Upload README.md with huggingface_hub

README.md

@@ -83,16 +83,28 @@ This model is a fine-tuned version of `gemma-4` designed to map candidate skills
 
 ---
 
-## Quickstart (Inference)
+## 📝 Prompt Formatting & Unsloth Usage
 
-### 1. Web Demo
-Test candidate skills directly in your browser:
-👉 [https://huggingface.co/spaces/mazafard/esco-gemma4-demo](https://huggingface.co/spaces/mazafard/esco-gemma4-demo)
+This model was trained using the standardized **Alpaca prompt template**. For optimal occupational classification, format your inputs as follows:
 
-### 2. Loading with Unsloth / Transformers
+### Prompt Template:
+```text
+Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
+
+### Instruction:
+Map the following professional skills and experience to the correct ESCO occupation title and ISCO-08 code.
+
+### Input:
+<ENTER_CANDIDATE_SKILLS_HERE>
+
+### Response:
+```
+
+### Complete Python Inference with Unsloth:
 ```python
 from unsloth import FastLanguageModel
 
+# 1. Load fine-tuned 16-bit or 4-bit model
 model, tokenizer = FastLanguageModel.from_pretrained(
     model_name="mazafard/esco-gemma4",
     max_seq_length=2048,
@@ -101,26 +113,64 @@ model, tokenizer = FastLanguageModel.from_pretrained(
 )
 FastLanguageModel.for_inference(model)
 
-prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
+# 2. Define the Alpaca prompt template
+alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
 
 ### Instruction:
 Map the following professional skills and experience to the correct ESCO occupation title and ISCO-08 code.
 
 ### Input:
-Kubernetes, Docker, Terraform, CI/CD, Python
+{}
 
 ### Response:
 """
-inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
-outputs = model.generate(**inputs, max_new_tokens=64)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+
+# 3. Format input skills
+skills = "Kubernetes, Docker container orchestration, Terraform IaC, CI/CD pipeline automation, Python, Prometheus monitoring, AWS cloud infrastructure"
+
+inputs = tokenizer(
+    [alpaca_prompt.format(skills)],
+    return_tensors="pt"
+).to("cuda")
+
+# 4. Generate deterministic output
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=64,
+    use_cache=True,
+    temperature=0.1,
+    do_sample=False
+)
+
+decoded = tokenizer.decode(outputs[0], skip_special_tokens=True)
+response = decoded.split("### Response:")[-1].strip()
+print("🎯 ESCO Classification Result:
+", response)
 ```
 
-### 3. Ollama Execution
+### Expected Model Output Format:
+```text
+ESCO Occupation Title: Cloud Engineer / DevOps Specialist
+ISCO-08 Code: 2512
+```
+
+---
+
+## ⚡ Edge & Local Runtime Quickstart
+
+### Ollama (Desktop / CLI)
 ```bash
 ollama run hf.co/mazafard/esco-gemma4-GGUF:q4_k_m
 ```
 
+### Apple Silicon Native MLX (macOS)
+```bash
+mlx_lm.generate \
+    --model mazafard/esco-gemma4-MLX \
+    --prompt "### Instruction:\nMap the following professional skills and experience to the correct ESCO occupation title and ISCO-08 code.\n\n### Input:\nKubernetes, Docker, CI/CD\n\n### Response:\n" \
+    --max-tokens 64
+```
+
 ## Training Framework
 - **Base Model**: Google Gemma 4 (4-bit QLoRA)
 - **Fine-Tuning Engine**: [Unsloth](https://github.com/unslothai/unsloth)