Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
TheBloke
/
sonya-medium-x8-MoE-GPTQ
like
3
Text Generation
Transformers
Safetensors
mixtral
text-generation-inference
4-bit precision
gptq
License:
wtfpl
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
gptq-8bit-128g-actorder_True
sonya-medium-x8-MoE-GPTQ
71.9 GB
1 contributor
History:
3 commits
TheBloke
Upload README.md
2b12c3c
almost 2 years ago
.gitattributes
1.52 kB
initial commit
almost 2 years ago
README.md
21.5 kB
Upload README.md
almost 2 years ago
config.json
3.01 kB
GPTQ model commit
almost 2 years ago
generation_config.json
137 Bytes
GPTQ model commit
almost 2 years ago
model-00001-of-00002.safetensors
49 GB
xet
GPTQ model commit
almost 2 years ago
model-00002-of-00002.safetensors
22.9 GB
xet
GPTQ model commit
almost 2 years ago
model.safetensors.index.json
641 kB
GPTQ model commit
almost 2 years ago
quantize_config.json
133 Bytes
GPTQ model commit
almost 2 years ago
special_tokens_map.json
436 Bytes
GPTQ model commit
almost 2 years ago
tokenizer.json
1.8 MB
GPTQ model commit
almost 2 years ago
tokenizer.model
493 kB
xet
GPTQ model commit
almost 2 years ago
tokenizer_config.json
968 Bytes
GPTQ model commit
almost 2 years ago