Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
Qwen2.5-32B-simpo-FP8 – AI Model by radm | AlphaNeural AI
You can deploy this model and start earning money today!
radm
/
Qwen2.5-32B-simpo-FP8
like
0
safetensors
qwen2
zho
eng
fra
spa
por
deu
ita
rus
jpn
kor
vie
tha
ara
IlyaGusev/saiga_preferences
40umov/dostoevsky
Vikhrmodels/gutenpromax
Qwen/Qwen2.5-32B-Instruct
finetune
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Model Card for radm/Qwen2.5-32B-simpo-FP8
Model Details
Improved quality on hard tasks by 25 percent relative to the base model Qwen2.5-32B-Instruct. Improved multilingual support.
Fine-tuning on A100 in 4-bit with unsloth using SIMPO and custom dataset
LoRA adapter:
radm/Qwen2.5-32B-simpo-LoRA
Eval results
Eval results on
ZebraLogic
image/png
