bayesianflow-for-chem 2.0.0__py3-none-any.whl → 2.0.1__py3-none-any.whl

bayesianflow_for_chem/__init__.py

@@ -17,7 +17,7 @@ __all__ = [
     "MLP",
     "EnsembleChemBFN",
 ]
-__version__ = "2.0.0"
+__version__ = "2.0.1"
 __author__ = "Nianze A. Tao (Omozawa Sueno)"
 
 

bayesianflow_for_chem/cli.py

@@ -78,6 +78,7 @@ epoch = 100
 batch_size = 512
 semi_autoregressive = false
 enable_lora = false
+dynamic_padding = false  # only set to true when pretraining a model
 restart = ""  # or a checkpoint file in absolute path
 dataset = "home/user/project/dataset/qm9.csv"
 molecule_tag = "smiles"
@@ -107,13 +108,24 @@ exclude_duplicate = true  # to only store unique samples
 result_file = "home/user/project/result/result.csv"
 """
 
+_MESSAGE = r"""
+madmadmadmadmadmadmadmadmadmadmadmadmadmadmad
+  __  __    __    ____  __  __  _____  __     
+ (  \/  )  /__\  (  _ \(  \/  )(  _  )(  )    
+  )    (  /(__)\  )(_) ))    (  )(_)(  )(__   
+ (_/\/\_)(__)(__)(____/(_/\/\_)(_____)(____) 
+                 Version {}
+madmadmadmadmadmadmadmadmadmadmadmadmadmadmad
+"""
+
 
 def parse_cli(version: str) -> argparse.Namespace:
     parser = argparse.ArgumentParser(
-        description="MadMol: a CLI molecular design tool for "
+        description="Madmol: a CLI molecular design tool for "
         "de novo design and R-group replacement, "
-        "based on generative route of ChemBFN method.",
-        epilog=f"MadMol {version}, developed in Hiroshima University",
+        "based on generative route of ChemBFN method. "
+        "Let's make some craziest molecules.",
+        epilog=f"Madmol {version}, developed in Hiroshima University",
         formatter_class=argparse.ArgumentDefaultsHelpFormatter,
     )
     parser.add_argument(
@@ -289,6 +301,7 @@ def main_script(version: str) -> None:
         return
     if flag_critical != 0:
         raise RuntimeError
+    print(_MESSAGE.format(version))
     # ####### build tokeniser #######
     tokeniser_config = runtime_config["tokeniser"]
     tokeniser_name = tokeniser_config["name"].lower()
@@ -369,7 +382,6 @@ def main_script(version: str) -> None:
             _mol = ".".join([i[j] for j in mol_idx])
             _data_len.append(tokeniser(_mol).shape[-1])
         lmax = max(_data_len)
-        print(f"maximum sequence length: {lmax}")
         dataset = CSVData(dataset_file)
         dataset.map(
             partial(_encode, mol_tag=mol_tag, obj_tag=obj_tag, tokeniser=tokeniser)
@@ -420,12 +432,13 @@ def main_script(version: str) -> None:
         )
         # ####### build model #######
         if runtime_config["train"]["enable_lora"]:
-            bfn.enable_lora(model_config["ChemBFN"]["channel"] // 128)
+            bfn.enable_lora(bfn.hparam["channel"] // 128)
         model = Model(bfn, mlp, scorer)
         model.model.semi_autoregressive = runtime_config["train"]["semi_autoregressive"]
         # ####### strat training #######
         os.environ["PYTORCH_CUDA_ALLOC_CONF"] = "max_split_size_mb:128"
-        os.environ["MAX_PADDING_LENGTH"] = f"{lmax}"  # important!
+        if not runtime_config["train"]["dynamic_padding"]:
+            os.environ["MAX_PADDING_LENGTH"] = f"{lmax}"  # important!
         torch.set_float32_matmul_precision("medium")
         trainer.fit(
             model,
@@ -442,7 +455,9 @@ def main_script(version: str) -> None:
             "padding_index": 0,
             "start_index": 1,
             "end_index": 2,
-            "padding_strategy": "static",
+            "padding_strategy": (
+                "dynamic" if runtime_config["train"]["dynamic_padding"] else "static"
+            ),
             "padding_length": lmax,
             "label": obj_tag,
             "name": runtime_config["run_name"],

