Initial model upload

app.py

@@ -0,0 +1,48 @@
+
+import gradio as gr
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+# Load model from the current directory
+MODEL_PATH = "." 
+
+LABELS = [
+    "Endocrinology Referral", "Nutrition Referral", "Cardiology Referral", "Bariatric Referral", 
+    "Mental Health Screen", "Food Insecurity Discussion", "GLP-1 Prescription", "Follow-up Scheduled"
+]
+
+# Load Model
+print("Loading model...")
+tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
+model = AutoModelForSequenceClassification.from_pretrained(MODEL_PATH)
+
+def analyze_note(text):
+    if not text.strip(): return None
+    
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=320)
+    
+    with torch.no_grad():
+        logits = model(**inputs).logits
+    
+    probs = torch.sigmoid(logits).cpu().numpy()[0]
+    return {label: float(conf) for label, conf in zip(LABELS, probs)}
+
+# Examples for users to click
+examples = [
+    ["VISIT DATE: 11/20/2025\nSUBJECTIVE: 16yo female presents for weight management. Reports trying to walk more.\nPLAN:\n1. Start Zepbound 2.5mg weekly.\n2. Referral to Pediatric Endocrinology.\n3. Consulting Registered Dietitian."],
+    ["HPI: Mom is requesting Wegovy today. PLAN: Discussed Wegovy but insurance denied the Prior Authorization. No medication prescribed. Offered referral to nutrition services but family declined."],
+    ["CC: Ear pain. Social History: Dad mentions he lost his job last week and they are currently using a food pantry. Plan: Amoxicillin."]
+]
+
+# The Interface
+demo = gr.Interface(
+    fn=analyze_note,
+    inputs=gr.Textbox(lines=10, label="Paste Clinical Note Here"),
+    outputs=gr.Label(num_top_classes=8, label="Predicted Actions"),
+    title="🏥 Clinical Note Analyzer (GatorTron)",
+    description="This model identifies referrals, prescriptions, and screenings in unstructured clinical text.",
+    examples=examples,
+    theme=gr.themes.Soft()
+)
+
+demo.launch()

config.json

@@ -0,0 +1,46 @@
+{
+  "architectures": [
+    "MegatronBertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 2560,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "megatron-bert",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_layers": 48,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "tokenizer_type": "BertWordPieceCase",
+  "transformers_version": "4.57.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50176
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d8c94e5f2e566ee36a239f3be55c3a5577eacfce68d0fee594fe5af10396010
+size 4977445672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:435165e5e2c81311bedbe31ecde296c735922d051ce7171f5136dab00433aeba
+size 4982875216

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0553143ad9282d4a9a373c10a9e128dda1d9fe721050d378c72c233560b9619
+size 4930436200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc66899581237a3c9b7e213fded56e73ef9ebb891230df4128069757f006ddd6
+size 760611288

