Downloads · 30 days
6
8% of all-time downloads
anslin-raj/Llama-2-7b-chat-hf-8-bit
Llama-2-7b-chat-hf-8-bit is a text generation model from anslin-raj. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as bsd-3-clause.
Downloads · 30 days
6
8% of all-time downloads
All-time downloads
72
Public
Repo size
14 GB
Likes
0
Public
Click a slice to open those files.
.bin7 GB · 100%
From the Hugging Face model README
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)