Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
Yana
/
compass-vlm
like
1
Image-Text-to-Text
Transformers
Safetensors
8 datasets
Japanese
English
llama
text-generation
vision-language-model
vlm
llava
llava-onevision
japanese
siglip
llm-jp
finance
financial-qa
document-understanding
multimodal
reasoning
sft
dpo
lora
conversational
text-generation-inference
arxiv:
9 papers
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
compass-vlm
/
generation_config.json
Yana
Upload merged VLM (LLM + Vision Tower + Projector)
47a171f
verified
about 1 month ago
raw
Copy download link
history
blame
contribute
delete
Safe
110 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
1
,
"eos_token_id"
:
2
,
"transformers_version"
:
"5.3.0"
}