v1v1d1/nayana-qwen3vl-4b-stage2
Image-Text-to-Text • 4B • Updated
• 63
ViViD
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
models 8
v1v1d1/nayana-qwen3vl-8b-stage1
Image-Text-to-Text • 9B • Updated
• 113
v1v1d1/nayana-qwen3vl-2b-stage1
Image-Text-to-Text • 2B • Updated
• 12 • 1
v1v1d1/nayana-qwen3vl-4b-stage1
Image-Text-to-Text • 4B • Updated
• 124
v1v1d1/nayana-gemma3-4b-stage1
Image-Text-to-Text • 4B • Updated
v1v1d1/vivid_docmatix_gemma3_4b_en_kn_hi_10k_50
Image-Text-to-Text • 4B • Updated
• 1
v1v1d1/vivid_docmatix_en_kn_hi_10k_50
4B • Updated
v1v1d1/vivid_docmatix_en_kn_hi_10k
4B • Updated
• 2
datasets 9
v1v1d1/vivid_docmatix_final_300k_multilingual
Viewer
• Updated
• 4.41M • 50
v1v1d1/NayanaOCRBench_Natural_final_transformed
Viewer
• Updated
• 10.5k • 30
v1v1d1/NayanaOCRBench_Natural_final
Viewer
• Updated
• 10.5k • 124
v1v1d1/NayanaOCRBench_Synthetic_final
Viewer
• Updated
• 16.9k • 16
v1v1d1/nayana_bench_200_sampled
Viewer
• Updated
• 4.4k • 43
v1v1d1/nayana_bench_human_annotated_normalised
Viewer
• Updated
• 19.6k • 20
v1v1d1/nayana_bench_human_annotated
Viewer
• Updated
• 19.6k • 12
v1v1d1/vivid_docmatix_final_250k
Viewer
• Updated
• 262k • 6
v1v1d1/vivid_docmatix_final_300k
Viewer
• Updated
• 262k • 5