Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
trl-lib
/
Qwen2-0.5B-DPO
like
3
Follow
TRL
36
Text Generation
Transformers
Safetensors
trl-lib/Capybara-Preferences
qwen2
Generated from Trainer
trl
dpo
conversational
text-generation-inference
Inference Endpoints
arxiv:
2305.18290
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
main
Qwen2-0.5B-DPO
/
added_tokens.json
qgallouedec
HF staff
Training in progress, epoch 1
ecca24c
verified
about 2 months ago
raw
Copy download link
history
blame
contribute
delete
Safe
80 Bytes
{
"<|endoftext|>"
:
151643
,
"<|im_end|>"
:
151645
,
"<|im_start|>"
:
151644
}