Transformers How to use geldarr/saiga-Yarn-Llama-2-7b-64k with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("question-answering", model="geldarr/saiga-Yarn-Llama-2-7b-64k", trust_remote_code=True) # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("geldarr/saiga-Yarn-Llama-2-7b-64k", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("geldarr/saiga-Yarn-Llama-2-7b-64k", trust_remote_code=True, device_map="auto") 
