PrunaAI
/

cognitivecomputations-Llama-3-8B-Instruct-abliterated-v2-HQQ-4bit-smashed

Text Generation

Inference Endpoints

Model card Files Files and versions Community

cognitivecomputations-Llama-3-8B-Instruct-abliterated-v2-HQQ-4bit-smashed

1 contributor

History: 2 commits

sharpenb's picture

0bfc7df561810e8825e5201aa6c2a1f2a27ef05fc47021bb59b805c11cfa8945

93e5514 verified 5 months ago

.gitattributes

1.52 kB

initial commit 5 months ago
qmodel.pt
Detected Pickle imports (8)
- "torch._utils._rebuild_parameter",
- "torch.uint8",
- "torch.ByteStorage",
- "torch.Size",
- "collections.OrderedDict",
- "torch.float16",
- "torch._utils._rebuild_tensor_v2",
- "torch.HalfStorage"
How to fix it?
5.76 GB
LFS

0bfc7df561810e8825e5201aa6c2a1f2a27ef05fc47021bb59b805c11cfa8945 5 months ago