Fine-tuned multimodal LLMs auto-generates rich cultural-heritage descriptions for visually impaired audiences in Romanian, Serbian and German.
Iosif Tsangko
JoseferEins
·
AI & ML interests
None yet
Recent Activity
updated
a model
8 days ago
JoseferEins/Qwen2.5-VL-3B-Art-Curator-SR
updated
a model
8 days ago
JoseferEins/Qwen2.5-VL-3B-Art-Curator-RO
updated
a model
8 days ago
JoseferEins/Qwen2.5-VL-3B-Art-Curator-DE
Organizations
None yet
models
10
JoseferEins/Qwen2.5-VL-3B-Art-Curator-SR
Image-to-Text
•
Updated
JoseferEins/Qwen2.5-VL-3B-Art-Curator-RO
Image-to-Text
•
Updated
JoseferEins/Qwen2.5-VL-3B-Art-Curator-DE
Image-to-Text
•
Updated
JoseferEins/SmolVLM-500M-Instruct-fer0
Image-to-Text
•
0.5B
•
Updated
•
13
JoseferEins/gemma-2-2B-it-thinking-function_calling-shift-V1
Updated
•
3
JoseferEins/OSCAR-ro-llama7
Updated
JoseferEins/OSCAR-ro-llama1.3
Updated
JoseferEins/OSCAR-ro-mistral
Updated
JoseferEins/OSCAR-ro-Llama-3-8B-Instruct
Updated
JoseferEins/sib200-ro-OSCAR-Llama-3-8B-Instruct
Updated
datasets
0
None public yet