{bayesianflow_for_chem-2.0.0.dist-info → bayesianflow_for_chem-2.0.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: bayesianflow_for_chem
-Version: 2.0.0
+Version: 2.0.1
 Summary: Bayesian flow network framework for Chemistry
 Home-page: https://augus1999.github.io/bayesian-flow-network-for-chemistry/
 Author: Nianze A. Tao
@@ -12,10 +12,9 @@ Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Science/Research
 Classifier: Natural Language :: English
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Scientific/Engineering :: Chemistry
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.11

{bayesianflow_for_chem-2.0.0.dist-info → bayesianflow_for_chem-2.0.1.dist-info}/RECORD

@@ -1,5 +1,5 @@
-bayesianflow_for_chem/__init__.py,sha256=kMTbQWiQ1FFihhW-VWJ9dq_ZKGciIIpNBG7vaux48V0,464
-bayesianflow_for_chem/cli.py,sha256=1RhqleQUEdsuH46XhIeJBklEyq1qzPGKIM59bnsz898,20451
+bayesianflow_for_chem/__init__.py,sha256=gkNLgOEBxs_WfxSVgEJ0u5zPAlfPezvtYUuFZoXLCFE,464
+bayesianflow_for_chem/cli.py,sha256=HPg_XbRqD3ViJ9q90X3TnnwI8RnWRFGyBI13eMBTQX8,21024
 bayesianflow_for_chem/data.py,sha256=WoOCOVmJX4WeHa2WeO4i66J2FS8rvRaYRCdlBN7ZeOM,6576
 bayesianflow_for_chem/model.py,sha256=qpRDEJR9ZhQOP9PSY5IVIG71w-Qg0sZnV-Oo35WvY20,50872
 bayesianflow_for_chem/scorer.py,sha256=gQFUlkyxitch02ntqcRh1ZS8aondKLynW5U6NfTQTb4,4084
@@ -7,9 +7,9 @@ bayesianflow_for_chem/spectra.py,sha256=Ba9ib1aDvTtDYbH3b4d-lIty3ZSQMu7jwehuV2Km
 bayesianflow_for_chem/tool.py,sha256=hjzeUlYrpHwCjyJR6conG8OoCfyHZdxmZyv0NePY6C4,20273
 bayesianflow_for_chem/train.py,sha256=hGKyhGhLch-exSYPZdLXrLn3gf39Q1VLSJs2qtuikQE,9709
 bayesianflow_for_chem/vocab.txt,sha256=HgtAZmpWYk4y8PqEVC4vqut1vE75DfRKE_10s2UW0rU,790
-bayesianflow_for_chem-2.0.0.dist-info/licenses/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
-bayesianflow_for_chem-2.0.0.dist-info/METADATA,sha256=siO9G2ctMva3eLOPbVrwlORHoPQRfpomJRbEN-HmXpQ,5662
-bayesianflow_for_chem-2.0.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-bayesianflow_for_chem-2.0.0.dist-info/entry_points.txt,sha256=N63RMoJsr8rxuKxc7Fj802SL8J5AlpCoPkS8E3IFPLI,54
-bayesianflow_for_chem-2.0.0.dist-info/top_level.txt,sha256=KHsanI3BMCt8D9Qpze2ycrF6nMa3PyojgO6eS1c8kco,22
-bayesianflow_for_chem-2.0.0.dist-info/RECORD,,
+bayesianflow_for_chem-2.0.1.dist-info/licenses/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
+bayesianflow_for_chem-2.0.1.dist-info/METADATA,sha256=YuVMnLW0z8OLzUmR4d90CsygNvqqisp-v3SrDQxxa70,5611
+bayesianflow_for_chem-2.0.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+bayesianflow_for_chem-2.0.1.dist-info/entry_points.txt,sha256=N63RMoJsr8rxuKxc7Fj802SL8J5AlpCoPkS8E3IFPLI,54
+bayesianflow_for_chem-2.0.1.dist-info/top_level.txt,sha256=KHsanI3BMCt8D9Qpze2ycrF6nMa3PyojgO6eS1c8kco,22
+bayesianflow_for_chem-2.0.1.dist-info/RECORD,,