ZHLiu627/verl_agent_alfworld-GRPO-kl-0.01-from-sft-Llama-3.2-3B-Instruct-15step
4B • Updated • 1
Zhihan Liu
ZHLiu627
AI & ML interests
LLMs
Organizations
None yet
ZHLiu627/verl_agent_alfworld-GRPO-kl-0.01-from-sft-Llama-3.2-3B-Instruct-nt-150step
4B • Updated • 1
ZHLiu627/verl_agent_alfworld-GRPO-kl-0.01-from-sft-Llama-3.2-3B-Instruct-nt-135step
4B • Updated • 1
ZHLiu627/verl_agent_alfworld-GRPO-kl-0.01-from-sft-Llama-3.2-3B-Instruct-nt-120step
4B • Updated • 1
ZHLiu627/verl_agent_alfworld-GRPO-kl-0.01-from-sft-Llama-3.2-3B-Instruct-nt-105step
4B • Updated • 1
ZHLiu627/verl_agent_alfworld-GRPO-kl-0.01-from-sft-Llama-3.2-3B-Instruct-nt-90step
4B • Updated • 1
ZHLiu627/verl_agent_alfworld-GRPO-kl-0.01-from-sft-Llama-3.2-3B-Instruct-nt-75step
4B • Updated • 1
ZHLiu627/verl_agent_alfworld-GRPO-kl-0.01-from-sft-Llama-3.2-3B-Instruct-nt-60step
4B • Updated • 1
ZHLiu627/verl_agent_alfworld-GRPO-kl-0.01-from-sft-Llama-3.2-3B-Instruct-nt-45step
4B • Updated • 1
ZHLiu627/verl_agent_alfworld-GRPO-kl-0.01-from-sft-Llama-3.2-3B-Instruct-nt-30step
4B • Updated • 1
ZHLiu627/verl_agent_alfworld-GRPO-kl-0.01-from-sft-Llama-3.2-3B-Instruct-nt-15step
4B • Updated • 1
ZHLiu627/verl_agent_webshop-new-GRPO-kl-0.01-from-sft-Llama-3.1-8B-Instruct-nothink-150step
8B • Updated • 1
ZHLiu627/verl_agent_webshop-new-GRPO-kl-0.01-from-sft-Llama-3.1-8B-Instruct-nothink-135step
8B • Updated • 1
ZHLiu627/verl_agent_webshop-new-GRPO-kl-0.01-from-sft-Llama-3.1-8B-Instruct-nothink-120step
8B • Updated
ZHLiu627/verl_agent_webshop-new-GRPO-kl-0.01-from-sft-Llama-3.1-8B-Instruct-nothink-105step
8B • Updated
ZHLiu627/verl_agent_webshop-new-GRPO-kl-0.01-from-sft-Llama-3.1-8B-Instruct-nothink-90step
8B • Updated
ZHLiu627/verl_agent_webshop-new-GRPO-kl-0.01-from-sft-Llama-3.1-8B-Instruct-nothink-75step
8B • Updated • 1
ZHLiu627/verl_agent_webshop-new-GRPO-kl-0.01-from-sft-Llama-3.1-8B-Instruct-nothink-60step
8B • Updated • 1
ZHLiu627/verl_agent_webshop-new-GRPO-kl-0.01-from-sft-Llama-3.1-8B-Instruct-nothink-45step
8B • Updated • 1
ZHLiu627/verl_agent_webshop-new-GRPO-kl-0.01-from-sft-Llama-3.1-8B-Instruct-nothink-30step
8B • Updated • 1
ZHLiu627/verl_agent_webshop-new-GRPO-kl-0.01-from-sft-Llama-3.1-8B-Instruct-nothink-15step
8B • Updated • 1
ZHLiu627/verl_agent_webshop-new-GRPO-kl-0.01-from-sft-Llama-3.1-8B-Instruct-150step
8B • Updated
ZHLiu627/verl_agent_webshop-new-GRPO-kl-0.01-from-sft-Llama-3.1-8B-Instruct-135step
8B • Updated
ZHLiu627/verl_agent_webshop-new-GRPO-kl-0.01-from-sft-Llama-3.1-8B-Instruct-120step
8B • Updated
ZHLiu627/verl_agent_webshop-new-GRPO-kl-0.01-from-sft-Llama-3.1-8B-Instruct-105step
8B • Updated
ZHLiu627/verl_agent_webshop-new-GRPO-kl-0.01-from-sft-Llama-3.1-8B-Instruct-90step
8B • Updated
ZHLiu627/verl_agent_webshop-new-GRPO-kl-0.01-from-sft-Llama-3.1-8B-Instruct-75step
8B • Updated
ZHLiu627/verl_agent_webshop-new-GRPO-kl-0.01-from-sft-Llama-3.1-8B-Instruct-60step
8B • Updated • 1
ZHLiu627/verl_agent_webshop-new-GRPO-kl-0.01-from-sft-Llama-3.1-8B-Instruct-45step
8B • Updated • 1
ZHLiu627/verl_agent_webshop-new-GRPO-kl-0.01-from-sft-Llama-3.1-8B-Instruct-30step
8B • Updated