Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
HuggingFaceTB
/
SmolVLM-Instruct-DPO
like
13
Follow
Hugging Face TB Research
668
Image-Text-to-Text
PEFT
Safetensors
HuggingFaceH4/rlaif-v_formatted
English
trl
dpo
conversational
License:
apache-2.0
Model card
Files
Files and versions
Community
1
Use this model
d96c774
SmolVLM-Instruct-DPO
/
added_tokens.json
kashif
HF staff
Upload 13 files
7c1915a
verified
15 days ago
raw
Copy download link
history
blame
Safe
92 Bytes
{
"<end_of_utterance>"
:
49154
,
"<fake_token_around_image>"
:
49152
,
"<image>"
:
49153
}