Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
tpo-alignment
/
Mistral-Instruct-7B-TPO-y2-v0.1
like
0
Follow
TPO
5
Safetensors
princeton-nlp/mistral-instruct-ultrafeedback
mistral
alignment-handbook
Generated from Trainer
arxiv:
2405.16681
License:
mit
Model card
Files
Files and versions
xet
Community
cf7635f
Mistral-Instruct-7B-TPO-y2-v0.1
/
generation_config.json
sahsaeedi
Upload MistralForCausalLM
6decec5
verified
7 months ago
raw
Copy download link
history
blame
Safe
111 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
1
,
"eos_token_id"
:
2
,
"transformers_version"
:
"4.45.0"
}