Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
trl-lib
/
Qwen2-0.5B-XPO
like
0
Follow
TRL
35
Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
trl
xpo
conversational
text-generation-inference
Inference Endpoints
arxiv:
2405.21046
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
bffbd10
Qwen2-0.5B-XPO
/
added_tokens.json
qgallouedec
HF staff
trl-lib/ultrafeedback-prompt
bffbd10
verified
15 days ago
raw
Copy download link
history
blame
Safe
80 Bytes
{
"<|endoftext|>"
:
151643
,
"<|im_end|>"
:
151645
,
"<|im_start|>"
:
151644
}