Update model card: v4 eval results (75% acc, 92% high-risk recall)

README.md

@@ -1,21 +1,179 @@
 ---
-base_model: vadimbelsky/qwen3.5-medical-ft-stage3-dpo
+base_model: vadimbelsky/qwen3.5-medical-ft-stage2
 tags:
 - text-generation-inference
 - transformers
 - unsloth
 - qwen3_5
+- medical
+- triage
+- emergency-medicine
+- dpo
+- rlhf
 license: apache-2.0
 language:
 - en
 ---
 
-# Uploaded finetuned  model
+# Qwen3.5-9B Medical Triage — Stage 3 DPO (v4)
 
-- **Developed by:** vadimbelsky
-- **License:** apache-2.0
-- **Finetuned from model :** vadimbelsky/qwen3.5-medical-ft-stage3-dpo
+Emergency department triage model fine-tuned on Qwen3.5-9B via a 3-stage pipeline:
+**Stage 1** (general medical SFT) → **Stage 2** (ED intake SOAP → ESI decision SFT) → **Stage 3** (DPO alignment to reduce over-triage, this model).
 
-This qwen3_5 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+Quantized to **Q4_K_M GGUF** for on-device inference.
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+---
+
+## Model Description
+
+Given an ED SOAP intake note, the model outputs a structured triage decision:
+- **ESI level** (1–5) with justification
+- Key clinical findings
+- Time-to-provider target
+- Immediate interventions required
+
+**ESI Scale:** 1 = Immediate life threat · 2 = Emergent high-risk · 3 = Urgent stable · 4 = Less urgent · 5 = Non-urgent
+
+---
+
+## Training Pipeline
+
+| Stage | Method | Objective |
+|-------|--------|-----------|
+| 1 | SFT (LoRA r=16) | General medical knowledge (PubMed, clinical guidelines) |
+| 2 | SFT (LoRA r=16) | SOAP note → structured ESI triage decision |
+| 3 | DPO (LoRA r=8) | Reduce over-triage · preserve ESI 1/2 high-risk recall |
+
+### Stage 3 DPO Details
+
+- **Base:** Stage 2 LoRA checkpoint (`vadimbelsky/qwen3.5-medical-ft-stage2`)
+- **Dataset:** `dpo_dataset_v4.jsonl` — 5,413 raw pairs → 7,789 weighted pairs
+- **Loss:** Combined `apo_down × 0.3 + sft × 1.0` (MPO-style)
+- **Beta:** 0.5 · **LR:** 5e-5 · **Epochs:** 0.1 (47 steps)
+- **Batch:** 2 × 8 gradient accumulation = effective 16
+- **ESI label prepending:** All chosen/rejected completions prefixed with explicit ESI label (e.g. `ESI 2 — Emergent (high risk)\n\n...`) to anchor preference signal at token position 0
+
+### Dataset Sources (v4)
+
+| Source | Description | Raw pairs | Weight | Weighted |
+|--------|-------------|-----------|--------|---------|
+| A | Anti-overtriage synthetic (ESI 3→1/2 rejected) | 2,388 | 1× | 2,388 |
+| B | Anti-overtriage synthetic (ESI 4/5→1/2 rejected) | 1,500 | 1× | 1,500 |
+| C / C-haiku | Edge cases (Claude Haiku generated) | 39 | 1× | 39 |
+| D | ESI 1/2 anchor pairs (high-risk recall preservation) | 890 | 3× | 2,670 |
+| E-over | ESI 3 bidirectional — anti-overtriage | 297 | 2× | 594 |
+| E-under | ESI 3 bidirectional — anti-undertriage | 299 | 2× | 598 |
+| **Total** | | **5,413** | | **7,789** |
+
+---
+
+## Evaluation Results
+
+Evaluated on **MIMIC-IV-Ext Triage Instruction Corpus** (MIETIC) — 36 human-expert validated RETAIN cases.
+
+### v4 vs Previous Stages
+
+| Metric | Stage 2 (SFT) | v1 DPO | v2 DPO | v3 DPO | **v4 DPO** | Target |
+|--------|--------------|--------|--------|--------|-----------|--------|
+| Accuracy | ~68% | 55.6% | 50.0% | 27.8% | **75.0%** | >82% |
+| Over-triage rate | ~22% | 22.2% | 30.6% | 0% | **13.9%** | <10% |
+| Under-triage rate | ~8% | 36.1% | 41.7% | 72.2% | **11.1%** | <6% |
