corrected-data model: README.md

README.md

@@ -10,15 +10,20 @@ tags: [tool-calling, agent, function-calling, on-device, webgpu, from-scratch, b
 A **28M-parameter, pretrained-from-scratch, byte-level** agent for tool dispatch. Selection is
 **generable** (no fixed-N classifier): a 5-way **route head** gates modality, a **dense two-tower
 selector** scores *any* tool by its description embedding, and a **pointer head** copies argument
-values from the prompt. 50-tool surface.
+values from the prompt. 50-tool surface. Trained on a corrected, paraphrase-rich + referent-
+conditioned dataset ([danelcsb/localagent-dispatch-data](https://huggingface.co/datasets/danelcsb/localagent-dispatch-data)).
 
-- Free-form out-of-distribution **call-name ~57%**; **multi-turn next-tool selection ~74%**.
-- Pure **PyTorch** (no `transformers`). Load with this repo's `LocalAgentLM` / `ModelConfig`.
+Eval (held, disjoint phrasings + slots):
+- free-form OOD **call-name 53%** / top-1 56% (45 hand-written queries)
+- paraphrase-eval selection **63%** · referent-conditioned (contextual) selection **72%**
+
+Pure **PyTorch** (no `transformers`). Load with this repo's `LocalAgentLM` / `ModelConfig`.
 
 ## Files
-- `model.pt` — PyTorch checkpoint (backbone + ptr_head + dense_selector + route_head + examples).
+- `model.pt` / `model.safetensors` + `config.json` — checkpoint (backbone + ptr + dense_selector + route_head).
 - `model.fp16.onnx` — ONNX graph (`logits`, `hidden`) for the in-browser demo.
 - `dispatch_heads.json` / `heads.json` / `meta.json` — head weights + tokenizer/tool contract.
 
-**Demo:** https://huggingface.co/spaces/danelcsb/localagent-webgpu  ·
+**Demo:** https://huggingface.co/spaces/danelcsb/localagent-webgpu ·
+**Data:** https://huggingface.co/datasets/danelcsb/localagent-dispatch-data ·
 **Code:** https://github.com/sangbumchoi/localagent