Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
ISTA-DASLab
/
Llama-2-7b-AQLM-2Bit-2x8-hf
like
2
Follow
IST Austria Distributed Algorithms and Systems Lab
107
Text Generation
Transformers
Safetensors
llama
text-generation-inference
8-bit precision
aqlm
arxiv:
2401.06118
Model card
Files
Files and versions
Community
1
Train
Deploy
Use this model
refs/pr/1
Llama-2-7b-AQLM-2Bit-2x8-hf
Ctrl+K
Ctrl+K
3 contributors
History:
8 commits
SpiridonSunRotator
Upload finetuned Llama-2-7b models
7b37574
verified
over 1 year ago
.gitattributes
1.52 kB
initial commit
over 1 year ago
README.md
1.76 kB
Upload finetuned Llama-2-7b models
over 1 year ago
config.json
2.5 kB
everythin
over 1 year ago
configuration_llama_aqlm.py
421 Bytes
everythin
over 1 year ago
modeling_llama_aqlm.py
65.6 kB
better checkpoint
over 1 year ago
pytorch_model.bin
pickle
Detected Pickle imports (4)
"torch._utils._rebuild_tensor_v2"
,
"torch.CharStorage"
,
"torch.HalfStorage"
,
"collections.OrderedDict"
What is a pickle import?
2.15 GB
LFS
Upload pytorch_model.bin with huggingface_hub
over 1 year ago
