Update README.md

README.md

@@ -209,49 +209,108 @@ Baseline refers to the original Qwen2.5-7B-Instruct model without fine-tuning.
 | Inference Latency | Baseline | Near Identical |
 | Additional GPU Memory | Baseline | ~50 MB Adapter |
 
-### Key Outcomes
-
-- Product classification improved from 1.0% to 90.8%.
-- Fine-tuning successfully learned CFPB complaint taxonomy.
-- The model generates structured operational data directly from free-form complaints.
-- Significant quality improvements were achieved with minimal inference overhead.
+### Run inference
+
+```python
+def categorise_complaint(complaint_text: str, model, tokenizer) -> dict:
+    messages = [
+        {
+            "role": "system",
+            "content": (
+                "You are a banking complaint classification assistant. "
+                "Given a consumer complaint narrative, extract the CFPB ticket fields "
+                "as a JSON object with keys: product, sub_product, issue, sub_issue."
+            ),
+        },
+        {
+            "role": "user",
+            "content": complaint_text,
+        },
+    ]
+
+    prompt = tokenizer.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=True,
+    )
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+
+    with torch.no_grad():
+        output = model.generate(
+            **inputs,
+            max_new_tokens=128,
+            do_sample=False,
+            pad_token_id=tokenizer.eos_token_id,
+        )
+
+    prompt_len = inputs["input_ids"].shape[1]
+    generated  = tokenizer.decode(output[0][prompt_len:], skip_special_tokens=True)
+    return generated
+
+
+complaint = """
+I reported fraudulent transactions on my debit card and the bank reversed
+my provisional credit without explaining the investigation outcome.
+"""
+
+result = categorise_complaint(complaint, model, tokenizer)
+print(result)
+# {"product": "Checking or savings account", "sub_product": "Checking account",
+#  "issue": "Unauthorized transactions or other transaction problem",
+#  "sub_issue": "Debit card issue"}
+```
 
 ---
 
-## Intended Use Cases
+## Dependencies
 
-- Complaint routing and triage
-- Banking operations automation
-- Regulatory complaint processing
-- Contact center workflow optimization
-- Financial NLP research
+```
+transformers==4.44.0
+peft==0.12.0
+accelerate==0.34.0
+datasets==2.21.0
+torch (ROCm-compatible build for AMD, or standard CUDA build)
+scikit-learn
+rouge-score
+sacrebleu
+nltk
+```
 
 ---
 
 ## Limitations
 
-- CFPB taxonomy specific
-- English-language complaints only
-- Long complaints may require truncation
-- Performance outside consumer finance is untested
+- **CFPB taxonomy only.** The model is trained on and constrained to CFPB Consumer Complaint Database labels. It is not a general-purpose complaint classifier and should not be used with complaint taxonomies from other regulatory bodies or internal systems without retraining.
+- **Issue field accuracy.** The `issue` field (33.6% accuracy) is the weakest link. The CFPB issue taxonomy contains 80+ canonical strings with overlapping phrasing. Expanding training data and further tuning the constrained decoder are the most direct paths to improvement.
+- **English language only.** All training data is in English. Performance on non-English complaints is untested and likely poor.
+- **Context length.** Complaints longer than 1024 tokens will be truncated. Most CFPB complaints are well within this limit, but very long narratives may lose relevant context.
+
+---
+
+## Intended Use
+
+This model is intended for use by:
+- Banking operations teams automating first-touch complaint categorisation
+- Compliance teams processing regulatory complaint filings
+- Contact centre platforms routing incoming complaints before agent assignment
+- Research teams studying LLM adaptation for financial NLP tasks
+
+It is not intended for consumer-facing deployment without human review of outputs, or for use in jurisdictions where automated complaint classification decisions have legal or regulatory implications without appropriate oversight.
 
 ---
 
 ## Training Infrastructure
 
-- AMD Instinct MI300X (192 GB HBM3)
-- ROCm
-- Transformers
-- PEFT
-- PyTorch
+Trained on an AMD Instinct MI300X GPU (192 GB HBM3 VRAM) running ROCm 7.2.4. The training stack is fully ROCm-native — `bitsandbytes` (CUDA-only) is not used. Model precision is bfloat16, which is the native compute type for the CDNA3 architecture.
 
 ---
 
 ## Citation
 
-Consumer Financial Protection Bureau (CFPB)
+If you use this model in research or production, please cite the CFPB Consumer Complaint Database as the data source:
 
+```
+Consumer Financial Protection Bureau (CFPB)
 Consumer Complaint Database
-
 https://www.consumerfinance.gov/data-research/consumer-complaints/
-
+```