Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Llama-2-7b-hf-simpa-dsg-randmask-p03-s42 – AI Model by twanghcmut | AlphaNeural AI
You can deploy this model and start earning money today!
twanghcmut
/
Llama-2-7b-hf-simpa-dsg-randmask-p03-s42
like
0
safetensors
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
twanghcmut/Llama-2-7b-hf-simpa-dsg-randmask-p03-s42
MixLoRA adapter (SIMPA) trained on top of
meta-llama/Llama-2-7b-hf
.
Training details
Branch mode:
dual_scalar_gate
Dataset:
meta-math/MetaMathQA
Training steps: 1563
GSM8K accuracy: pending eval
Base model:
meta-llama/Llama-2-7b-hf
