Oscar-1 demo: gradio app over the published 17m/32m deciders

README.md

@@ -1,13 +1,25 @@
 ---
-title: Oscar 1 Demo
-emoji: 📉
-colorFrom: pink
-colorTo: pink
+title: Oscar-1 Decision Demo
+emoji: 🎯
+colorFrom: indigo
+colorTo: purple
 sdk: gradio
-sdk_version: 6.28.0
-python_version: '3.13'
 app_file: app.py
-pinned: false
+license: apache-2.0
+short_description: RLCD-calibrated deciders 00b7 choice 00b7 score 00b7 noul
+tags:
+- laya
+- rlcd
+- calibrated-classification
+- ettin
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Oscar-1 demo — loads [mgoeckel/oscar-1-17m](https://huggingface.co/mgoeckel/oscar-1-17m) and
+[mgoeckel/oscar-1-32m](https://huggingface.co/mgoeckel/oscar-1-32m) (RLCD-calibrated
+Laya-compatible decision encoders on Ettin backbones) and serves the full calibrated
+decision surface: **choice** label probabilities, **score** expected level 0–4 with the full
+level distribution, and **noul** calibrated binary confidence — all in one forward pass
+through the stock `laya.Agent` seam.
+
+Benchmark (typed-decisions, 400 cases): 32M **0.701** acc / Brier 0.087; 17M 0.678 / 0.104 —
+at 2.5 ms vs hosted jev's ~710 ms at 0.727.

