j5ng
/

kullm-12.8b-GPTQ-8bit

Text Generation

Inference Endpoints

Model card Files Files and versions Community

kullm-12.8b-GPTQ-8bit

1 contributor

History: 6 commits

j5ng's picture

Rename pytorch_model.bin to gptq_model-8bit-128g.bin

7ec6a4b about 1 year ago

.gitattributes

1.52 kB

initial commit about 1 year ago
README.md

28 Bytes

initial commit about 1 year ago
config.json

691 Bytes

init about 1 year ago
gptq_model-8bit-128g.bin
Detected Pickle imports (6)
- "torch.HalfStorage",
- "collections.OrderedDict",
- "torch.FloatStorage",
- "torch._utils._rebuild_tensor_v2",
- "torch.BoolStorage",
- "torch.IntStorage"
What is a pickle import?
13.7 GB
LFS

Rename pytorch_model.bin to gptq_model-8bit-128g.bin about 1 year ago
quantize_config.json

184 Bytes

init about 1 year ago
tokenizer.json

1.65 MB

tokenizer about 1 year ago
tokenizer_config.json

210 Bytes

tokenizer about 1 year ago