PrunaAI
/

llama-moe-LLaMA-MoE-v1-3_5B-4_16-HQQ-2bit-smashed

Text Generation

Model card Files Files and versions Community

llama-moe-LLaMA-MoE-v1-3_5B-4_16-HQQ-2bit-smashed

1 contributor

History: 2 commits

sharpenb's picture

5a53d93a1fcff53a1e1f7f3237f8f4d0cf03a7db95243ca952aa25ef589bb894

2e3b3c7 verified 7 months ago

.gitattributes

1.52 kB

initial commit 7 months ago
qmodel.pt
Detected Pickle imports (8)
- "torch._utils._rebuild_tensor_v2",
- "torch.Size",
- "torch.uint8",
- "torch.float16",
- "torch._utils._rebuild_parameter",
- "collections.OrderedDict",
- "torch.HalfStorage",
- "torch.ByteStorage"
How to fix it?
9.77 GB
LFS

5a53d93a1fcff53a1e1f7f3237f8f4d0cf03a7db95243ca952aa25ef589bb894 7 months ago