app.py

@@ -0,0 +1,142 @@
+import os
+import warnings
+
+warnings.filterwarnings("ignore")
+
+import gradio as gr  # noqa: E402
+from huggingface_hub import snapshot_download  # noqa: E402
+from laya import Agent  # noqa: E402
+
+REPOS = {
+    "Oscar-1 17M": "mgoeckel/oscar-1-17m",
+    "Oscar-1 32M": "mgoeckel/oscar-1-32m",
+}
+DEFAULT_OPTIONS = "refund, cancel, information, other"
+URGENCY_LEVELS = ["routine", "low", "moderate", "high", "critical"]
+
+_agents = {}
+_cache_root = os.environ.get("OSCAR_CACHE", "oscar_models")
+
+
+def get_agent(model_key: str) -> Agent:
+    if model_key not in _agents:
+        local = os.path.join(_cache_root, model_key.split()[-1].lower())
+        snapshot_download(REPOS[model_key], local_dir=local)
+        _agents[model_key] = Agent(local)
+    return _agents[model_key]
+
+
+def decide(model_key, text, options_raw, urgency_instructions, sensitive_instructions):
+    text = (text or "").strip()
+    if not text:
+        raise gr.Error("Enter a message to classify.")
+
+    questions = {}
+    options = [o.strip() for o in (options_raw or "").split(",") if o.strip()]
+    if len(options) >= 2:
+        questions["intent"] = {
+            "type": "choice",
+            "instructions": "What does the customer want?",
+            "criteria": options,
+        }
+    if (urgency_instructions or "").strip():
+        questions["urgency"] = {
+            "type": "score",
+            "instructions": urgency_instructions.strip(),
+            "criteria": list(URGENCY_LEVELS),
+        }
+    if (sensitive_instructions or "").strip():
+        questions["sensitive"] = {
+            "type": "noul",
+            "instructions": sensitive_instructions.strip(),
+            "criteria": {"true": "sensitive", "false": "not sensitive"},
+        }
+    if not questions:
+        raise gr.Error("Enable at least one question (add intent options or fill a prompt).")
+
+    answers = get_agent(model_key).predict({"text": text}, questions)["answers"]
+
+    intent_label = urgency_label = noul_label = None
+    lines = [f"**Model:** {model_key}", ""]
+    if "intent" in answers:
+        a = answers["intent"]
+        probs = {k: float(v) for k, v in a["probabilities"].items()}
+        intent_label = probs
+        lines += [
+            f"- **Intent:** `{a['choice']}` at **{a['answer_confidence']:.1%}** confidence",
+        ]
+    if "urgency" in answers:
+        a = answers["urgency"]
+        levels = {f"{int(k)} · {URGENCY_LEVELS[int(k)]}": float(v) for k, v in a["probabilities"].items()}
+        urgency_label = levels
+        lines += [
+            f"- **Urgency score:** **{a['score']:.2f}** (expected level, 0–4) — top level "
+            f"`{max(levels, key=levels.get)}` at {a['answer_confidence']:.1%}",
+        ]
+    if "sensitive" in answers:
+        a = answers["sensitive"]
+        p_true = float(a["noul"])
+        conf = float(a["confidence"])
+        verdict = "SENSITIVE" if p_true > 0.5 else "not sensitive"
+        noul_label = {"true (sensitive)": p_true, "false (not sensitive)": 1.0 - p_true}
+        lines += [f"- **Sensitive:** {verdict} — **{conf:.1%}** calibrated confidence"]
+    lines += ["", f"*(one forward pass, CPU — p50 latency on RTX 5060 Ti was 2.5–2.6 ms)*"]
+    return intent_label, urgency_label, noul_label, "\n".join(lines)
+
+
+INTRO = """# Oscar-1 — RLCD-calibrated decision models
+
+**Oscar-1** is a series of [Laya](https://huggingface.co/convaiinnovations/laya-typed)-compatible,
+calibrated **decision encoders** trained with RLCD (proper scoring rules: log + spherical + RPS,
+GRPO-style noisy-logit REINFORCE) on [JHU-CLSP Ettin](https://huggingface.co/jhu-clsp) backbones.
+One forward pass answers **choice** (label probabilities), **score** (expected level + full
+distribution) and **noul** (calibrated binary confidence) — post-hoc temperature-calibrated.
+
+| typed-decisions test | acc | Brier | latency p50 | vs published |
+|---|---:|---:|---:|---|
+| **Oscar-1 32M** | **0.701** | 0.087 | **2.5 ms** | laya-typed 0.766 · jev 0.727 @ ~710 ms |
+| **Oscar-1 17M** | 0.678 | 0.104 | **2.6 ms** | ~1/250th of jev's latency |
+
+Weights: [oscar-1-32m](https://huggingface.co/mgoeckel/oscar-1-32m) ·
+[oscar-1-17m](https://huggingface.co/mgoeckel/oscar-1-17m) (Apache-2.0; base encoders MIT).
+Runs the stock `laya.Agent` seam — try editing the intent options and prompts below.
+"""
+
+with gr.Blocks(title="Oscar-1 decision demo") as demo:
+    gr.Markdown(INTRO)
+    with gr.Row():
+        with gr.Column(scale=1):
+            model = gr.Radio(list(REPOS), value="Oscar-1 32M", label="Model")
+            text = gr.Textbox(label="Message",
+                              placeholder="e.g. I was charged twice, please return the money.")
+            options = gr.Textbox(label="Intent options (comma-separated; blank to disable intent question)",
+                                 value=DEFAULT_OPTIONS)
+            urg = gr.Textbox(label="Score prompt (blank to disable score question)",
+                             value="Rate the urgency of this message on a 0 to 4 scale.")
+            sens = gr.Textbox(label="Binary prompt (blank to disable noul question)",
+                              value="Is this request fraud or a security issue?")
+            btn = gr.Button("Decide", variant="primary")
+        with gr.Column(scale=1):
+            out_intent = gr.Label(label="Intent (choice)", num_top_classes=5)
+            out_urgency = gr.Label(label="Urgency level (score 0–4)", num_top_classes=5)
+            out_noul = gr.Label(label="Sensitivity (noul)")
+            out_summary = gr.Markdown()
+
+    btn.click(decide, [model, text, options, urg, sens],
+              [out_intent, out_urgency, out_noul, out_summary])
+    for w in (text, options, urg, sens, model):
+        w.change(decide, [model, text, options, urg, sens],
+                 [out_intent, out_urgency, out_noul, out_summary], show_progress="hidden")
+
+    gr.Examples(
+        examples=[
+            ["Oscar-1 32M", "I was charged twice, please return the money.", DEFAULT_OPTIONS, urg.value, sens.value],
+            ["Oscar-1 32M", "The API has been down since Tuesday and it is blocking our launch.", DEFAULT_OPTIONS, urg.value, sens.value],
+            ["Oscar-1 32M", "Someone tried to take over my account and changed the email.", DEFAULT_OPTIONS, urg.value, sens.value],
+            ["Oscar-1 17M", "How do I reset my password?", DEFAULT_OPTIONS, urg.value, sens.value],
+        ],
+        inputs=[model, text, options, urg, sens],
+    )
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,3 @@
+laya==0.3.20
+transformers>=4.44,<5
+torch