Update README.md
d74ab45 verified - 1.63 kB Attach ExecuTorch model file and tokenizer to run on-device
- 10.5 kB Update README.md
- 5.6 kB Upload tokenizer
- 4.26 kB Upload SmolLM3ForCausalLM
- 182 Bytes Upload SmolLM3ForCausalLM
pytorch_model.bin Detected Pickle imports (17)
- "torch.device",
- "torch._utils._rebuild_wrapper_subclass",
- "torch._tensor._rebuild_from_type_v2",
- "collections.OrderedDict",
- "torchao.quantization.linear_activation_quantized_tensor.LinearActivationQuantizedTensor",
- "torchao.dtypes.uintx.q_dq_layout.QDQLayout",
- "torch.FloatStorage",
- "torchao.quantization.quant_primitives.ZeroPointDomain",
- "torch.CharStorage",
- "torchao.quantization.quant_api._int8_asymm_per_token_quant",
- "torch._utils._rebuild_tensor_v2",
- "torch.float32",
- "torch.serialization._get_layout",
- "torchao.dtypes.affine_quantized_tensor.AffineQuantizedTensor",
- "torch.BFloat16Storage",
- "torchao.dtypes.uintx.q_dq_layout.QDQTensorImpl",
- "torch.int8"
How to fix it?
4.41 GB Upload SmolLM3ForCausalLM - 1.99 GB Attach ExecuTorch model file and tokenizer to run on-device
- 289 Bytes Upload tokenizer
- 17.2 MB Attach ExecuTorch model file and tokenizer to run on-device
- 50.4 kB Upload tokenizer
