Hritik Bansal's picture

7 6 32

Hritik Bansal

hbXNov

·

https://sites.google.com/view/hbansal

AI & ML interests

Multimodal | LLM

Recent Activity

updated a dataset 22 days ago

hbXNov/MATHVERSE_NUMERIC_OR_CHOICE_ANSWER

published a dataset 25 days ago

hbXNov/MATHVERSE_NUMERIC_OR_CHOICE_ANSWER

upvoted a paper about 1 month ago

LaViDa: A Large Diffusion Language Model for Multimodal Understanding

View all activity

Organizations

hbXNov 's models 52

hbXNov/lavida-llada-reason

8B • Updated May 10 • 2.26k • 2

hbXNov/hero-reason-ckpt-ep2

8B • Updated May 10 • 25

hbXNov/vlrethinker-full-ep5

8B • Updated May 6 • 5

hbXNov/vlrethinker-partial-ep5

8B • Updated May 5 • 37

hbXNov/llada_sft_rethinker_partial_2048

8B • Updated May 5 • 27

hbXNov/llada_sft_openvlthinker2_sft1_2048

8B • Updated May 4 • 5

hbXNov/LLaDA-8B-Instruct-mlp2x_gelu-pretrain_blip558k_plain_e3

Updated Apr 19 • 26

hbXNov/LLaDA-8B-Instruct-mlp2x_gelu-pretrain_blip558_v4-cont_200k_openllavanext_allava_gpt4omini

8B • Updated Apr 17 • 49

hbXNov/LLaDA-8B-Instruct-mlp2x_gelu-pretrain_blip558_v4-cont_lr_8e-5

8B • Updated Apr 14 • 7

hbXNov/LLaDA-8B-Instruct-mlp2x_gelu-pretrain_blip558k_plain

Updated Apr 13 • 9

hbXNov/distill_r1_llama8b_gpt4o_verify_openthoughts_processed_train

hbXNov/distill_r1_llama8b_gpt4o_verify_openthoughts_processed

hbXNov/videophy_autoeval_three_models_rule_e3_lr5e-4_bs64_part2_vta_pc_rule_ckpt502

hbXNov/llama_8b_instruct_distill_r1_q1p5b_balanced_train_e3_lr5e-7_all-ckpt_3278

8B • Updated Mar 3 • 9

hbXNov/llama_8b_instruct_distill_r1_q1p5b_balanced_train_e6_lr5e-7_balanced_ckpt-4386

8B • Updated Mar 2 • 10

hbXNov/qwen_1p5b_base_distill_r1_q1p5b_balanced_train_e3_lr1e-5_balanced_ckpt_2193

2B • Updated Mar 2 • 10

hbXNov/llama_8b_instruct_distill_r1_q1p5b_balanced_train_e3_lr5e-7_balanced_ckpt_2193

8B • Updated Mar 1 • 9

hbXNov/llama_8b_instruct_distill_r1_q1p5b_balanced_train_e3_lr1e-5_balanced_ckpt_2193

8B • Updated Mar 1 • 12

hbXNov/qwen_1p5b_instruct_distill_r1_q1p5b_train_e3_lr1e-5_balanced-ckpt-4383

2B • Updated Feb 27 • 6

hbXNov/qwen_1p5b_instruct_distill_r1_q1p5b_train_e3_lr1e-5_all_ckpt_19659

2B • Updated Feb 27 • 13

hbXNov/llama_3_1_8b_instruct_verifier_direct_lr5e-6_e3_ckpt_44892

8B • Updated Feb 26 • 8

hbXNov/llama_3_1_8b_instruct_verifier_direct_lr1e-7_e3_ckpt_44892

8B • Updated Feb 26 • 9

hbXNov/llama_3_1_8b_instruct_verifier_direct-merged-44892

8B • Updated Feb 21 • 10

hbXNov/llama8b_instruct_verifier_qwen_solutions_direct_14403-merged

8B • Updated Feb 21 • 8

hbXNov/qwen_2p5_7b_base_gpt_4o_verify_qwen2p5_7b_instruct_solns-11049

8B • Updated Feb 10 • 7

hbXNov/qwen_2p5_7b_distill_qwen_7b_gpt_4o_verify_1e-5_3072_e3-2103

8B • Updated Feb 3 • 9

hbXNov/qwen_2p5_7b_instruct_distill_qwen_7b_gpt_4o_verify_1e-5_3072_e6-2793

8B • Updated Feb 2 • 9

hbXNov/qwen_2p5_7b_instruct_distill_qwen_1p5b_gpt_4o_verify_1e-5_3072_e3

hbXNov/qwen_2p5_1p5b_instruct_distill_qwen_1p5b_gpt_4o_verify_1e-5_3072_e6-checkpoint-7536-merged

2B • Updated Jan 29 • 8

hbXNov/qwen_2p5_1p5b_instruct_distill_qwen_1p5b_gpt_4o_verify_5e-7_3072_merged

2B • Updated Jan 29 • 9