# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("wcde/llama-7b-4bit-act")
model = AutoModelForCausalLM.from_pretrained("wcde/llama-7b-4bit-act", device_map="auto")Quick Links
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Generated with: --wbits 4 --act-order --true-sequential --new-eval --faster-kernel
- Downloads last month
- 11
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="wcde/llama-7b-4bit-act")