from transformers import AutoTokenizer, AutoModelForCausalLM

HF_MODEL_REPO = "anslin-raj/Llama-2-7b-chat-hf-8-bit"

tokenizer = AutoTokenizer.from_pretrained(HF_MODEL_REPO, device=device)

model = AutoModelForCausalLM.from_pretrained(HF_MODEL_REPO, device_map=device, load_in_8bit=True)
Downloads last month
373
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.