baa-ai
/

GLM-4.7-Flash-SWAN-4bit-MLX

mixed-precision

4-bit precision

Model card Files Files and versions

GLM-4.7-Flash-SWAN-4bit-MLX

18 GB

Ctrl+K

Ctrl+K

2 contributors

History: 9 commits

tomkay's picture

Update model card: use generic language for allocation method

f1fae26 verified about 9 hours ago

.gitattributes

1.57 kB
Upload folder using huggingface_hub 26 days ago
README.md

3.61 kB
Update model card: use generic language for allocation method about 9 hours ago
chat_template.jinja

3.12 kB
Upload folder using huggingface_hub 26 days ago
config.json

21.3 kB
Fix: reconvert with group_size=64 (was 128, broke on dim=192 MLA tensors) 18 days ago
generation_config.json

181 Bytes
Upload folder using huggingface_hub 26 days ago
model-00001-of-00004.safetensors

5.27 GB
xet

Fix: reconvert with group_size=64 (was 128, broke on dim=192 MLA tensors) 18 days ago
model-00002-of-00004.safetensors

5.3 GB
xet

Fix: reconvert with group_size=64 (was 128, broke on dim=192 MLA tensors) 18 days ago
model-00003-of-00004.safetensors

5.32 GB
xet

Fix: reconvert with group_size=64 (was 128, broke on dim=192 MLA tensors) 18 days ago
model-00004-of-00004.safetensors

2.07 GB
xet

Fix: reconvert with group_size=64 (was 128, broke on dim=192 MLA tensors) 18 days ago
model.safetensors.index.json

175 kB
Fix: reconvert with group_size=64 (was 128, broke on dim=192 MLA tensors) 18 days ago
rd-curve.png

60.6 kB
Add rate-distortion curve image 4 days ago
tokenizer.json

20.2 MB
xet

Fix: reconvert with group_size=64 (was 128, broke on dim=192 MLA tensors) 18 days ago
tokenizer_config.json

335 Bytes
Fix: reconvert with group_size=64 (was 128, broke on dim=192 MLA tensors) 18 days ago