Tong Liu's picture

In a Training Loop 🔄

5 27

Tong Liu

tongliuphysics

·

AI & ML interests

None yet

Recent Activity

updated a model 27 minutes ago

tongliuphysics/Qwen2.57binstruct-normal-n1multiturn-binary-rollout8-epoch40-0201-step40

published a model 29 minutes ago

tongliuphysics/Qwen2.57binstruct-normal-n1multiturn-binary-rollout8-epoch40-0201-step40

updated a model 36 minutes ago

tongliuphysics/Qwen2.57binstruct-normal-n1multiturn-binary-rollout8-epoch40-0201-step20

View all activity

Organizations

tongliuphysics 's models 26

tongliuphysics/Qwen2.57binstruct-normal-n1multiturn-binary-rollout8-epoch40-0201-step40

8B • Updated 27 minutes ago

tongliuphysics/Qwen2.57binstruct-normal-n1multiturn-binary-rollout8-epoch40-0201-step20

8B • Updated 36 minutes ago

tongliuphysics/qwen_7binstruct_normal_0.5qwen_granular_rollout8_1012_320steps_conti5

8B • Updated 23 days ago • 22

tongliuphysics/qwen_7binstruct_normal_0.5qwen_granular_rollout8_1012_320steps

8B • Updated 23 days ago • 21

tongliuphysics/qwen_7binstruct_normal_0.5qwen_granular_rollout8_260steps

8B • Updated 24 days ago • 23

tongliuphysics/qwen2.5i-toolrl-grpo-105steps

3B • Updated Nov 26, 2025 • 2

tongliuphysics/qwen-3binstruct-normal-0.5with5rollouts-granular-rollout5-340steps-addentropytoadvantage-alpha1

3B • Updated Nov 19, 2025 • 23

tongliuphysics/llama3b-instruct-80steps

4B • Updated Oct 15, 2025 • 4

tongliuphysics/qwen3b-instruct-160steps-speed1

3B • Updated Sep 23, 2025 • 5

tongliuphysics/qwen3b-instruct-80steps-speed1

3B • Updated Sep 23, 2025 • 6

tongliuphysics/qwen3b-instruct-80steps

3B • Updated Sep 18, 2025 • 7

tongliuphysics/qwen7b-instruct-80steps

8B • Updated Sep 8, 2025 • 2

tongliuphysics/qwen7b-instruct-160steps

8B • Updated Sep 8, 2025 • 6

tongliuphysics/qwen7b-instruct-320steps

8B • Updated Sep 8, 2025 • 7

tongliuphysics/qwen7b-instruct-240steps

8B • Updated Sep 8, 2025 • 4

tongliuphysics/qwen3b-instruct-160steps

3B • Updated Sep 5, 2025 • 3

tongliuphysics/qwen3b-instruct-240steps

3B • Updated Sep 5, 2025 • 4

tongliuphysics/qwen3b-instruct-10steps

3B • Updated Sep 2, 2025 • 5

tongliuphysics/Llama-3-8B-Instruct-FocalPO

8B • Updated Jul 14, 2025 • 4 • 1

tongliuphysics/Qwen2.5-3B-MATH-lighteval-GRPO-verl-1epoch3-step_4

3B • Updated Jul 10, 2025 • 5

tongliuphysics/Qwen2.5-3B-MATH-lighteval-GRPO-verl-1epoch3-step_2

3B • Updated Jul 10, 2025 • 7

tongliuphysics/Qwen2.5-3B-MATH-lighteval-GRPO-verl-1epoch-step_2

3B • Updated Jul 6, 2025 • 3

tongliuphysics/Qwen2.5-3B-MATH-lighteval-GRPO-verl-1epoch-step_16

3B • Updated Jul 5, 2025 • 6

tongliuphysics/Llama0-3-8b-v0.1-p-0.05-lr5e-7-e1

Text Generation • 8B • Updated Dec 6, 2024 • 5

tongliuphysics/Llama0-3-8b-v0.1-dpo-lr1e-6-e1

Text Generation • 8B • Updated Dec 5, 2024 • 4

tongliuphysics/Mistral-7B-Base-SFT-FocalPO

Text Generation • 7B • Updated Nov 29, 2024 • 16 • 1