21.4 GB

Ctrl+K

1 contributor

History: 18 commits

caiovicentino1

Remove legacy polar_config.json

06a40d2 verified 10 days ago

.gitattributes

1.57 kB
Upload folder using huggingface_hub 20 days ago
POLARQUANT_GEMMA4_31B_INFERENCE.ipynb

26.6 kB
Upload POLARQUANT_GEMMA4_31B_INFERENCE.ipynb with huggingface_hub 20 days ago
POLARQUANT_UNIFIED_GEMMA4_31B.ipynb

57.2 kB
Upload POLARQUANT_UNIFIED_GEMMA4_31B.ipynb with huggingface_hub 20 days ago
README.md

6.66 kB
HLWQ rebrand: title, tags, notice, self-links 10 days ago
chat_template.jinja

12 kB
Upload folder using huggingface_hub 20 days ago
config.json

4.77 kB
fix: quant_method polar -> polarengine for vLLM compatibility 17 days ago
context_chart.png

49.3 kB
Upload context_chart.png with huggingface_hub 20 days ago
generation_config.json

208 Bytes
Update config + tokenizer 20 days ago
hlwq_config.json

389 Bytes
Add hlwq_config.json (rename from polar_config.json) 10 days ago
kv_speed_chart.png

41.7 kB
Upload kv_speed_chart.png with huggingface_hub 20 days ago
model_int4.pt
Detected Pickle imports (14)
- "torchao.dtypes.uintx.tensor_core_tiled_layout.TensorCoreTiledAQTTensorImpl",
- "torch.bfloat16",
- "torchao.quantization.quant_primitives.ZeroPointDomain",
- "torchao.dtypes.uintx.tensor_core_tiled_layout.TensorCoreTiledLayout",
- "torch._tensor._rebuild_from_type_v2",
- "torch._utils._rebuild_wrapper_subclass",
- "torch.int32",
- "torch.IntStorage",
- "torch.device",
- "torch.serialization._get_layout",
- "collections.OrderedDict",
- "torchao.dtypes.affine_quantized_tensor.AffineQuantizedTensor",
- "torch.BFloat16Storage",
- "torch._utils._rebuild_tensor_v2"
How to fix it?
21.4 GB
xet

Add INT4 model weights (torch.save, 21.5 GB) 20 days ago
tokenizer.json

32.2 MB
xet

Upload folder using huggingface_hub 20 days ago
tokenizer_config.json

2.69 kB
Upload folder using huggingface_hub 20 days ago

Detected Pickle imports (14)