Verdict-ready von package (onnx, independent_options)

.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
+von.onnx.data filter=lfs diff=lfs merge=lfs -text

.ms_upload_cache

@@ -0,0 +1 @@
+{"version": 3, "repo_id": "sgyaqing/von", "files": {"von.onnx|1791768534.0|2958691": {"hash": "daa80b0720198922f89eae98a3f41a8e16777b80580a29ea75c79d99718ef289", "size": 2958691, "status": "c"}, "tokenizer/tokenizer.json|1792031265.0|3583486": {"hash": "bb637767e8dfb8044597df6c58243bff2e592ae9e3b310c0bbdb8591f6ac543d", "size": 3583486, "status": "c"}, "von.onnx.data|1791768534.0|1581240320": {"hash": "d5b804c5ceb8f096daf516cccf0fce7a77028b25ec3031ba9cff09a3a663e121", "size": 1581240320, "status": "c"}, "SHA256SUMS|1792069764.0|497": {"hash": "e32411e9daba590a3ae99f1ccda97c3ddb6f0d5680d3ab9afb4d60be9a015fe5", "size": 497, "status": "c"}, "README.md|1792069656.0|3258": {"hash": "617d6ebc7e045fc51fb61721f334cfb2a07339d2538a0e2a4b83459bfbbaee88", "size": 3258, "status": "c"}, "model.json|1792055637.0|464": {"hash": "1d0beb3f1d96a63a8a12a7904bf51ac99bd926838821657b60bb3b99e90d53d2", "size": 464, "status": "c"}, "tokenizer/tokenizer_config.json|1792031265.0|571": {"hash": "4d2a485d5fd1ee514db180744fc00807c11da34012ac3666744c0377f6c23731", "size": 571, "status": "c"}}}

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+base_model: wfzyx/von
+pipeline_tag: zero-shot-classification
+tags:
+- verdict
+- onnx
+- system-one
+- decision-models
+- von
+- serving
+---
+
+# Von (Verdict-ready)
+
+The [Von](https://huggingface.co/wfzyx/von) System One decision model (ModernBERT-large, 395M, English, 8192-token context), exported to ONNX fp32 and packaged for [Verdict](https://github.com/sgyaqing/verdict) -- a high-performance serving engine for System One decision models. Serve it with one command:
+
+Pick the image that matches the host. The `-v` mounts cache the model, so only the first
+run downloads it.
+
+```bash
+# CPU host
+docker run --rm -p 8080:8080 \
+    -v ~/.cache/huggingface:/root/.cache/huggingface \
+    -v ~/.cache/verdict:/root/.cache/verdict \
+    sgyaqing/verdict:0.2.0-cpu serve verdict-models/von
+
+# GPU host
+docker run --rm --gpus all -p 8080:8080 \
+    -v ~/.cache/huggingface:/root/.cache/huggingface \
+    -v ~/.cache/verdict:/root/.cache/verdict \
+    sgyaqing/verdict:0.2.0-cuda serve verdict-models/von
+```
+
+Add `-e VERDICT_USE_MODELSCOPE=1` and use `sgyaqing/von` to fetch from ModelScope instead of the
+hub; add `-e HF_ENDPOINT=https://hf-mirror.com` if the hub is slow or unreachable.
+
+Endpoints: the standard decision protocols `POST /v1/systemone` and `POST /v1/decisions`, native `POST /v1/choice | /v1/score | /v1/noul`, plus an OpenAI-compatible layer (`/v1/chat/completions`, `/v1/models`).
+
+## Performance
+
+Measured on one machine (RTX 4090, AMD EPYC 7543, 16 threads), end to end over HTTP with
+[`oha`](https://github.com/hatoo/oha) and an identical request body for both servers. The
+baseline is the model author's own server (`von serve`, von-sdk, `--no-chains`); the Verdict
+column is this package. Latencies are per-request P50 / P99 at the stated concurrency. The
+ratios are oriented so that **above 1× means Verdict is ahead** in both: throughput ratio =
+Verdict ÷ baseline, latency ratio = baseline ÷ Verdict.
+
+| concurrency | Verdict rps | Verdict P50 / P99 | `von` rps | `von` P50 / P99 | ratio rps | ratio P50 / P99 |
+|---|---:|---:|---:|---:|---:|---:|
+| 1 | 113.8 | 8.61 / 11.98 ms | 46.4 | 22.89 / 28.46 ms | 2.45× | 2.66 / 2.38× |
+| 8 | 536.4 | 14.86 / 16.61 ms | 31.2 | 250.91 / 435.99 ms | 17.2× | 16.9 / 26.2× |
+| 64 | 1476.1 | 42.58 / 53.24 ms | 22.3 | 2848.80 / 3333.40 ms | 66.1× | 66.9 / 62.6× |
+
+## Files
+
+| File | Purpose |
+|---|---|
+| `model.json` | manifest: graph file name, budgets, family recipe (`independent_options`), calibration map |
+| `von.onnx` + `von.onnx.data` | the ONNX graph (fp32, external weights) |
+| `tokenizer/tokenizer.json` (+ `tokenizer_config.json`) | the tokenizer |
+| `SHA256SUMS` | checksums for every file above |
+
+## Provenance & fidelity
+
+Weights are unchanged from `wfzyx/von`; this repo adds only the ONNX export and the serving manifest. Conversion and serving are verified against the official model (von-sdk 1.3.7): identical answers on CPU (29-case golden corpus, logit parity ≤ 4.6e-5) and on CUDA (RTX 4090, logit parity ≤ 7.4e-5, batch invariance bitwise).
+
+## License
+
+Apache-2.0, inherited from the base model. Credit for the model itself belongs to the [original author](https://huggingface.co/wfzyx); this repository only repackages it for serving.

SHA256SUMS

@@ -0,0 +1,6 @@
+617d6ebc7e045fc51fb61721f334cfb2a07339d2538a0e2a4b83459bfbbaee88  README.md
+1d0beb3f1d96a63a8a12a7904bf51ac99bd926838821657b60bb3b99e90d53d2  model.json
+daa80b0720198922f89eae98a3f41a8e16777b80580a29ea75c79d99718ef289  von.onnx
+d5b804c5ceb8f096daf516cccf0fce7a77028b25ec3031ba9cff09a3a663e121  von.onnx.data
+bb637767e8dfb8044597df6c58243bff2e592ae9e3b310c0bbdb8591f6ac543d  tokenizer/tokenizer.json
+4d2a485d5fd1ee514db180744fc00807c11da34012ac3666744c0377f6c23731  tokenizer/tokenizer_config.json

model.json

@@ -0,0 +1,21 @@
+{
+  "family": "independent_options",
+  "runtime": "ort",
+  "graph": "von.onnx",
+  "max_len": 8192,
+  "cls_token": "[CLS]",
+  "sep_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sliding_window": 64,
+  "calibration_formula": {
+    "bias": 2.0151,
+    "entropy": -3.2369,
+    "log_tokens": 11.4916,
+    "n_options": -3.5574,
+    "lo": 0.3,
+    "hi": 12.0
+  },
+  "noul_band": {"edge": 0.8, "slope": 0.1},
+  "noul_prior": {"a": -0.5, "b": 0.3}
+}

tokenizer/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": 2048,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "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]"
+}

von.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daa80b0720198922f89eae98a3f41a8e16777b80580a29ea75c79d99718ef289
+size 2958691

von.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5b804c5ceb8f096daf516cccf0fce7a77028b25ec3031ba9cff09a3a663e121
+size 1581240320