smol 2B VLMs with 32k context.
qresearch
AI & ML interests
None defined yet.
Collections
1
models
8
qresearch/llama-3.1-8B-vision-378
Image-Text-to-Text
•
Updated
•
378
•
33
qresearch/doubutsu-2b-lora-756-vqa
Updated
•
3
qresearch/doubutsu-2b-lora-378-docci
Image-Text-to-Text
•
Updated
•
3
qresearch/doubutsu-2b-lora-756-docci
Image-Text-to-Text
•
Updated
•
37
qresearch/doubutsu-2b-pt-378
Image-Text-to-Text
•
Updated
•
8
qresearch/doubutsu-2b-pt-756
Image-Text-to-Text
•
Updated
•
46
•
2
qresearch/llama-3-vision-alpha-hf
Image-Text-to-Text
•
Updated
•
141
•
57
qresearch/llama-3-vision-alpha
Updated
•
60
datasets
None public yet