Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
QWQ-RP-RandomFT-0.5B-v0.01 – AI Model by Disya | AlphaNeural AI
You can deploy this model and start earning money today!
Disya
/
QWQ-RP-RandomFT-0.5B-v0.01
like
0
safetensors
qwen2
Undi95/R1-RP-ShareGPT3
Qwen/Qwen2.5-0.5B-Instruct
finetune
apache-2.0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
This is a reasoning model that almost always shows the
<think>
prefix, even outside of RP. It was a quick fine-tune done just for fun.
It works terribly in languages other than English.
Don't evaluate this as something serious at the moment.
Training Details
Sequence Length
: 8192
Epochs
: 1 epoch
Full fine-tuning
Learning Rate
: 0.00008
Scheduler: Cosine
Total batch size
(4 x 16 x 1) = 64