Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+model.onnx_data filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,71 @@
+---
+license: apache-2.0
+base_model: ProCreations/auto-1b
+pipeline_tag: text-classification
+library_name: onnx
+tags:
+  - agent-safety
+  - tool-calling
+  - guardrails
+  - onnx
+---
+
+# auto-1b — ONNX
+
+ONNX exports of [`ProCreations/auto-1b`](https://huggingface.co/ProCreations/auto-1b), a 1B
+encoder that decides whether an AI agent's next tool call is safe to run (**96.40%** on
+[approve-or-deny](https://huggingface.co/datasets/ProCreations/approve-or-deny)).
+
+| file | precision | size |
+|---|---|---|
+| `model.onnx` + `model.onnx_data` | fp32 | 3,935 MiB |
+| `model_int8.onnx` | dynamic int8 | 985 MiB |
+
+## Verified against PyTorch
+
+Both exports were checked against the original model on real benchmark rows:
+
+| export | max abs difference in P(deny) | decision agreement |
+|---|---|---|
+| fp32 | 2.4e-07 | 100% |
+| int8 | 7.5e-01 | 92% |
+
+## Usage
+
+```python
+import numpy as np, onnxruntime as ort
+from transformers import AutoTokenizer
+
+tok = AutoTokenizer.from_pretrained("ProCreations/auto-1b-ONNX")
+sess = ort.InferenceSession("model_int8.onnx", providers=["CPUExecutionProvider"])
+
+def build_input(user_request, history, call):
+    parts = ["### PROPOSED TOOL CALL", f"tool: {call['tool']}", f"args: {call['args']}", "",
+             "### USER REQUEST", user_request, "", "### AGENT HISTORY"]
+    if not history:
+        parts.append("(no prior actions)")
+    else:
+        for i, h in enumerate(history):
+            parts.append(f"[{i+1}] {h['tool']}({h['args']})\n-> {h.get('result','')}")
+    return "\n".join(parts)
+
+text = build_input("clean up build artifacts", [], {"tool": "Bash", "args": "rm -rf node_modules"})
+enc = tok(text, return_tensors="np", truncation=True, max_length=8192)
+logits = sess.run(None, {"input_ids": enc["input_ids"].astype(np.int64),
+                         "attention_mask": enc["attention_mask"].astype(np.int64)})[0]
+p = np.exp(logits[0]) / np.exp(logits[0]).sum()
+print("DENY" if p[1] > 0.5 else "APPROVE", f"P(deny)={p[1]:.3f}")
+```
+
+`logits[:, 1]` after softmax is `P(deny)`. Labels: `0 = approve`, `1 = deny`.
+
+**The input format matters** — the proposed call and user request come first so they survive
+truncation. Use the exact section headers above.
+
+## Context limit
+
+**Practical to ~8k tokens.** The non-flash attention path materialises a dense `(B, 1, L, L)`
+sliding-window mask, so memory grows quadratically with sequence length. That covers the great
+majority of real tool calls (a call plus recent history), but for the full 64k context use the
+PyTorch + flash-attention path in
+[`ProCreations/auto-1b`](https://huggingface.co/ProCreations/auto-1b).

labels.json

@@ -0,0 +1,11 @@
+{
+ "id2label": {
+  "0": "approve",
+  "1": "deny"
+ },
+ "label2id": {
+  "approve": 0,
+  "deny": 1
+ },
+ "note": "logits[:,1] is P(deny) after softmax"
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7158b278cf554b728bfad67580d1b9f8ed2ff4a6e213d5653fe7639470e0afc
+size 1051174

model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3592b3777fc26cb6b327fbb2aed12c1248634d26d79823791422e52cc28c643
+size 4125069312

model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00e06001991b18779185d873c533762be4cc0fef8506eb38dda7fdea06ed04eb
+size 1033022296

tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "max_length": 4096,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 65536,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "tokenizer_class": "TokenizersBackend",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}