Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
iproskurina
/
bloom-1b7-GPTQ-4bit-g128
like
0
Text Generation
Transformers
Safetensors
48 languages
bloom
gptq
4-bit precision
text-generation-inference
arxiv:
2210.17323
License:
bigscience-bloom-rail-1.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
bloom-1b7-GPTQ-4bit-g128
2.7 GB
1 contributor
History:
24 commits
iproskurina
Update README.md to include GPTQModel usage.
6290f5d
verified
11 months ago
.gitattributes
1.57 kB
Upload tokenizer
about 2 years ago
README.md
2.83 kB
Update README.md to include GPTQModel usage.
11 months ago
config.json
805 Bytes
AutoGPTQ model for bigscience/bloom-1b7: 4bits, gr128, desc_act=False
over 1 year ago
model.safetensors
2.69 GB
xet
Rename gptq_model-4bit-128g.safetensors to model.safetensors
over 1 year ago
quantize_config.json
211 Bytes
AutoGPTQ model for bigscience/bloom-1b7: 4bits, gr128, desc_act=False
over 1 year ago
special_tokens_map.json
552 Bytes
Add tokenizer for the model bloom-1b7
over 1 year ago
tokenizer.json
14.5 MB
xet
Add tokenizer for the model bloom-1b7
over 1 year ago
tokenizer_config.json
983 Bytes
Add tokenizer for the model bloom-1b7
over 1 year ago