model.safetensors.index.json

@@ -0,0 +1,785 @@
+{
+  "metadata": {
+    "total_parameters": 3912819208,
+    "total_size": 15651276832
+  },
+  "weight_map": {
+    "bert.embeddings.position_embeddings.weight": "model-00001-of-00004.safetensors",
+    "bert.embeddings.token_type_embeddings.weight": "model-00001-of-00004.safetensors",
+    "bert.embeddings.word_embeddings.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.0.attention.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.0.attention.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.0.attention.self.key.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.0.attention.self.key.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.0.attention.self.query.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.0.attention.self.query.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.0.attention.self.value.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.0.attention.self.value.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.0.intermediate.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.0.intermediate.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.0.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.0.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.0.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.0.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.1.attention.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.1.attention.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.1.attention.self.key.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.1.attention.self.key.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.1.attention.self.query.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.1.attention.self.query.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.1.attention.self.value.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.1.attention.self.value.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.1.intermediate.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.1.intermediate.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.1.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.1.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.1.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.1.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.10.attention.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.10.attention.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.10.attention.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.10.attention.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.10.attention.self.key.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.10.attention.self.key.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.10.attention.self.query.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.10.attention.self.query.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.10.attention.self.value.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.10.attention.self.value.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.10.intermediate.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.10.intermediate.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.10.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.10.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.10.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.10.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.11.attention.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.11.attention.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.11.attention.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.11.attention.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.11.attention.self.key.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.11.attention.self.key.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.11.attention.self.query.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.11.attention.self.query.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.11.attention.self.value.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.11.attention.self.value.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.11.intermediate.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.11.intermediate.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.11.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.11.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.11.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.11.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.12.attention.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.12.attention.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.12.attention.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.12.attention.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.12.attention.self.key.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.12.attention.self.key.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.12.attention.self.query.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.12.attention.self.query.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.12.attention.self.value.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.12.attention.self.value.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.12.intermediate.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.12.intermediate.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.12.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.12.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.12.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.12.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.13.attention.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.13.attention.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.13.attention.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.13.attention.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.13.attention.self.key.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.13.attention.self.key.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.13.attention.self.query.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.13.attention.self.query.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.13.attention.self.value.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.13.attention.self.value.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.13.intermediate.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.13.intermediate.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.13.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.13.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.13.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.13.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.14.attention.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.14.attention.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.14.attention.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.14.attention.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.14.attention.self.key.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.14.attention.self.key.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.14.attention.self.query.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.14.attention.self.query.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.14.attention.self.value.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.14.attention.self.value.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.14.intermediate.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.14.intermediate.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.14.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.14.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.14.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.14.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.15.attention.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.15.attention.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.15.attention.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.15.attention.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.15.attention.self.key.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.15.attention.self.key.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.15.attention.self.query.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.15.attention.self.query.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.15.attention.self.value.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.15.attention.self.value.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.15.intermediate.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.15.intermediate.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.15.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.15.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.15.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.15.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.16.attention.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.16.attention.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.16.attention.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.16.attention.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.16.attention.self.key.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.16.attention.self.key.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.16.attention.self.query.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.16.attention.self.query.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.16.attention.self.value.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.16.attention.self.value.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.16.intermediate.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.16.intermediate.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.16.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.16.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.16.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.16.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.17.attention.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.17.attention.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.17.attention.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.17.attention.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.17.attention.self.key.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.17.attention.self.key.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.17.attention.self.query.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.17.attention.self.query.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.17.attention.self.value.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.17.attention.self.value.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.17.intermediate.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.17.intermediate.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.17.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.17.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.17.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.17.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.18.attention.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.18.attention.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.18.attention.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.18.attention.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.18.attention.self.key.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.18.attention.self.key.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.18.attention.self.query.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.18.attention.self.query.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.18.attention.self.value.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.18.attention.self.value.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.18.intermediate.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.18.intermediate.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.18.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.18.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.18.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.18.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.19.attention.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.19.attention.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.19.attention.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.19.attention.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.19.attention.self.key.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.19.attention.self.key.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.19.attention.self.query.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.19.attention.self.query.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.19.attention.self.value.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.19.attention.self.value.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.19.intermediate.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.19.intermediate.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.19.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.19.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.19.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.19.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.2.attention.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.2.attention.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.2.attention.self.key.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.2.attention.self.key.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.2.attention.self.query.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.2.attention.self.query.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.2.attention.self.value.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.2.attention.self.value.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.2.intermediate.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.2.intermediate.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.2.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.2.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.2.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.2.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.20.attention.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.20.attention.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.20.attention.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.20.attention.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.20.attention.self.key.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.20.attention.self.key.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.20.attention.self.query.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.20.attention.self.query.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.20.attention.self.value.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.20.attention.self.value.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.20.intermediate.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.20.intermediate.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.20.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.20.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.20.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.20.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.21.attention.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.21.attention.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.21.attention.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.21.attention.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.21.attention.self.key.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.21.attention.self.key.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.21.attention.self.query.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.21.attention.self.query.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.21.attention.self.value.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.21.attention.self.value.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.21.intermediate.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.21.intermediate.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.21.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.21.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.21.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.21.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.22.attention.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.22.attention.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.22.attention.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.22.attention.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.22.attention.self.key.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.22.attention.self.key.