Upload folder using huggingface_hub

config.json

@@ -0,0 +1,21 @@
+{
+  "architectures": [
+    "SuaveMultitaskModel"
+  ],
+  "model_type": "suave_multitask",
+  "base_model_name": "roberta-base",
+  "num_ai_classes": 62,
+  "classifier_dropout": 0.1,
+  "id2label": {
+    "0": "human",
+    "1": "ai"
+  },
+  "label2id": {
+    "human": 0,
+    "ai": 1
+  },
+  "auto_map": {
+    "AutoConfig": "configuration_suave_multitask.SuaveMultitaskConfig",
+    "AutoModel": "modeling_suave_multitask.SuaveMultitaskModel"
+  }
+}

prepare_hf_artifacts_light.py

@@ -5,6 +5,7 @@ from pathlib import Path
 
 import torch
 from huggingface_hub import hf_hub_download
+from huggingface_hub.errors import EntryNotFoundError
 
 
 def _normalize_state_dict(raw_obj):
@@ -18,18 +19,27 @@ def _normalize_state_dict(raw_obj):
 
 
 def _download_roberta_tokenizer_files(local_dir: Path):
-    files = [
+    required_files = [
         "tokenizer_config.json",
-        "special_tokens_map.json",
         "vocab.json",
         "merges.txt",
+    ]
+    optional_files = [
+        "special_tokens_map.json",
         "tokenizer.json",
     ]
 
-    for name in files:
+    for name in required_files:
         downloaded = hf_hub_download(repo_id="roberta-base", filename=name)
         shutil.copy2(downloaded, local_dir / name)
 
+    for name in optional_files:
+        try:
+            downloaded = hf_hub_download(repo_id="roberta-base", filename=name)
+            shutil.copy2(downloaded, local_dir / name)
+        except EntryNotFoundError:
+            print(f"Optional tokenizer file not found and skipped: {name}")
+
 
 def main():
     root = Path(".")

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7627394cdadc634e9def45c93d4e044f2403a127531607c4f9dda0fe9a2fa938
+size 498846582

tokenizer_config.json

@@ -0,0 +1 @@
+{"model_max_length": 512}