Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
sergiopaniego
/
smolvlm-instruct-trl-dpo-rlaif-v
like
0
Transformers
TensorBoard
Safetensors
HuggingFaceH4/rlaif-v_formatted
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
fb83b2f
smolvlm-instruct-trl-dpo-rlaif-v
File size: 68 Bytes
51dde93
1
2
3
4
5
{
"image_seq_len"
:
81
,
"processor_class"
:
"Idefics3Processor"
}