Upload README.md with huggingface_hub

README.md

@@ -19,33 +19,21 @@ base_model:
 
 A tiny, fast **bilingual (EN + RU) word denoiser** — it decides whether a single word form is a
 **meaningful technical term** (keep) or **noise / ballast** (drop). It ships with the
-[UltraCode](https://github.com/faxenoff/ultracode) MCP server, where it runs Stage 6
-(`SYS_BOOTSTRAP`) of the knowledge-graph pipeline: classifying the UNKNOWN word forms harvested from a
-codebase's docs/identifiers so the search vocabulary stays clean.
-
-It **replaces a prompt-based LLM denoiser** (Qwen2.5-Coder-1.5B answering YES/NO per word) with a
-frozen encoder + a trained linear head. On the daemon's bootstrap pass this is **~60× faster**
-(~0.8 s vs ~400 s) at the same quality, runs on the **CPU** (OpenVINO INT8), and never competes with
-the main LLM for VRAM.
+[UltraCode](https://github.com/faxenoff/ultracode) MCP server, where it runs  in the knowledge-graph pipeline: classifying the UNKNOWN word forms harvested from a codebase's docs/identifiers so the search vocabulary stays clean.
 
 - **Frozen encoder** — [`intfloat/multilingual-e5-small`](https://huggingface.co/intfloat/multilingual-e5-small)
   (XLM-RoBERTa, 384-dim), **no weight changes**. Mean-pooling + L2-norm are baked into the graph.
 - **Trained linear head** — a logistic-regression probe (scikit-learn) over the 384-dim embedding,
   **folded with its input scaler into a single affine** `P(keep) = sigmoid(w·e + b)`. Ships as
-  `denoise_head.json` (`{dim, w[384], b, strip_threshold}`) — no Python at runtime; the daemon does
-  the dot product in-process.
-- **Vocab-pruned** — the 250k-token SentencePiece vocab is cut by character class to **Latin +
-  Cyrillic + punctuation (142k tokens)**, lossless for EN + RU, dropping the INT8 weights from ~121 MB
-  to **~76 MB**. The pruned-vocab id map is folded into a remap-Gather at the model input.
+  `denoise_head.json` (`{dim, w[384], b, strip_threshold}`) — no Python at runtime; the daemon does the dot product in-process.
+- **Vocab-pruned** — the 250k-token SentencePiece vocab is cut by character class to **Latin + Cyrillic + punctuation (142k tokens)**, lossless for EN + RU, dropping the INT8 weights from ~121 MB to **~76 MB**. The pruned-vocab id map is folded into a remap-Gather at the model input.
 
 ## How it was made
 
-1. **Encoder**: export the frozen mE5-small to ONNX with mean-pool + L2-norm fused, prune the
-   embedding table to the kept character classes, and PTQ-quantize to INT8 (NNCF) for OpenVINO.
+1. **Encoder**: export the frozen mE5-small to ONNX with mean-pool + L2-norm fused, prune the embedding table to the kept character classes, and PTQ-quantize to INT8 (NNCF) for OpenVINO.
 2. **Head**: embed a bilingual word-label set (EN: WordNet/BNC mid-frequency lemmas; RU:
    Taiga/OpenCorpora/Nerus mid-Zipf) plus per-language manual gold, fit
-   `LogisticRegression(class_weight="balanced")`, then **fold** `StandardScaler` + LR into one
-   `(w, b)`. A `strip_threshold` (default **0.95**) trades strip precision vs recall.
+   `LogisticRegression(class_weight="balanced")`, then **fold** `StandardScaler` + LR into one `(w, b)`. A `strip_threshold` (default **0.95**) trades strip precision vs recall.
 
 Words are embedded with a fixed `"vocab: "` prefix (the daemon pads every candidate word the same
 way) so very short inputs are not dropped by batch de-duplication — the head is trained on the
@@ -89,7 +77,8 @@ scores = p_keep(["mutex", "tensorrt", "пожалуйста", "asdfgh"])
 Pre-compiled, ready-to-run engines named per **runtime × GPU arch × OS** (single `s` bucket):
 
 - **OpenVINO** `*_ov_cpu_int8_b64_s40.{xml,bin}` — Intel/AMD/any CPU, INT8 (the default lane).
-- **TensorRT** `*_{win_x64,linux_x64}_trt_sm_{86,89,120}.engine` — NVIDIA, INT8 (optional GPU lane).
+- **TensorRT** `*_{win_x64,linux_x64}_trt_sm_{86,89,120}.engine` — NVIDIA, BF16 (optional GPU lane;
+  the INT8 lane is OV CPU — this remap-baked SentencePiece ONNX isn't compatible with generic INT8 PTQ).
 - **TVM** `*_b64_s40_{win_x64,…}_tvm_vulkan.{dll,so}` — Vulkan fallback (optional GPU lane).
 - **Head** — `denoise_head.json` (the trained affine; required).
 - **Tokenizer** — `sentencepiece.bpe.model` (+ `tokenizer_config.json`). The daemon feeds raw
@@ -101,7 +90,7 @@ Pre-compiled, ready-to-run engines named per **runtime × GPU arch × OS** (sing
 
 On a frozen held-out word set (EN + RU): **SAFE F1 ≈ 0.79**, BALLAST F1 ≈ 0.84, strip precision ≈
 0.88 at `strip_threshold = 0.95`. The INT8 vocab-pruned build matches the full-vocab FP build (F1 0.79
-vs 0.79) at 38 % of the size. (INT4 was evaluated and rejected: −10 MB for measurable precision loss.)
+vs 0.79) at 38 % of the size.
 
 ## License & attribution