bayesianflow-for-chem 1.2.5__py3-none-any.whl → 1.2.7__py3-none-any.whl

bayesianflow_for_chem/__init__.py

@@ -7,5 +7,5 @@ from . import data, tool, train, scorer
 from .model import ChemBFN, MLP
 
 __all__ = ["data", "tool", "train", "scorer", "ChemBFN", "MLP"]
-__version__ = "1.2.5"
+__version__ = "1.2.7"
 __author__ = "Nianze A. Tao (Omozawa Sueno)"

bayesianflow_for_chem/tool.py

@@ -161,6 +161,8 @@ def split_dataset(
     :return:
     :rtype: None
     """
+    if isinstance(file, Path):
+        file = file.__str__()
     assert file.endswith(".csv")
     assert len(split_ratio) == 3
     assert method in ("random", "scaffold")
@@ -170,7 +172,7 @@ def split_dataset(
     raw_data = data[1:]
     smiles_idx = []  # only first index will be used
     for key, h in enumerate(header):
-        if h.lower() == "smiles":
+        if "smiles" in h.lower():
             smiles_idx.append(key)
     assert len(smiles_idx) > 0
     data_len = len(raw_data)
@@ -186,6 +188,14 @@ def split_dataset(
         scaffolds: Dict[str, List] = {}
         for key, d in enumerate(raw_data):
             # compute Bemis-Murcko scaffold
+            if len(smiles_idx) > 1:
+                warnings.warn(
+                    "\033[32;1m"
+                    f"We found {len(smiles_idx)} SMILES strings in a row!"
+                    " Only the first SMILES will be used to compute the molecular scaffold."
+                    "\033[0m",
+                    stacklevel=2,
+                )
             scaffold = MurckoScaffoldSmiles(d[smiles_idx[0]])
             if scaffold in scaffolds:
                 scaffolds[scaffold].append(key)
@@ -492,15 +502,16 @@ def inpaint(
 
 def quantise_model(model: ChemBFN) -> nn.Module:
     """
-    Dynamic quantisation of the trained model.
+    Dynamic quantisation of the trained model to `torch.qint8` data type.
 
     :param model: trained ChemBFN model
     :type model: bayesianflow_for_chem.model.ChemBFN
     :return: quantised model
     :rtype: torch.nn.Module
     """
-    from torch.ao.nn.quantized.modules.utils import _quantize_weight
     from torch.ao.nn.quantized import dynamic
+    from torch.ao.nn.quantized.modules.utils import _quantize_weight
+    from torch.ao.quantization.qconfig import default_dynamic_qconfig
 
     class QuantisedLinear(dynamic.Linear):
         # Modified from https://github.com/pytorch/pytorch/blob/main/torch/ao/nn/quantized/dynamic/modules/linear.py
@@ -543,7 +554,22 @@ def quantise_model(model: ChemBFN) -> nn.Module:
             self._packed_params.requires_grad_(False)
 
         def forward(self, x: Tensor) -> Tensor:
-            result = dynamic.Linear.forward(self, x)
+            if self._packed_params.dtype == torch.qint8:
+                if self.version is None or self.version < 4:
+                    Y = torch.ops.quantized.linear_dynamic(
+                        x, self._packed_params._packed_params
+                    )
+                else:
+                    Y = torch.ops.quantized.linear_dynamic(
+                        x, self._packed_params._packed_params, reduce_range=True
+                    )
+            elif self._packed_params.dtype == torch.float16:
+                Y = torch.ops.quantized.linear_dynamic_fp16(
+                    x, self._packed_params._packed_params
+                )
+            else:
+                raise RuntimeError("Unsupported dtype on dynamic quantized linear!")
+            result = Y.to(x.dtype)
             if self.lora_enabled and isinstance(self.lora_dropout, float):
                 result += (
                     nn.functional.dropout(x, self.lora_dropout, self.training)
@@ -562,11 +588,6 @@ def quantise_model(model: ChemBFN) -> nn.Module:
             if mod.qconfig is not None and mod.qconfig.weight is not None:
                 weight_observer = mod.qconfig.weight()
             else:
-                # We have the circular import issues if we import the qconfig in the beginning of this file:
-                # https://github.com/pytorch/pytorch/pull/24231. The current workaround is to postpone the
-                # import until we need it.
-                from torch.ao.quantization.qconfig import default_dynamic_qconfig
-
                 weight_observer = default_dynamic_qconfig.weight()
             dtype = weight_observer.dtype
             assert dtype in [torch.qint8, torch.float16], (

