Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
morizon
/
idefics2-8b-dpo-rlaif-v
like
0
PEFT
Safetensors
trl
dpo
Generated from Trainer
License:
apache-2.0
Model card
Files
Files and versions
Community
Use this model
main
idefics2-8b-dpo-rlaif-v
/
added_tokens.json
morizon
Training in progress, step 312
d261446
verified
4 months ago
raw
Copy download link
history
blame
contribute
delete
Safe
92 Bytes
{
"<end_of_utterance>"
:
32002
,
"<fake_token_around_image>"
:
32000
,
"<image>"
:
32001
}