Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
sbintuitions
/
sarashina2-vision-8b
like
9
Follow
SB Intuitions
240
Image-to-Text
Transformers
Safetensors
Japanese
English
sarashina2_vision
text-generation
multimodal
vision-language
llama
qwen2_vl
custom_code
License:
mit
Model card
Files
Files and versions
xet
Community
2
Deploy
Use this model
refs/pr/2
sarashina2-vision-8b
16 GB
1 contributor
History:
5 commits
kkokkie2360
Remove outdated VideoInput import in processing_sarashina2_vision.py
4c5a985
verified
2 months ago
.gitattributes
Safe
1.57 kB
update
9 months ago
LICENSE
Safe
1.07 kB
update
9 months ago
README.md
Safe
5.44 kB
Update README.md
9 months ago
chat_template.json
Safe
533 Bytes
update
9 months ago
config.json
Safe
852 Bytes
update
9 months ago
configuration_sarashina2_vision.py
Safe
2.92 kB
update
9 months ago
generation_config.json
Safe
111 Bytes
update
9 months ago
model-00001-of-00002.safetensors
9.99 GB
xet
update
9 months ago
model-00002-of-00002.safetensors
6 GB
xet
update
9 months ago
model.safetensors.index.json
Safe
53.9 kB
update
9 months ago
modeling_sarashina2_vision.py
Safe
11.5 kB
update modeling_sarashina2_vision.py
8 months ago
preprocessor_config.json
Safe
680 Bytes
update
9 months ago
processing_sarashina2_vision.py
17.1 kB
Remove outdated VideoInput import in processing_sarashina2_vision.py
2 months ago
processor_config.json
Safe
150 Bytes
update
9 months ago
sample.jpg
Safe
2.51 MB
xet
update
9 months ago
special_tokens_map.json
Safe
968 Bytes
update
9 months ago
tokenizer.json
Safe
6.72 MB
update
9 months ago
tokenizer.model
Safe
1.83 MB
xet
update
9 months ago
tokenizer_config.json
Safe
4.46 kB
update
9 months ago