworld_worldmodels2_sciworld_Llama-3.1-8B-Instruct
8B • Updated • 1
ZHLiu627/sciworld_worldmodels2_sciworld_Qwen2.5-7B-Instruct
8B • Updated • 1
ZHLiu627/sciworld_worldmodels2_sciworld_Llama-3.2-3B-Instruct
4B • Updated • 1
ZHLiu627/sciworld_baseline_sft_sciworld_Llama-3.2-3B-Instruct
4B • Updated • 1
ZHLiu627/sciworld_baseline_sft_sciworld_Llama-3.1-8B-Instruct
8B • Updated • 1
ZHLiu627/sciworld_baseline_sft_sciworld_Qwen2.5-7B-Instruct
8B • Updated • 1
ZHLiu627/sokoban-GRPO-from-webshop-Llama-3.1-8B-Instruct-150step
8B • Updated • 1
ZHLiu627/sokoban-GRPO-from-webshop-Llama-3.1-8B-Instruct-135step
8B • Updated • 1
ZHLiu627/sokoban-GRPO-from-webshop-Llama-3.1-8B-Instruct-120step
8B • Updated • 1
ZHLiu627/sokoban-GRPO-from-webshop-Llama-3.1-8B-Instruct-105step
8B • Updated ZHLiu627/sokoban-GRPO-from-webshop-Llama-3.1-8B-Instruct-90step
8B • Updated ZHLiu627/sokoban-GRPO-from-webshop-Llama-3.1-8B-Instruct-75step
8B • Updated ZHLiu627/sokoban-GRPO-from-webshop-Llama-3.1-8B-Instruct-60step
8B • Updated ZHLiu627/sokoban-GRPO-from-webshop-Llama-3.1-8B-Instruct-45step
8B • Updated