Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
ProphetOfBostrom
/
Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss_attn-4bit-moe-2bit-HQQ
like
6
Text Generation
Transformers
mixtral
HQQ
Mixture of Experts
quantized
2bit
conversational
Inference Endpoints
text-generation-inference
License:
cc-by-nc-4.0
Model card
Files
Files and versions
Community
1
Train
Deploy
Use this model
main
Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss_attn-4bit-moe-2bit-HQQ
1 contributor
History:
8 commits
ProphetOfBostrom
Update README.md
ff58d51
verified
3 months ago
.gitattributes
1.52 kB
initial commit
4 months ago
LICENSE-CC-BY-NC-4.0.txt
19.3 kB
Upload 10 files
4 months ago
MISLEAD.md
1.74 kB
Create MISLEAD.md
4 months ago
README.md
6.09 kB
Update README.md
3 months ago
added_tokens.json
51 Bytes
Upload 10 files
4 months ago
config.json
791 Bytes
Upload 10 files
4 months ago
config_prequant.json
798 Bytes
Upload 10 files
4 months ago
generation_config.json
116 Bytes
Upload 10 files
4 months ago
qmodel.pt
pickle
Detected Pickle imports (6)
"torch.Size"
,
"torch.ByteStorage"
,
"collections.OrderedDict"
,
"torch._utils._rebuild_tensor_v2"
,
"torch.HalfStorage"
,
"torch._utils._rebuild_parameter"
How to fix it?
18.2 GB
LFS
Upload qmodel.pt with huggingface_hub
4 months ago
special_tokens_map.json
414 Bytes
Upload 10 files
4 months ago
tokenizer.json
1.8 MB
Upload 10 files
4 months ago
tokenizer.model
493 kB
LFS
Upload 10 files
4 months ago
tokenizer_config.json
1.46 kB
Upload 10 files
4 months ago