Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking
Paper • 2403.09629 • Published • 79
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("pharaouk/Quiet-Star-Custom", trust_remote_code=True, dtype="auto")Quick Links
Mistral-7b with continued pretraining using Quiet-STaR (https://arxiv.org/abs/2403.09629) for generating 8 thought tokens before each output token.
Forked from Crystalcareai/Quiet-Star-Custom
- Downloads last month
- 15
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="pharaouk/Quiet-Star-Custom", trust_remote_code=True)