Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
TheBloke
/
8x7B-MoE-test-NOT-MIXTRAL-GPTQ
like
2
Text Generation
Transformers
Safetensors
English
Chinese
mixtral
qwen
text-generation-inference
4-bit precision
gptq
License:
gpl-3.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
main
8x7B-MoE-test-NOT-MIXTRAL-GPTQ
1 contributor
History:
4 commits
TheBloke
Upload README.md
c9b7f8b
11 months ago
.gitattributes
Safe
1.52 kB
initial commit
11 months ago
README.md
Safe
20.4 kB
Upload README.md
11 months ago
config.json
Safe
3.07 kB
GPTQ model commit
11 months ago
generation_config.json
Safe
164 Bytes
GPTQ model commit
11 months ago
merges.txt
Safe
1.05 MB
GPTQ model commit
11 months ago
model.safetensors
Safe
20.9 GB
LFS
GPTQ model commit
11 months ago
quantize_config.json
Safe
132 Bytes
GPTQ model commit
11 months ago
special_tokens_map.json
Safe
174 Bytes
GPTQ model commit
11 months ago
tokenizer_config.json
Safe
260 Bytes
GPTQ model commit
11 months ago
visual.py
Safe
14.7 kB
GPTQ model commit
11 months ago
vocab.json
Safe
3.39 MB
GPTQ model commit
11 months ago