better error messages

pytorch_pretrained_bert/modeling.py

@@ -646,13 +646,18 @@ class BertPreTrainedModel(nn.Module):
         try:
             resolved_archive_file = cached_path(archive_file, cache_dir=cache_dir)
         except EnvironmentError:
-            logger.error(
-                "Model name '{}' was not found in model name list ({}). "
-                "We assumed '{}' was a path or url but couldn't find any file "
-                "associated to this path or url.".format(
-                    pretrained_model_name_or_path,
-                    ', '.join(PRETRAINED_MODEL_ARCHIVE_MAP.keys()),
-                    archive_file))
+            if pretrained_model_name_or_path in PRETRAINED_MODEL_ARCHIVE_MAP:
+                logger.error(
+                    "Couldn't reach server at '{}' to download pretrained weights.".format(
+                        archive_file))
+            else:
+                logger.error(
+                    "Model name '{}' was not found in model name list ({}). "
+                    "We assumed '{}' was a path or url but couldn't find any file "
+                    "associated to this path or url.".format(
+                        pretrained_model_name_or_path,
+                        ', '.join(PRETRAINED_MODEL_ARCHIVE_MAP.keys()),
+                        archive_file))
             return None
         if resolved_archive_file == archive_file:
             logger.info("loading archive file {}".format(archive_file))

pytorch_pretrained_bert/modeling_gpt2.py

@@ -446,14 +446,19 @@ class GPT2PreTrainedModel(nn.Module):
             resolved_archive_file = cached_path(archive_file, cache_dir=cache_dir)
             resolved_config_file = cached_path(config_file, cache_dir=cache_dir)
         except EnvironmentError:
-            logger.error(
-                "Model name '{}' was not found in model name list ({}). "
-                "We assumed '{}' was a path or url but couldn't find files {} and {} "
-                "at this path or url.".format(
-                    pretrained_model_name_or_path, ", ".join(PRETRAINED_MODEL_ARCHIVE_MAP.keys()), pretrained_model_name_or_path,
-                    archive_file, config_file
+            if pretrained_model_name_or_path in PRETRAINED_MODEL_ARCHIVE_MAP:
+                logger.error(
+                    "Couldn't reach server at '{}' to download pretrained weights.".format(
+                        archive_file))
+            else:
+                logger.error(
+                    "Model name '{}' was not found in model name list ({}). "
+                    "We assumed '{}' was a path or url but couldn't find files {} and {} "
+                    "at this path or url.".format(
+                        pretrained_model_name_or_path, ", ".join(PRETRAINED_MODEL_ARCHIVE_MAP.keys()), pretrained_model_name_or_path,
+                        archive_file, config_file
+                    )
                 )
-            )
             return None
         if resolved_archive_file == archive_file and resolved_config_file == config_file:
             logger.info("loading weights file {}".format(archive_file))

pytorch_pretrained_bert/modeling_openai.py

@@ -472,14 +472,19 @@ class OpenAIGPTPreTrainedModel(nn.Module):
             resolved_archive_file = cached_path(archive_file, cache_dir=cache_dir)
             resolved_config_file = cached_path(config_file, cache_dir=cache_dir)
         except EnvironmentError:
-            logger.error(
-                "Model name '{}' was not found in model name list ({}). "
-                "We assumed '{}' was a path or url but couldn't find files {} and {} "
-                "at this path or url.".format(
-                    pretrained_model_name_or_path, ", ".join(PRETRAINED_MODEL_ARCHIVE_MAP.keys()), pretrained_model_name_or_path,
-                    archive_file, config_file
+            if pretrained_model_name_or_path in PRETRAINED_MODEL_ARCHIVE_MAP:
+                logger.error(
+                    "Couldn't reach server at '{}' to download pretrained weights.".format(
+                        archive_file))
+            else:
+                logger.error(
+                    "Model name '{}' was not found in model name list ({}). "
+                    "We assumed '{}' was a path or url but couldn't find files {} and {} "
+                    "at this path or url.".format(
+                        pretrained_model_name_or_path, ", ".join(PRETRAINED_MODEL_ARCHIVE_MAP.keys()), pretrained_model_name_or_path,
+                        archive_file, config_file
+                    )
                 )
-            )
             return None
         if resolved_archive_file == archive_file and resolved_config_file == config_file:
             logger.info("loading weights file {}".format(archive_file))

