Update README.md
af4d45e verified - 1.57 kB Upload tokenizer
- 11.7 kB Update README.md
- 35 Bytes Upload tokenizer
- 1.53 kB Upload tokenizer
- 4.22 kB Upload Gemma3ForConditionalGeneration
- 210 Bytes Upload Gemma3ForConditionalGeneration
- 569 Bytes Create preprocessor_config.json
- 4.96 GB Upload Gemma3ForConditionalGeneration
pytorch_model-00002-of-00003.bin Detected Pickle imports (17)
- "collections.OrderedDict",
- "torch._utils._rebuild_tensor_v3",
- "torchao.quantization.granularity.PerRow",
- "torchao.quantization.Float8Tensor",
- "torch.bfloat16",
- "torchao.float8.inference.Float8MMConfig",
- "torch._tensor._rebuild_from_type_v2",
- "torch.device",
- "torch.serialization._get_layout",
- "torch._utils._rebuild_tensor_v2",
- "torch.FloatStorage",
- "torchao.quantization.quantize_.workflows.float8.float8_tensor.QuantizeTensorToFloat8Kwargs",
- "torch.BFloat16Storage",
- "torchao.quantization.quantize_.common.kernel_preference.KernelPreference",
- "torch.float8_e4m3fn",
- "torch.storage.UntypedStorage",
- "torch._utils._rebuild_wrapper_subclass"
How to fix it?
4.99 GB Upload Gemma3ForConditionalGeneration pytorch_model-00003-of-00003.bin Detected Pickle imports (17)
- "collections.OrderedDict",
- "torch._utils._rebuild_tensor_v3",
- "torchao.quantization.granularity.PerRow",
- "torchao.quantization.Float8Tensor",
- "torch.bfloat16",
- "torchao.float8.inference.Float8MMConfig",
- "torch._tensor._rebuild_from_type_v2",
- "torch.device",
- "torch.serialization._get_layout",
- "torch._utils._rebuild_tensor_v2",
- "torch.FloatStorage",
- "torchao.quantization.quantize_.workflows.float8.float8_tensor.QuantizeTensorToFloat8Kwargs",
- "torch.BFloat16Storage",
- "torchao.quantization.quantize_.common.kernel_preference.KernelPreference",
- "torch.float8_e4m3fn",
- "torch.storage.UntypedStorage",
- "torch._utils._rebuild_wrapper_subclass"
How to fix it?
3.26 GB Upload Gemma3ForConditionalGeneration - 109 kB Upload Gemma3ForConditionalGeneration
- 662 Bytes Upload tokenizer
- 33.4 MB Upload tokenizer
- 4.69 MB Upload tokenizer
- 1.16 MB Upload tokenizer
