Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
cluebbers
/
Llama-3.1-8B-paraphrase-type-generation-apty-ipo
like
0
Text Generation
Transformers
TensorBoard
Safetensors
worta/apty
English
llama
Generated from Trainer
trl
dpo
ipo
text-generation-inference
Inference Endpoints
arxiv:
2305.18290
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
1e8ceab
Llama-3.1-8B-paraphrase-type-generation-apty-ipo
/
adapter
1 contributor
History:
5 commits
cluebbers
Rename adapter/adapter_config.json to adapter_config.json
1e8ceab
verified
2 months ago
adapter_model.safetensors
Safe
168 MB
LFS
Rename adapter_model.safetensors to adapter/adapter_model.safetensors
2 months ago