lebe1
/

opt-125m-8bit

Text Generation

text-generation-inference

8-bit precision

Model card Files Files and versions

413 MB

1 contributor

History: 4 commits

lebe1's picture

AutoGPTQ model for facebook/opt-125m: 8 bits

0dc8b1a about 2 years ago

.gitattributes
1.52 kB

initial commit about 2 years ago
config.json
1.45 kB

AutoGPTQ model for facebook/opt-125m: 8 bits about 2 years ago
generation_config.json
137 Bytes

AutoGPTQ model for facebook/opt-125m: 8 bits about 2 years ago
gptq_model-8bit-128g.safetensors
245 MB
xet

AutoGPTQ model for facebook/opt-125m: 8bits, gr128, desc_act=False about 2 years ago
model.safetensors
168 MB
xet

AutoGPTQ model for facebook/opt-125m: 8bits about 2 years ago
quantize_config.json
240 Bytes

AutoGPTQ model for facebook/opt-125m: 8bits, gr128, desc_act=False about 2 years ago