Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
TheBloke
/
bloomz-176B-GPTQ
like
19
Text Generation
Transformers
bigscience/xP3
46 languages
bloom
Eval Results
text-generation-inference
arxiv:
2211.01786
License:
bigscience-bloom-rail-1.0
Model card
Files
Files and versions
Community
2
Train
Deploy
Use in Transformers
main
bloomz-176B-GPTQ
2 contributors
History:
19 commits
TheBloke
Update README.md
6e23c46
10 months ago
.gitattributes
1.92 kB
Rename bloomz-splitac to gptq_model-4bit--1g.splitac
10 months ago
README.md
36.1 kB
Update README.md
10 months ago
config.json
666 Bytes
Upload GPTQ split into three parts to avoid HF upload limit
10 months ago
gptq_model-4bit--1g.JOINBEFOREUSE.split-a.safetensors
48.3 GB
LFS
Rename gptq_model-4bit--1g.splitaa to gptq_model-4bit--1g.JOINBEFOREUSE.split-a.safetensors
10 months ago
gptq_model-4bit--1g.JOINBEFOREUSE.split-b.safetensors
48.3 GB
LFS
Rename gptq_model-4bit--1g.splitab to gptq_model-4bit--1g.JOINBEFOREUSE.split-b.safetensors
10 months ago
gptq_model-4bit--1g.JOINBEFOREUSE.split-c.safetensors
4.15 GB
LFS
Rename gptq_model-4bit--1g.splitac to gptq_model-4bit--1g.JOINBEFOREUSE.split-c.safetensors
10 months ago
quantize_config.json
182 Bytes
Upload GPTQ split into three parts to avoid HF upload limit
10 months ago
special_tokens_map.json
85 Bytes
Upload GPTQ split into three parts to avoid HF upload limit
10 months ago
tokenizer.json
14.5 MB
LFS
Upload GPTQ split into three parts to avoid HF upload limit
10 months ago
tokenizer_config.json
222 Bytes
Upload GPTQ split into three parts to avoid HF upload limit
10 months ago