Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
mobiuslabsgmbh
/
Mixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-3bit-metaoffload-HQQ
like
13
Follow
Mobius Labs GmbH
79
Text Generation
Transformers
mixtral
Mixture of Experts
conversational
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
454e767
Mixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-3bit-metaoffload-HQQ
1 contributor
History:
3 commits
mobicham
upload model
454e767
11 months ago
.gitattributes
1.52 kB
upload model
11 months ago
README.md
4.71 kB
upload model
11 months ago
config.json
773 Bytes
upload model
11 months ago
qmodel.pt
pickle
Detected Pickle imports (8)
"torch.ByteStorage"
,
"torch.HalfStorage"
,
"torch._utils._rebuild_parameter"
,
"torch.float16"
,
"torch._utils._rebuild_tensor_v2"
,
"torch.IntStorage"
,
"torch.Size"
,
"collections.OrderedDict"
How to fix it?
22.4 GB
LFS
upload model
11 months ago
special_tokens_map.json
414 Bytes
upload model
11 months ago
tokenizer.json
1.8 MB
upload model
11 months ago
tokenizer.model
493 kB
LFS
upload model
11 months ago
tokenizer_config.json
1.46 kB
upload model
11 months ago
