Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
smangrul
/
mistral-dpo
like
0
PEFT
TensorBoard
Safetensors
trl
dpo
Generated from Trainer
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
8779455
mistral-dpo
/
added_tokens.json
smangrul
Training in progress, epoch 1
8779455
verified
about 1 year ago
raw
Copy download link
history
blame
Safe
138 Bytes
{
"<pad>"
:
32001
,
"<|im_end|>"
:
32000
,
"<|im_start|>assistant"
:
32003
,
"<|im_start|>system"
:
32004
,
"<|im_start|>user"
:
32002
}