Jandial

Surgan 's models 26

Sort:  Recently updated

Surgan/Qwen2-0.5B-GRPO-test

Updated Feb 25

Surgan/Qwen2-0.5B-GRPO-test-len

Updated Feb 24

Surgan/Qwen2-0.5B-GRPO-test_lenrew

Updated Feb 24

Surgan/smolvlm-instruct_mix_2k_prm_text_img_text

2B • Updated Mar 28, 2025 • 2

Surgan/smolvlm-instruct_mix_2k_prm

2B • Updated Mar 27, 2025 • 2

Surgan/smolvlm-instruct_base_2k_random

2B • Updated Mar 26, 2025 • 3

Surgan/smolvlm-instruct_full_dpo_16k

2B • Updated Mar 25, 2025 • 1

Surgan/smolvlm-instruct_mix_2k

2B • Updated Mar 23, 2025 • 2

Surgan/smolvlm-instruct_dpo_4000_full_dpo_peft

Updated Mar 22, 2025

Surgan/smolvlm-instruct_dpo_2k_ours_full_dpo_peft

Updated Mar 22, 2025

Surgan/smolvlm-instruct_mix_2k_dpo_5e-06_0.1

Updated Mar 22, 2025

Surgan/smolvlm-instruct_mix_2k_5e-06_0.05

2B • Updated Mar 22, 2025 • 2

Surgan/smolvlm-instruct_mix_2k_1e-06_0.05

2B • Updated Mar 22, 2025 • 1

Surgan/smolvlm-instruct_mix_2k_5e-06_0.1

2B • Updated Mar 22, 2025 • 1

Surgan/smolvlm-instruct_mix_2k_1e-06_0.1

2B • Updated Mar 22, 2025

Surgan/smolvlm-instruct_mix_2k_5e-07_0.1

2B • Updated Mar 22, 2025 • 1

Surgan/smolvlm-instruct_mix_2k_5e-07_0.05

2B • Updated Mar 22, 2025 • 1

Surgan/smolvlm-instruct_4000_full_dpo_begin

Updated Mar 22, 2025

Surgan/smolvlm-instruct_4000_full

2B • Updated Mar 22, 2025

Surgan/smolvlm-instruct_adv_ft_2

2B • Updated Mar 21, 2025 • 1

Surgan/smolvlm-instruct_adv_ft

2B • Updated Mar 20, 2025 • 1

Surgan/smolvlm-instruct_full_rpo

2B • Updated Mar 19, 2025 • 1

Surgan/smolvlm-instruct_full

2B • Updated Mar 19, 2025

Surgan/smolvlm-instruct_adv_full

Updated Mar 18, 2025

Surgan/smolvlm-instruct_adv

Updated Mar 18, 2025

Surgan/smolvlm-instruct-trl-dpo-rlaif-v

Updated Mar 16, 2025