PrunaAI
/

mlx-community-gemma-2-2b-it-HQQ-1bit-smashed

Model card Files Files and versions

mlx-community-gemma-2-2b-it-HQQ-1bit-smashed

Ctrl+K

Ctrl+K

1 contributor

History: 2 commits

sharpenb's picture

Upload folder using huggingface_hub (#1)

e1f50a2 verified 9 months ago

.gitattributes

1.57 kB

Upload folder using huggingface_hub (#1) 9 months ago
README.md

5.51 kB

Upload folder using huggingface_hub (#1) 9 months ago
config.json

888 Bytes

Upload folder using huggingface_hub (#1) 9 months ago
qmodel.pt
Detected Pickle imports (8)
- "torch.ByteStorage",
- "torch.uint8",
- "torch._utils._rebuild_tensor_v2",
- "torch.HalfStorage",
- "torch._utils._rebuild_parameter",
- "collections.OrderedDict",
- "torch.Size",
- "torch.float16"
How to fix it?
1.48 GB
xet

Upload folder using huggingface_hub (#1) 9 months ago
smash_config.json

1.02 kB

Upload folder using huggingface_hub (#1) 9 months ago
special_tokens_map.json

555 Bytes

Upload folder using huggingface_hub (#1) 9 months ago
tokenizer.json

17.5 MB
xet

Upload folder using huggingface_hub (#1) 9 months ago
tokenizer.model

4.24 MB
xet

Upload folder using huggingface_hub (#1) 9 months ago
tokenizer_config.json

46.9 kB

Upload folder using huggingface_hub (#1) 9 months ago