Domain Tuned Models 😳
Collection
Models that would act as domain experts for their specific domains. • 5 items • Updated
How to use lightbird-ai/gemma-2b-healthcare with Transformers:
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("lightbird-ai/gemma-2b-healthcare", dtype="auto")How to use lightbird-ai/gemma-2b-healthcare with Unsloth Studio:
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for lightbird-ai/gemma-2b-healthcare to start chatting
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for lightbird-ai/gemma-2b-healthcare to start chatting
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for lightbird-ai/gemma-2b-healthcare to start chatting
pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
model_name="lightbird-ai/gemma-2b-healthcare",
max_seq_length=2048,
)This gemma2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
Base model
unsloth/gemma-2-2b-it-bnb-4bit