Efficient-ML
/

Qwen3-4B-gptq-w8-128

Model card Files Files and versions Community

Qwen3-4B-gptq-w8-128

Ctrl+K

Ctrl+K

1 contributor

History: 2 commits

HaoranChu's picture

Upload gptq_4B_w8.pth

505600c verified 2 months ago

.gitattributes

1.52 kB

initial commit 2 months ago
gptq_4B_w8.pth
Detected Pickle imports (5)
- "torch.IntStorage",
- "torch._utils._rebuild_tensor_v2",
- "torch.HalfStorage",
- "collections.OrderedDict",
- "torch.BFloat16Storage"
What is a pickle import?
4.5 GB
LFS

Upload gptq_4B_w8.pth 2 months ago