{bayesianflow_for_chem-1.2.5.dist-info → bayesianflow_for_chem-1.2.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: bayesianflow_for_chem
-Version: 1.2.5
+Version: 1.2.7
 Summary: Bayesian flow network framework for Chemistry
 Home-page: https://augus1999.github.io/bayesian-flow-network-for-chemistry/
 Author: Nianze A. Tao
@@ -39,6 +39,7 @@ Dynamic: description-content-type
 Dynamic: home-page
 Dynamic: keywords
 Dynamic: license
+Dynamic: license-file
 Dynamic: project-url
 Dynamic: provides-extra
 Dynamic: requires-dist

bayesianflow_for_chem-1.2.7.dist-info/RECORD

@@ -0,0 +1,12 @@
+bayesianflow_for_chem/__init__.py,sha256=xYC8F86oe8y40GGqzGGjbbjSXPK16Qci8XqDMjrbxK8,293
+bayesianflow_for_chem/data.py,sha256=9tpRba40lxwrB6aPSJMkxUglEVC3VEQC9wWxhDuz3Q8,7760
+bayesianflow_for_chem/model.py,sha256=HvEvW_xRbkv4eSv5lhd72BJMZkg-ZACEi1DAW3p5Q1Y,35918
+bayesianflow_for_chem/scorer.py,sha256=mV1vX8aBGFra2BE7N8WHihVIo3dXmUdPQIGfSaiuNdk,4084
+bayesianflow_for_chem/tool.py,sha256=yZrWCI3Zi6EHxo3zqCU_ebmzVECaco8Vbx-oTg-rHhg,24118
+bayesianflow_for_chem/train.py,sha256=kj6icGqymUUYopDtpre1oE_wpvpeNilbpzgffBsd1tk,9589
+bayesianflow_for_chem/vocab.txt,sha256=HgtAZmpWYk4y8PqEVC4vqut1vE75DfRKE_10s2UW0rU,790
+bayesianflow_for_chem-1.2.7.dist-info/licenses/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
+bayesianflow_for_chem-1.2.7.dist-info/METADATA,sha256=9v-CEHo1DJGmgwopQiQ68sFEaUZkHzFIhfiNTL2r6mc,5913
+bayesianflow_for_chem-1.2.7.dist-info/WHEEL,sha256=0CuiUZ_p9E4cD6NyLD6UG80LBXYyiSYZOKDm5lp32xk,91
+bayesianflow_for_chem-1.2.7.dist-info/top_level.txt,sha256=KHsanI3BMCt8D9Qpze2ycrF6nMa3PyojgO6eS1c8kco,22
+bayesianflow_for_chem-1.2.7.dist-info/RECORD,,

{bayesianflow_for_chem-1.2.5.dist-info → bayesianflow_for_chem-1.2.7.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.8.0)
+Generator: setuptools (80.3.1)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

bayesianflow_for_chem-1.2.5.dist-info/RECORD

@@ -1,12 +0,0 @@
-bayesianflow_for_chem/__init__.py,sha256=GMGe5nU963qFL6vJ9OZSfqfSyEImC_P2zyUS0cyP3Mg,293
-bayesianflow_for_chem/data.py,sha256=9tpRba40lxwrB6aPSJMkxUglEVC3VEQC9wWxhDuz3Q8,7760
-bayesianflow_for_chem/model.py,sha256=HvEvW_xRbkv4eSv5lhd72BJMZkg-ZACEi1DAW3p5Q1Y,35918
-bayesianflow_for_chem/scorer.py,sha256=mV1vX8aBGFra2BE7N8WHihVIo3dXmUdPQIGfSaiuNdk,4084
-bayesianflow_for_chem/tool.py,sha256=tJjb8q3_orNkj2BYJwz5VxqeaOv55dvqO93_uigLJIk,23221
-bayesianflow_for_chem/train.py,sha256=kj6icGqymUUYopDtpre1oE_wpvpeNilbpzgffBsd1tk,9589
-bayesianflow_for_chem/vocab.txt,sha256=HgtAZmpWYk4y8PqEVC4vqut1vE75DfRKE_10s2UW0rU,790
-bayesianflow_for_chem-1.2.5.dist-info/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
-bayesianflow_for_chem-1.2.5.dist-info/METADATA,sha256=hwEEDW6ipmHpjRjQDKxWk5zqI9jwjsl-yxBpvYn93HQ,5890
-bayesianflow_for_chem-1.2.5.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-bayesianflow_for_chem-1.2.5.dist-info/top_level.txt,sha256=KHsanI3BMCt8D9Qpze2ycrF6nMa3PyojgO6eS1c8kco,22
-bayesianflow_for_chem-1.2.5.dist-info/RECORD,,