Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
XueyingJia
/
qwen-1.5b-sft-HH-online-dpo
like
0
Transformers
TensorBoard
Safetensors
XueyingJia/hh-rlhf-train
Generated from Trainer
trl
online-dpo
Inference Endpoints
arxiv:
2402.04792
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
ea7678a
qwen-1.5b-sft-HH-online-dpo
/
added_tokens.json
XueyingJia
Training in progress, step 100
9820fc5
verified
3 months ago
raw
Copy download link
history
blame
Safe
80 Bytes
{
"<|endoftext|>"
:
151643
,
"<|im_end|>"
:
151645
,
"<|im_start|>"
:
151644
}