Introducing ConTextual: How well can your Multimodal model jointly reason over text and image in text-rich scenes?
•
4
Hritik Bansal
hbXNov
AI & ML interests
Multimodal | LLM
Recent Activity
updated
a model
29 minutes ago
hbXNov/llama-3.1-8b-instruct-star-gen-ver-w-gt-sol-e3-lr5e-7-75324-merged
updated
a dataset
1 day ago
hbXNov/ultrafeedback-pref-tuning-ori-plus-chosen-rejected
updated
a dataset
1 day ago
hbXNov/ultrafeedback-pref-tuning
Articles
Organizations
models
11
hbXNov/llama-3.1-8b-instruct-star-gen-ver-w-gt-sol-e3-lr5e-7-75324-merged
Updated
hbXNov/mistral_7b_zephyr
Updated
•
4
hbXNov/checkpoint-108666-merged
Updated
•
7
hbXNov/ckpt-229224-merged
Updated
•
13
hbXNov/ckpt-152816-merged
Updated
•
8
hbXNov/ckpt-76408-merged
Updated
•
30
hbXNov/llama-3.2-3b-instruct-star-gen-ver-e3
Updated
hbXNov/talc_finetuned_modelscope_t2v
Updated
•
1
hbXNov/reward_model_rating
Updated
hbXNov/reward_model_ranking
Updated
datasets
19
hbXNov/ultrafeedback-pref-tuning-ori-plus-chosen-rejected
Viewer
•
Updated
•
122k
hbXNov/ultrafeedback-pref-tuning
Viewer
•
Updated
•
61.2k
hbXNov/ultrachat-sft
Viewer
•
Updated
•
231k
hbXNov/llama-3.1-8B-correct-verifications-with-gt-solutions
Preview
•
Updated
hbXNov/llama-3.1-8b-instruct-star-gen-ver-w-gt-sol-e3-120516-merged
Updated
hbXNov/llama-3.1-8b-instruct-math_train-correct-verifications-balanced
Viewer
•
Updated
•
36.3k
•
16
hbXNov/math_7500_llama3.2_3b_instruct_star_gen_ver
Viewer
•
Updated
•
76.7k
•
9
hbXNov/llama_3.2_3b_sft_3solns_per_problem
Viewer
•
Updated
•
11.2k
•
11
hbXNov/llama_3.1_8b_sft_one_soln_per_problem
Viewer
•
Updated
•
3.68k
•
8
hbXNov/llama_3.2_3b_star-math
Viewer
•
Updated
•
11.2k
•
8