+| High-risk recall (ESI 1+2) | ~84% | 76% | 64% | 40% | **92%** | 100% |
+| ESI 3 accuracy | ~45% | ~40% | ~30% | ~0% | **60%** | >65% |
+
+### v4 Detailed Results (MIETIC, n=36)
+
+```
+Samples evaluated   : 36
+ESI level parsed    : 36 / 36
+Correct             : 27
+Accuracy            : 75.0%
+Under-triage rate   : 11.1% (4 cases)
+Over-triage rate    : 13.9% (5 cases)
+High-risk recall    : 92.0% (ESI 1+2, n=25)
+```
+
+**Per-ESI Accuracy:**
+
+| ESI Level | N  | Correct | Accuracy |
+|-----------|----|---------|----------|
+| ESI 1     | 14 | 12      | 85.7%    |
+| ESI 2     | 11 | 9       | 81.8%    |
+| ESI 3     | 5  | 3       | 60.0%    |
+| ESI 4     | 4  | 2       | 50.0%    |
+| ESI 5     | 2  | 1       | 50.0%    |
+
+**Confusion Matrix** (rows = ground truth, cols = predicted):
+
+```
+GT \ Pred  ESI 1  ESI 2  ESI 3  ESI 4  ESI 5
+ESI 1         12      2      0      0      0
+ESI 2          0      9      2      0      0
+ESI 3          0      2      3      0      0
+ESI 4          0      0      2      2      0
+ESI 5          0      0      0      1      1
+```
+
+All remaining errors are ±1 ESI boundary confusions — no catastrophic mis-triage.
+
+---
+
+## Key Lessons from DPO Iteration
+
+- **v1–v3 failure:** IPO/sigmoid loss collapsed when dataset direction was 100% anti-overtriage → catastrophic under-triage regression (40% high-risk recall at worst)
+- **v4 fix:** (1) ESI label prepended at token position 0 for unambiguous preference signal; (2) `apo_down + sft` combined loss preserves ESI 1/2 recall via SFT component; (3) Sources D (ESI 1/2 anchors ×3) + E (ESI 3 bidirectional ×2) balance dataset direction
+
+---
+
+## Usage
+
+```python
+# Requires llama.cpp server running with the Q4_K_M GGUF
+# llama-server --model qwen3.5-medical-ft-stage3-dpo-q4km.gguf --port 8080 -c 4096
+
+from openai import OpenAI
+client = OpenAI(base_url="http://localhost:8080/v1", api_key="none")
+
+SYSTEM_PROMPT = (
+    "You are an expert emergency medicine triage nurse. "
+    "Given a SOAP intake note, provide a structured triage decision including "
+    "ESI level with justification, key clinical findings, time-to-provider target, "
+    "and any immediate interventions required."
+)
+
+response = client.chat.completions.create(
+    model="local",
+    messages=[
+        {"role": "system", "content": SYSTEM_PROMPT},
+        {"role": "user", "content": "<SOAP intake note here>"},
+    ],
+    temperature=0.1,
+    max_tokens=512,
+)
+print(response.choices[0].message.content)
+```
+
+---
+
+## Limitations & Safety
+
+> ⚠️ **This model is for research purposes only. It must NOT be used for clinical decision-making without licensed clinician oversight.**
+
+- Evaluated on 36 MIETIC validation cases — not a clinical trial
+- 11.1% under-triage rate means critical patients may be down-triaged
+- 92% high-risk recall means ~8% of ESI 1/2 patients may be missed
+- Model has not been validated on real ED populations
+- Fine-tuned on synthetic + MIMIC-IV derived data only
+
+---
+
+## Training Infrastructure
+
+- **Hardware:** NVIDIA GB10 (121 GB VRAM), 1 GPU
+- **Framework:** Unsloth 2026.3.4 + TRL DPOTrainer + Transformers 5.2.0
+- **Training time:** ~2 hours (47 steps)
+- **Quantization:** GGUF Q4_K_M via llama.cpp
+
+---
+
+*Fine-tuned with [Unsloth](https://github.com/unslothai/unsloth) 🦥*