Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
ISTA-DASLab
/
Llama-2-7b-AQLM-2Bit-1x16-hf
like
5
Follow
IST Austria Distributed Algorithms and Systems Lab
53
Text Generation
Transformers
Safetensors
llama
text-generation-inference
Inference Endpoints
aqlm
arxiv:
2401.06118
Model card
Files
Files and versions
Community
2
Train
Deploy
Use this model
3b64d42
Llama-2-7b-AQLM-2Bit-1x16-hf
Commit History
Create README.md
3b64d42
verified
BlackSamorez
commited on
Feb 8
try except flash-attn
f48478c
Andrei Panferov
commited on
Feb 6
inference lib
03ea233
Andrei Panferov
commited on
Jan 28
slightly faster inference
f1a2023
Andrei Panferov
commited on
Jan 22
newer inference
115e749
Andrei Panferov
commited on
Jan 20
new code
dfb8eb3
Andrei Panferov
commited on
Jan 18
removed init
161c13a
Andrei Panferov
commited on
Jan 18
tokenizer
8abdf20
Andrei Panferov
commited on
Jan 18
deleted leftovers
0110580
Andrei Panferov
commited on
Jan 18
depth 1
5edaefc
Andrei Panferov
commited on
Jan 18
flat
7e4a8ff
Andrei Panferov
commited on
Jan 18
correct import
c0d7cc2
Andrei Panferov
commited on
Jan 18
Custom config in modeling
c43662f
Andrei Panferov
commited on
Jan 18
inference and autoloading
5c0d7ef
Andrei Panferov
commited on
Jan 18
model
cc25d01
Andrei Panferov
commited on
Jan 18
config
d1f8951
Andrei Panferov
commited on
Jan 18
initial commit
e8c0770
verified
BlackSamorez
commited on
Jan 18