ZHLiu627/sokoban-GRPO-from-sft-Llama-3.1-8B-Instruct-window-1-nothink-30step
Updated
Zhihan Liu PRO
ZHLiu627
AI & ML interests
LLMs
Recent Activity
upvoted
a
paper
about 1 month ago
Scaling Agent Learning via Experience Synthesis
published
a model
about 2 months ago
ZHLiu627/sokoban-GRPO-from-sft-Llama-3.1-8B-Instruct-window-1-nothink-30step
published
a model
about 2 months ago
ZHLiu627/sokoban-GRPO-from-sft-Llama-3.1-8B-Instruct-window-1-nothink-15step
Organizations
None yet
models
739
ZHLiu627/sokoban-GRPO-from-sft-Llama-3.1-8B-Instruct-window-1-nothink-15step
Updated
ZHLiu627/aug_verl_agent_webshop-GRPO-kl0.01-from-webshop-20step-v2-Llama-3.1-8B-Instruct-info40-150step
Updated
ZHLiu627/aug_verl_agent_webshop-GRPO-kl0.01-from-webshop-20step-v2-Llama-3.1-8B-Instruct-info40-135step
Updated
ZHLiu627/aug_verl_agent_webshop-GRPO-kl0.01-from-webshop-20step-v2-Llama-3.1-8B-Instruct-info40-120step
Updated
ZHLiu627/aug_verl_agent_webshop-GRPO-kl0.01-from-webshop-20step-v2-Llama-3.1-8B-Instruct-info40-105step
Updated
ZHLiu627/aug_verl_agent_webshop-GRPO-kl0.01-from-webshop-20step-v2-Llama-3.1-8B-Instruct-info40-90step
Updated
ZHLiu627/aug_verl_agent_webshop-GRPO-kl0.01-from-webshop-20step-v2-Llama-3.1-8B-Instruct-info40-75step
Updated
ZHLiu627/aug_verl_agent_webshop-GRPO-kl0.01-from-webshop-20step-v2-Llama-3.1-8B-Instruct-info40-60step
Updated
ZHLiu627/aug_verl_agent_webshop-GRPO-kl0.01-from-webshop-20step-v2-Llama-3.1-8B-Instruct-info40-45step
Updated
datasets
20
ZHLiu627/logger-a100
Updated
•
6
ZHLiu627/logger-h100
Updated
•
7
ZHLiu627/warm_start_sft_v2
Preview
•
Updated
•
7
ZHLiu627/sciworld_dataset
Preview
•
Updated
•
9
ZHLiu627/updated_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212__self_correction_iter1_v1
Viewer
•
Updated
•
29.3k
•
6
ZHLiu627/dataset_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212_2_global_step_70filtered_v1_v1
Viewer
•
Updated
•
29.3k
•
9
•
1
ZHLiu627/dataset_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212_2_global_step_70filtered_v1
Viewer
•
Updated
•
29.3k
•
6
ZHLiu627/updated-code-qwen7-edufiltered
Viewer
•
Updated
•
43k
•
11
ZHLiu627/updated-code-qwen7-edu
Viewer
•
Updated
•
75.6k
•
9
ZHLiu627/updated_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212__self_correction_iter1_v2filtered
Viewer
•
Updated
•
28.9k
•
7