Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
abshetty
/
llava-lora-12-06-rpo-0.1
like
0
Transformers
TensorBoard
Safetensors
Generated from Trainer
trl
dpo
Inference Endpoints
arxiv:
2305.18290
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
024f6c6
llava-lora-12-06-rpo-0.1
/
processor_config.json
abshetty
abshetty/llava-dpo-rpo-0.1
1cf7acf
verified
about 1 month ago
raw
Copy download link
history
blame
Safe
137 Bytes
{
"image_token"
:
"<image>"
,
"patch_size"
:
14
,
"processor_class"
:
"LlavaProcessor"
,
"vision_feature_select_strategy"
:
"default"
}