Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
AIR-hl
/
Qwen2.5-1.5B-DPO
like
0
Text Generation
Transformers
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
qwen2
trl
qwen
dpo
alignment
custome
chat
conversational
text-generation-inference
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
main
Qwen2.5-1.5B-DPO
/
.ipynb_checkpoints
1 contributor
History:
2 commits
AIR-hl
updata beta=0.01 version
01ef97e
verified
about 1 month ago
trainer_state-checkpoint.json
Safe
22.7 kB
updata beta=0.01 version
about 1 month ago