PrunaAI
/

winglian-llama-3-8b-256k-PoSE-HQQ-2bit-smashed

Text Generation

Inference Endpoints

Model card Files Files and versions Community

winglian-llama-3-8b-256k-PoSE-HQQ-2bit-smashed

1 contributor

History: 2 commits

sharpenb's picture

d106b07ae2d6aac2e921cfb2d1b339bdb1044c2e2d654ad30979a5213f47a476

f98b3b7 verified 8 months ago

.gitattributes

1.52 kB

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

d106b07ae2d6aac2e921cfb2d1b339bdb1044c2e2d654ad30979a5213f47a476 8 months ago