Expose main checkpoint at repository root for Hub indexing

.gitattributes

@@ -1,46 +1,4 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
-data/processed/r8_5class_train.jsonl filter=lfs diff=lfs merge=lfs -text
-data/processed/enriched_13class_train.jsonl filter=lfs diff=lfs merge=lfs -text
-data/processed/enriched_5class_train.jsonl filter=lfs diff=lfs merge=lfs -text
-data/processed/enriched_5class_train_cleaned_trimmed.jsonl filter=lfs diff=lfs merge=lfs -text
-data/processed/r8_5class_train_propagated.jsonl filter=lfs diff=lfs merge=lfs -text
-data/processed/enriched_5class_train_cleaned.jsonl filter=lfs diff=lfs merge=lfs -text
-data/processed/r7_5class_train.jsonl filter=lfs diff=lfs merge=lfs -text
-data/processed/r9_5class_train.jsonl filter=lfs diff=lfs merge=lfs -text
-data/processed/enriched_5class_train_cleaned_deleaked.jsonl filter=lfs diff=lfs merge=lfs -text
-data/processed/backup/enriched_13class_train.jsonl filter=lfs diff=lfs merge=lfs -text
-data/processed/backup/enriched_5class_train.jsonl filter=lfs diff=lfs merge=lfs -text

README.md

@@ -12,6 +12,7 @@ tags:
 - moe
 - span-detection
 base_model: openai/privacy-filter
+base_model_relation: finetune
 pipeline_tag: token-classification
 ---
 
@@ -176,13 +177,13 @@ Sanity-check fine-tune on 50 examples to validate the training pipeline end-to-e
 # Install the base framework
 pip install -e vendor/privacy-filter
 
-# Run inference with the R8 checkpoint
-opf --checkpoint checkpoints/r8_5class/epoch_4 --device cpu \
+# Run inference with the default R8 checkpoint at the repository root
+opf --checkpoint . --device cpu \
   "APT29 deployed Cobalt Strike beacon via CVE-2021-44228 against Microsoft Exchange servers."
 
 # Evaluate on a JSONL test file
 opf eval data/processed/cyner_test.jsonl \
-  --checkpoint checkpoints/r8_5class/epoch_4 \
+  --checkpoint . \
   --device cpu
 
 # Fine-tune further with a custom dataset
@@ -213,8 +214,10 @@ opf train my_train.jsonl \
 
 ```
 arcspan/
+├── config.json                 ← Main checkpoint config for Hugging Face Hub indexing
+├── model.safetensors           ← Main R8 checkpoint weights for Hugging Face Hub indexing
 ├── checkpoints/
-│   ├── r8_5class/epoch_4/      ← Main checkpoint (model.safetensors + config.json)
+│   ├── r8_5class/epoch_4/      ← Archived copy of main checkpoint
 │   └── cyner_v1_sanity/        ← Sanity-check checkpoint
 ├── data/
 │   ├── processed/              ← Training/eval JSONL splits (all benchmarks)

config.json

@@ -0,0 +1,59 @@
+{
+  "bidirectional_context": true,
+  "bidirectional_left_context": 128,
+  "bidirectional_right_context": 128,
+  "category_version": "cyner_v1",
+  "default_n_ctx": 128000,
+  "encoding": "o200k_base",
+  "experts_per_token": 4,
+  "head_dim": 64,
+  "hidden_size": 640,
+  "inference_contract_version": 1,
+  "initial_context_length": 4096,
+  "intermediate_size": 640,
+  "max_position_embeddings": 131072,
+  "model_type": "privacy_filter",
+  "ner_class_names": [
+    "O",
+    "B-Malware",
+    "I-Malware",
+    "E-Malware",
+    "S-Malware",
+    "B-Indicator",
+    "I-Indicator",
+    "E-Indicator",
+    "S-Indicator",
+    "B-System",
+    "I-System",
+    "E-System",
+    "S-System",
+    "B-Organization",
+    "I-Organization",
+    "E-Organization",
+    "S-Organization",
+    "B-Vulnerability",
+    "I-Vulnerability",
+    "E-Vulnerability",
+    "S-Vulnerability"
+  ],
+  "num_attention_heads": 14,
+  "num_experts": 128,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 2,
+  "num_labels": 21,
+  "param_dtype": "bfloat16",
+  "rope_ntk_alpha": 1.0,
+  "rope_ntk_beta": 32.0,
+  "rope_scaling_factor": 32.0,
+  "rope_theta": 150000,
+  "sliding_window": 257,
+  "span_class_names": [
+    "O",
+    "Malware",
+    "Indicator",
+    "System",
+    "Organization",
+    "Vulnerability"
+  ],
+  "vocab_size": 200064
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4b901e80d256fe774fcf161ac3b430a31b2b3be975118806f59806e546d0680
+size 2798968616