21.9 GB

Ctrl+K

2 contributors

History: 19 commits

caiovicentino1

docs: add HLWQ rebrand notice (cite Han et al. PolarQuant prior art)

493ee3e verified 3 days ago

.gitattributes

1.57 kB
Upload tokenizer.json with huggingface_hub 10 days ago
README.md

5.09 kB
docs: add HLWQ rebrand notice (cite Han et al. PolarQuant prior art) 3 days ago
chat_template.jinja

12 kB
Update chat_template.jinja (#1) 8 days ago
compression.png

60.6 kB
Upload compression.png with huggingface_hub 10 days ago
config.json

4.89 kB
fix: quant_method polar -> polarengine for vLLM compatibility 7 days ago
context.png

45.6 kB
Upload context.png with huggingface_hub 10 days ago
family.png

70.4 kB
Upload family.png with huggingface_hub 10 days ago
model_int4.pt
Detected Pickle imports (14)
- "torch.bfloat16",
- "torch._tensor._rebuild_from_type_v2",
- "torch._utils._rebuild_wrapper_subclass",
- "torchao.quantization.quant_primitives.ZeroPointDomain",
- "torch.device",
- "collections.OrderedDict",
- "torch._utils._rebuild_tensor_v2",
- "torch.IntStorage",
- "torch.int32",
- "torch.serialization._get_layout",
- "torchao.dtypes.uintx.tensor_core_tiled_layout.TensorCoreTiledLayout",
- "torchao.dtypes.affine_quantized_tensor.AffineQuantizedTensor",
- "torchao.dtypes.uintx.tensor_core_tiled_layout.TensorCoreTiledAQTTensorImpl",
- "torch.BFloat16Storage"
How to fix it?
21.8 GB
xet

Add INT4 model (21 GB, direct load) 10 days ago
polar_config.json

437 Bytes
Upload polar_config.json with huggingface_hub 10 days ago
processor_config.json

1.69 kB
Upload processor_config.json with huggingface_hub 10 days ago
tokenizer.json

32.2 MB
xet

Upload tokenizer.json with huggingface_hub 10 days ago
tokenizer_config.json

15 kB
Update tokenizer_config.json (#2) 8 days ago
vram_breakdown.png

64.4 kB
Upload vram_breakdown.png with huggingface_hub 10 days ago

Detected Pickle imports (14)