pytorch_pretrained_bert/modeling_transfo_xl.py

@@ -926,14 +926,19 @@ class TransfoXLPreTrainedModel(nn.Module):
             resolved_archive_file = cached_path(archive_file, cache_dir=cache_dir)
             resolved_config_file = cached_path(config_file, cache_dir=cache_dir)
         except EnvironmentError:
-            logger.error(
-                "Model name '{}' was not found in model name list ({}). "
-                "We assumed '{}' was a path or url but couldn't find files {} and {} "
-                "at this path or url.".format(
-                    pretrained_model_name_or_path,
-                    ', '.join(PRETRAINED_MODEL_ARCHIVE_MAP.keys()),
-                    pretrained_model_name_or_path,
-                    archive_file, config_file))
+            if pretrained_model_name_or_path in PRETRAINED_MODEL_ARCHIVE_MAP:
+                logger.error(
+                    "Couldn't reach server at '{}' to download pretrained weights.".format(
+                        archive_file))
+            else:
+                logger.error(
+                    "Model name '{}' was not found in model name list ({}). "
+                    "We assumed '{}' was a path or url but couldn't find files {} and {} "
+                    "at this path or url.".format(
+                        pretrained_model_name_or_path,
+                        ', '.join(PRETRAINED_MODEL_ARCHIVE_MAP.keys()),
+                        pretrained_model_name_or_path,
+                        archive_file, config_file))
             return None
         if resolved_archive_file == archive_file and resolved_config_file == config_file:
             logger.info("loading weights file {}".format(archive_file))

pytorch_pretrained_bert/tokenization.py

@@ -181,13 +181,18 @@ class BertTokenizer(object):
         try:
             resolved_vocab_file = cached_path(vocab_file, cache_dir=cache_dir)
         except EnvironmentError:
-            logger.error(
-                "Model name '{}' was not found in model name list ({}). "
-                "We assumed '{}' was a path or url but couldn't find any file "
-                "associated to this path or url.".format(
-                    pretrained_model_name_or_path,
-                    ', '.join(PRETRAINED_VOCAB_ARCHIVE_MAP.keys()),
-                    vocab_file))
+            if pretrained_model_name_or_path in PRETRAINED_VOCAB_ARCHIVE_MAP:
+                logger.error(
+                    "Couldn't reach server at '{}' to download vocabulary.".format(
+                        vocab_file))
+            else:
+                logger.error(
+                    "Model name '{}' was not found in model name list ({}). "
+                    "We assumed '{}' was a path or url but couldn't find any file "
+                    "associated to this path or url.".format(
+                        pretrained_model_name_or_path,
+                        ', '.join(PRETRAINED_VOCAB_ARCHIVE_MAP.keys()),
+                        vocab_file))
             return None
         if resolved_vocab_file == vocab_file:
             logger.info("loading vocabulary file {}".format(vocab_file))

