Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Llama2-7B-GSM8K-MFT – AI Model by adalaw | AlphaNeural AI
You can deploy this model and start earning money today!
adalaw
/
Llama2-7B-GSM8K-MFT
like
0
transformers
safetensors
llama
text-generation
openai/gsm8k
2403.02178
autotrain_compatible
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Introduction
The model is trained with Masked thought Fine-Tuning (MFT), a simple variant of standard Supervised Fine-Tuning (SFT). You can refer to our code and paper below.
Links
Code
:
https://github.com/ChangyuChen347/MaskedThought
Paper
:
https://arxiv.org/abs/2403.02178
Results
We test it with the scripts provided in our code.
Model
GSM8K
adalaw/Llama2-7B-GSM8K-SFT
42.8
adalaw/Llama2-7B-GSM8K-MFT
47.3