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.22.attention.self.query.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.22.attention.self.query.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.22.attention.self.value.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.22.attention.self.value.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.22.intermediate.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.22.intermediate.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.22.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.22.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.22.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.22.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.23.attention.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.23.attention.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.23.attention.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.23.attention.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.23.attention.self.key.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.23.attention.self.key.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.23.attention.self.query.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.23.attention.self.query.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.23.attention.self.value.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.23.attention.self.value.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.23.intermediate.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.23.intermediate.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.23.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.23.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.23.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.23.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.24.attention.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.24.attention.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.24.attention.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.24.attention.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.24.attention.self.key.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.24.attention.self.key.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.24.attention.self.query.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.24.attention.self.query.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.24.attention.self.value.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.24.attention.self.value.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.24.intermediate.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.24.intermediate.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.24.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.24.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.24.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.24.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.25.attention.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.25.attention.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.25.attention.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.25.attention.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.25.attention.self.key.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.25.attention.self.key.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.25.attention.self.query.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.25.attention.self.query.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.25.attention.self.value.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.25.attention.self.value.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.25.intermediate.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.25.intermediate.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.25.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.25.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.25.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.25.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.26.attention.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.26.attention.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.26.attention.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.26.attention.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.26.attention.self.key.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.26.attention.self.key.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.26.attention.self.query.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.26.attention.self.query.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.26.attention.self.value.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.26.attention.self.value.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.26.intermediate.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.26.intermediate.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.26.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.26.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.26.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.26.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.27.attention.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.27.attention.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.27.attention.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.27.attention.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.27.attention.self.key.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.27.attention.self.key.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.27.attention.self.query.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.27.attention.self.query.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.27.attention.self.value.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.27.attention.self.value.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.27.intermediate.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.27.intermediate.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.27.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.27.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.27.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.27.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.28.attention.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.28.attention.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.28.attention.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.28.attention.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.28.attention.self.key.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.28.attention.self.key.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.28.attention.self.query.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.28.attention.self.query.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.28.attention.self.value.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.28.attention.self.value.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.28.intermediate.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.28.intermediate.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.28.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.28.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.28.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.28.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.29.attention.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.29.attention.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.29.attention.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.29.attention.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.29.attention.self.key.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.29.attention.self.key.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.29.attention.self.query.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.29.attention.self.query.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.29.attention.self.value.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.29.attention.self.value.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.29.intermediate.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.29.intermediate.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.29.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.29.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.29.output.dense.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.29.output.dense.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.3.attention.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.3.attention.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.3.attention.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.3.attention.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.3.attention.self.key.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.3.attention.self.key.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.3.attention.self.query.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.3.attention.self.query.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.3.attention.self.value.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.3.attention.self.value.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.3.intermediate.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.3.intermediate.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.3.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.3.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.3.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.3.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.30.attention.ln.bias": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.30.attention.ln.weight": "model-00002-of-00004.safetensors",
+    "bert.encoder.layer.30.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.30.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.30.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.30.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.30.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.30.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.30.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.30.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.30.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.30.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.30.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.30.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.30.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.30.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.31.attention.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.31.attention.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.31.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.31.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.31.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.31.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.31.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.31.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.31.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.31.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.31.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.31.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.31.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.31.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.31.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.31.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.32.attention.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.32.attention.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.32.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.32.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.32.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.32.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.32.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.32.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.32.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.32.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.32.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.32.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.32.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.32.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.32.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.32.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.33.attention.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.33.attention.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.33.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.33.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.33.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.33.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.33.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.33.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.33.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.33.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.33.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.33.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.33.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.33.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.33.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.33.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.34.attention.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.34.attention.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.34.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.34.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.34.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.34.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.34.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.34.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.34.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.34.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.34.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.34.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.34.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.34.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.34.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.34.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.35.attention.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.35.attention.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.35.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.35.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.35.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.35.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.35.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.35.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.35.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.35.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.35.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.35.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.35.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.35.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.35.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.35.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.36.attention.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.36.attention.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.36.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.36.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.36.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.36.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.36.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.36.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.36.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.36.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.36.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.36.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.36.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.36.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.36.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.36.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.37.attention.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.37.attention.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.37.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.37.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.37.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.37.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.37.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.37.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.37.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.37.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.37.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.37.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.37.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.37.