pytorch_pretrained_bert/tokenization_gpt2.py

@@ -113,14 +113,19 @@ class GPT2Tokenizer(object):
             resolved_vocab_file = cached_path(vocab_file, cache_dir=cache_dir)
             resolved_merges_file = cached_path(merges_file, cache_dir=cache_dir)
         except EnvironmentError:
-            logger.error(
-                "Model name '{}' was not found in model name list ({}). "
-                "We assumed '{}' was a path or url but couldn't find files {} and {} "
-                "at this path or url.".format(
-                    pretrained_model_name_or_path,
-                    ', '.join(PRETRAINED_VOCAB_ARCHIVE_MAP.keys()),
-                    pretrained_model_name_or_path,
-                    vocab_file, merges_file))
+            if pretrained_model_name_or_path in PRETRAINED_VOCAB_ARCHIVE_MAP:
+                logger.error(
+                    "Couldn't reach server at '{}' to download vocabulary.".format(
+                        vocab_file))
+            else:
+                logger.error(
+                    "Model name '{}' was not found in model name list ({}). "
+                    "We assumed '{}' was a path or url but couldn't find files {} and {} "
+                    "at this path or url.".format(
+                        pretrained_model_name_or_path,
+                        ', '.join(PRETRAINED_VOCAB_ARCHIVE_MAP.keys()),
+                        pretrained_model_name_or_path,
+                        vocab_file, merges_file))
             return None
         if resolved_vocab_file == vocab_file and resolved_merges_file == merges_file:
             logger.info("loading vocabulary file {}".format(vocab_file))

pytorch_pretrained_bert/tokenization_openai.py

@@ -101,14 +101,19 @@ class OpenAIGPTTokenizer(object):
             resolved_vocab_file = cached_path(vocab_file, cache_dir=cache_dir)
             resolved_merges_file = cached_path(merges_file, cache_dir=cache_dir)
         except EnvironmentError:
-            logger.error(
-                "Model name '{}' was not found in model name list ({}). "
-                "We assumed '{}' was a path or url but couldn't find files {} and {} "
-                "at this path or url.".format(
-                    pretrained_model_name_or_path,
-                    ', '.join(PRETRAINED_VOCAB_ARCHIVE_MAP.keys()),
-                    pretrained_model_name_or_path,
-                    vocab_file, merges_file))
+            if pretrained_model_name_or_path in PRETRAINED_VOCAB_ARCHIVE_MAP:
+                logger.error(
+                    "Couldn't reach server at '{}' to download vocabulary.".format(
+                        vocab_file))
+            else:
+                logger.error(
+                    "Model name '{}' was not found in model name list ({}). "
+                    "We assumed '{}' was a path or url but couldn't find files {} and {} "
+                    "at this path or url.".format(
+                        pretrained_model_name_or_path,
+                        ', '.join(PRETRAINED_VOCAB_ARCHIVE_MAP.keys()),
+                        pretrained_model_name_or_path,
+                        vocab_file, merges_file))
             return None
         if resolved_vocab_file == vocab_file and resolved_merges_file == merges_file:
             logger.info("loading vocabulary file {}".format(vocab_file))

pytorch_pretrained_bert/tokenization_transfo_xl.py

@@ -71,14 +71,19 @@ class TransfoXLTokenizer(object):
         try:
             resolved_vocab_file = cached_path(vocab_file, cache_dir=cache_dir)
         except EnvironmentError:
-            logger.error(
-                "Model name '{}' was not found in model name list ({}). "
-                "We assumed '{}' was a path or url but couldn't find files {} "
-                "at this path or url.".format(
-                    pretrained_model_name_or_path,
-                    ', '.join(PRETRAINED_VOCAB_ARCHIVE_MAP.keys()),
-                    pretrained_model_name_or_path,
-                    vocab_file))
+            if pretrained_model_name_or_path in PRETRAINED_VOCAB_ARCHIVE_MAP:
+                logger.error(
+                    "Couldn't reach server at '{}' to download vocabulary.".format(
+                        vocab_file))
+            else:
+                logger.error(
+                    "Model name '{}' was not found in model name list ({}). "
+                    "We assumed '{}' was a path or url but couldn't find files {} "
+                    "at this path or url.".format(
+                        pretrained_model_name_or_path,
+                        ', '.join(PRETRAINED_VOCAB_ARCHIVE_MAP.keys()),
+                        pretrained_model_name_or_path,
+                        vocab_file))
             return None
         if resolved_vocab_file == vocab_file:
             logger.info("loading vocabulary file {}".format(vocab_file))