Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
alvarobartt
/
mistral-orpo-mix
like
0
Text Generation
Transformers
TensorBoard
Safetensors
alvarobartt/dpo-mix-7k-simplified
English
mistral
orpo
trl
conversational
text-generation-inference
arxiv:
2403.07691
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
152670b
mistral-orpo-mix
File size: 51 Bytes
152670b
1
2
3
4
5
{
"<|im_end|>"
:
32001
,
"<|im_start|>"
:
32000
}