Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
radm
/
Qwen2.5-32B-simpo-LoRA
like
0
PEFT
Safetensors
IlyaGusev/saiga_preferences
40umov/dostoevsky
Vikhrmodels/gutenpromax
13 languages
llama-factory
lora
Generated from Trainer
License:
other
Model card
Files
Files and versions
Community
Use this model
main
Qwen2.5-32B-simpo-LoRA
/
training_loss.png
radm
first model version
e8a12f2
6 months ago
download
Copy download link
history
contribute
delete
Safe
45.6 kB