drawais
/

Qwen3-14B-HQQ-INT4

Text Generation

4-bit precision

Model card Files Files and versions

Qwen3-14B-HQQ-INT4

10.1 GB

Ctrl+K

Ctrl+K

1 contributor

History: 5 commits

drawais's picture

Add context-length recommendation

945820d verified 13 days ago

.gitattributes

1.57 kB
Initial HQQ INT4 release (calibration-free) 14 days ago
README.md

1.53 kB
Add context-length recommendation 13 days ago
chat_template.jinja

4.17 kB
Initial HQQ INT4 release (calibration-free) 14 days ago
config.json

1.68 kB
Initial HQQ INT4 release (calibration-free) 14 days ago
qmodel.pt
Detected Pickle imports (8)
- "torch._utils._rebuild_tensor_v2",
- "torch.bfloat16",
- "torch.ByteStorage",
- "torch.uint8",
- "torch.Size",
- "torch.BFloat16Storage",
- "torch._utils._rebuild_parameter",
- "collections.OrderedDict"
How to fix it?
10.1 GB
xet

Initial HQQ INT4 release (calibration-free) 14 days ago
tokenizer.json

11.4 MB
xet

Initial HQQ INT4 release (calibration-free) 14 days ago
tokenizer_config.json

694 Bytes
Initial HQQ INT4 release (calibration-free) 14 days ago