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.37.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.37.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.38.attention.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.38.attention.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.38.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.38.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.38.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.38.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.38.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.38.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.38.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.38.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.38.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.38.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.38.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.38.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.38.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.38.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.39.attention.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.39.attention.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.39.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.39.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.39.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.39.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.39.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.39.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.39.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.39.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.39.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.39.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.39.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.39.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.39.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.39.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.4.attention.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.4.attention.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.4.attention.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.4.attention.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.4.attention.self.key.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.4.attention.self.key.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.4.attention.self.query.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.4.attention.self.query.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.4.attention.self.value.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.4.attention.self.value.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.4.intermediate.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.4.intermediate.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.4.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.4.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.4.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.4.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.40.attention.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.40.attention.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.40.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.40.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.40.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.40.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.40.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.40.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.40.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.40.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.40.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.40.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.40.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.40.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.40.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.40.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.41.attention.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.41.attention.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.41.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.41.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.41.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.41.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.41.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.41.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.41.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.41.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.41.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.41.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.41.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.41.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.41.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.41.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.42.attention.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.42.attention.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.42.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.42.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.42.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.42.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.42.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.42.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.42.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.42.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.42.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.42.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.42.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.42.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.42.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.42.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.43.attention.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.43.attention.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.43.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.43.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.43.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.43.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.43.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.43.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.43.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.43.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.43.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.43.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.43.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.43.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.43.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.43.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.44.attention.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.44.attention.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.44.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.44.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.44.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.44.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.44.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.44.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.44.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.44.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.44.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.44.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.44.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.44.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.44.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.44.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.45.attention.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.45.attention.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.45.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.45.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.45.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.45.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.45.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.45.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.45.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.45.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.45.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.45.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.45.ln.bias": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.45.ln.weight": "model-00003-of-00004.safetensors",
+    "bert.encoder.layer.45.output.dense.bias": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.45.output.dense.weight": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.46.attention.ln.bias": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.46.attention.ln.weight": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.46.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.46.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.46.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.46.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.46.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.46.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.46.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.46.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.46.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.46.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.46.ln.bias": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.46.ln.weight": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.46.output.dense.bias": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.46.output.dense.weight": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.47.attention.ln.bias": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.47.attention.ln.weight": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.47.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.47.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.47.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.47.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.47.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.47.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.47.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.47.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.47.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.47.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.47.ln.bias": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.47.ln.weight": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.47.output.dense.bias": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.47.output.dense.weight": "model-00004-of-00004.safetensors",
+    "bert.encoder.layer.5.attention.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.5.attention.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.5.attention.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.5.attention.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.5.attention.self.key.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.5.attention.self.key.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.5.attention.self.query.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.5.attention.self.query.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.5.attention.self.value.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.5.attention.self.value.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.5.intermediate.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.5.intermediate.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.5.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.5.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.5.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.5.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.6.attention.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.6.attention.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.6.attention.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.6.attention.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.6.attention.self.key.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.6.attention.self.key.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.6.attention.self.query.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.6.attention.self.query.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.6.attention.self.value.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.6.attention.self.value.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.6.intermediate.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.6.intermediate.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.6.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.6.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.6.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.6.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.7.attention.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.7.attention.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.7.attention.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.7.attention.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.7.attention.self.key.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.7.attention.self.key.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.7.attention.self.query.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.7.attention.self.query.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.7.attention.self.value.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.7.attention.self.value.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.7.intermediate.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.7.intermediate.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.7.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.7.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.7.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.7.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.8.attention.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.8.attention.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.8.attention.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.8.attention.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.8.attention.self.key.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.8.attention.self.key.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.8.attention.self.query.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.8.attention.self.query.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.8.attention.self.value.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.8.attention.self.value.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.8.intermediate.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.8.intermediate.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.8.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.8.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.8.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.8.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.9.attention.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.9.attention.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.9.attention.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.9.attention.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.9.attention.self.key.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.9.attention.self.key.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.9.attention.self.query.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.9.attention.self.query.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.9.attention.self.value.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.9.attention.self.value.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.9.intermediate.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.9.intermediate.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.9.ln.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.9.ln.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.9.output.dense.bias": "model-00001-of-00004.safetensors",
+    "bert.encoder.layer.9.output.dense.weight": "model-00001-of-00004.safetensors",
+    "bert.encoder.ln.bias": "model-00004-of-00004.safetensors",
+    "bert.encoder.ln.weight": "model-00004-of-00004.safetensors",
+    "bert.pooler.dense.bias": "model-00004-of-00004.safetensors",
+    "bert.pooler.dense.weight": "model-00004-of-00004.safetensors",
+    "classifier.bias": "model-00004-of-00004.safetensors",
+    "classifier.weight": "model-00004-of-00004.safetensors"
+  }
+}

requirements.txt

@@ -0,0 +1,4 @@
+
+torch
+transformers
+gradio

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a40d0839c4fc959d28536584361ec8c488b6c31f75aed3706787915c9adcfc5
+size 5841