Meta-Llama-3.1-Quantized
Collection
Collection of quantized Llama 3.1 models (8B & 70B versions for now), using bitsandbites.
•
4 items
•
Updated
•
1
Model Card for Model ID
This is a quantized version of Llama 3.1 70B Instruct. Quantized to 4-bit using bistandbytes and accelerate.
- Developed by: Farid Saud @ DSRS
- License: llama3.1
- Base Model: meta-llama/Meta-Llama-3.1-70B-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-3.1-70B-Instruct-NF4")
pipe(messages)
Load model directly
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("fsaudm/Meta-Llama-3.1-70B-Instruct-NF4")
model = AutoModelForCausalLM.from_pretrained("fsaudm/Meta-Llama-3.1-70B-Instruct-NF4")
The base model information can be found in the original meta-llama/Meta-Llama-3.1-70B-Instruct
- Downloads last month
- 835
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.
Model tree for fsaudm/Meta-Llama-3.1-70B-Instruct-NF4
Base model
meta-llama/Llama-3.1-70B
Finetuned
meta-llama/Llama-3.1-70B-Instruct