fsaudm/Meta-Llama-3.1-8B-Instruct-NF4

Model Card for Model ID

This is a quantized version of Llama 3.1 8B Instruct. Quantized to 4-bit using bistandbytes and accelerate.

• Developed by: Farid Saud @ DSRS
• License: llama3.1
• Base Model: meta-llama/Meta-Llama-3.1-8B-Instruct

Use this model

Use a pipeline as a high-level helper:

# Use a pipeline as a high-level helper
from transformers import pipeline

messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe = pipeline("text-generation", model="fsaudm/Meta-Llama-3.1-8B-Instruct-NF4")
pipe(messages)

Load model directly

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fsaudm/Meta-Llama-3.1-8B-Instruct-NF4")
model = AutoModelForCausalLM.from_pretrained("fsaudm/Meta-Llama-3.1-8B-Instruct-NF4")

The base model information can be found in the original meta-llama/Meta-Llama-3.1-8B-Instruct