deccan-ai/insuranceQA-v2
Viewer • Updated • 28k • 323 • 19
How to use tcotter/TinyLlama-Insurance-Adapter with Transformers:
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tcotter/TinyLlama-Insurance-Adapter", dtype="auto")How to use tcotter/TinyLlama-Insurance-Adapter 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 tcotter/TinyLlama-Insurance-Adapter 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 tcotter/TinyLlama-Insurance-Adapter to start chatting
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for tcotter/TinyLlama-Insurance-Adapter to start chatting
pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
model_name="tcotter/TinyLlama-Insurance-Adapter",
max_seq_length=2048,
)This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
Base model
unsloth/tinyllama-bnb-4bit