Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
neuralmagic-ent
/
Llama-3.1-8B-quantized.w8a8
like
0
Follow
Neural Magic Enterprise
12
Text Generation
Safetensors
8 languages
llama
int8
vllm
quantized
8-bit precision
compressed-tensors
arxiv:
2210.17323
License:
llama3.1
Model card
Files
Files and versions
Community
Train
main
Llama-3.1-8B-quantized.w8a8
1 contributor
History:
3 commits
nm-research
Update README.md
22f2102
verified
15 days ago
.gitattributes
Safe
1.52 kB
initial commit
15 days ago
README.md
Safe
6.7 kB
Update README.md
15 days ago
config.json
Safe
2.1 kB
Upload folder using huggingface_hub
15 days ago
generation_config.json
Safe
180 Bytes
Upload folder using huggingface_hub
15 days ago
model-00001-of-00002.safetensors
Safe
5 GB
LFS
Upload folder using huggingface_hub
15 days ago
model-00002-of-00002.safetensors
Safe
4.08 GB
LFS
Upload folder using huggingface_hub
15 days ago
model.safetensors.index.json
Safe
43.5 kB
Upload folder using huggingface_hub
15 days ago
recipe.yaml
Safe
173 Bytes
Upload folder using huggingface_hub
15 days ago
special_tokens_map.json
Safe
335 Bytes
Upload folder using huggingface_hub
15 days ago
tokenizer.json
Safe
9.09 MB
Upload folder using huggingface_hub
15 days ago
tokenizer_config.json
Safe
50.5 kB
Upload folder using huggingface_hub
15 days ago
