Vatsal Baherwani

vatsalb 's models 15

Sort:  Recently updated

vatsalb/attn_4b_im4jm07c_step150

4B • Updated Oct 2, 2025 • 3

vatsalb/length_penalty_8b_step700

8B • Updated Sep 24, 2025 • 9

vatsalb/weak_model_interp_4b_2

4B • Updated Sep 13, 2025 • 5

vatsalb/weak_model_interp_4b_1

4B • Updated Sep 13, 2025 • 4

vatsalb/length_penalty_4b

4B • Updated Sep 13, 2025 • 6

vatsalb/weak_model_interp_4b

4B • Updated Sep 8, 2025 • 5

vatsalb/qwen_4b_length_penalty_step_1100_encoded_format

4B • Updated Sep 4, 2025 • 5

vatsalb/checkpoints_weak_model_interp

Updated Aug 16, 2025

vatsalb/checkpoints_length_penalty

Updated Aug 16, 2025

vatsalb/qwen_4b_length_penalty_step1100

4B • Updated Aug 16, 2025 • 5

vatsalb/checkpoints_encoded

Updated Aug 16, 2025

vatsalb/qwen_4b_length_penalty_step300

4B • Updated Aug 14, 2025 • 3

vatsalb/grpo_weak_model_interp

Updated Aug 13, 2025

vatsalb/pt.zip

Updated May 16, 2025

vatsalb/fineweb_edu_tokenized

Updated May 12, 2025