Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
ISTA-DASLab
/
Llama-2-7b-AQLM-2Bit-1x16-hf
like
5
Text Generation
Transformers
Safetensors
llama
text-generation-inference
Inference Endpoints
aqlm
arxiv:
2401.06118
Model card
Files
Files and versions
Community
1
Train
Deploy
Use this model
f48478c
Llama-2-7b-AQLM-2Bit-1x16-hf
3 contributors
History:
16 commits
Andrei Panferov
try except flash-attn
f48478c
7 months ago
.gitattributes
1.52 kB
initial commit
8 months ago
config.json
2.5 kB
try except flash-attn
7 months ago
configuration_llama_aqlm.py
421 Bytes
new code
8 months ago
generation_config.json
132 Bytes
tokenizer
8 months ago
modeling_llama_aqlm.py
65.5 kB
try except flash-attn
7 months ago
pytorch_model.bin
pickle
Detected Pickle imports (5)
"torch.ShortStorage"
,
"torch.HalfStorage"
,
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
,
"torch._utils._rebuild_parameter"
How to fix it?
2.38 GB
LFS
model
8 months ago
special_tokens_map.json
414 Bytes
tokenizer
8 months ago
tokenizer.json
1.84 MB
tokenizer
8 months ago
tokenizer.model
500 kB
LFS
tokenizer
8 months ago
tokenizer_config.json
776 Bytes
tokenizer
8 months ago