Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
neuralmagic
/
Meta-Llama-3.1-70B-Instruct-quantized.w8a16
like
3
Follow
Neural Magic
162
Text Generation
Transformers
Safetensors
8 languages
llama
int88
vllm
conversational
text-generation-inference
Inference Endpoints
compressed-tensors
arxiv:
2210.17323
License:
llama3.1
Model card
Files
Files and versions
Community
5
Train
Deploy
Use this model
cc2f1e3
Meta-Llama-3.1-70B-Instruct-quantized.w8a16
/
model-00001-of-00015.safetensors
Commit History
Upload folder using huggingface_hub
3d7e3dc
verified
alexmarques
commited on
Jul 24