Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
StableGalen-6b – AI Model by NewstaR | AlphaNeural AI
You can deploy this model and start earning money today!
NewstaR
/
StableGalen-6b
like
0
transformers
pytorch
llama
text-generation
medicine
doctor
custom_code
en
Photolens/MedText-DoctorLLaMa-OpenOrca-formatted
shibing624/medical
other
autotrain_compatible
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
This model is the DeciLM-6b-Instruct model, trained specifically for medicine
Galen uses the
### User: {prompt} ### Response:
or
{prompt}
Prompt templates
Galen Training Recipe:
target_modules = ["q_proj", "v_proj", "gate_proj", "down_proj", "up_proj", "k_proj", "o_proj"]
Learning Rate: 4e-4
LR Scheduler: constant
250 Steps
Loss
T3: 1 Hour
