maderix
/

llama-65b-4bit

Model card Files Files and versions

54.2 GB

1 contributor

History: 4 commits

maderix's picture

Upload llama7b-4bit.pt with huggingface_hub

be1e150 over 2 years ago

.gitattributes

1.48 kB

initial commit over 2 years ago
llama30b-4bit.pt
Detected Pickle imports (5)
- "torch.HalfStorage",
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict",
- "torch.FloatStorage",
- "torch.IntStorage"
What is a pickle import?
17 GB
xet

Upload llama30b-4bit.pt with huggingface_hub over 2 years ago
llama65b-4bit.pt
Detected Pickle imports (5)
- "torch.FloatStorage",
- "collections.OrderedDict",
- "torch._utils._rebuild_tensor_v2",
- "torch.HalfStorage",
- "torch.IntStorage"
What is a pickle import?
33.5 GB
xet

Upload llama65b-4bit.pt with huggingface_hub over 2 years ago
llama7b-4bit.pt
Detected Pickle imports (5)
- "torch.FloatStorage",
- "torch.IntStorage",
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict",
- "torch.HalfStorage"
What is a pickle import?
3.78 GB
xet

Upload llama7b-4bit.pt with huggingface_hub over 2 years ago