Updated readme Example Usage to point to notebook on GitHub

README.md

@@ -19,34 +19,16 @@ This model converts legalese into short, human-readable summaries, based on data
 
 ## 💡 Example Usage
 
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
+For complete setup instructions and working inference examples, see:  
+👉 [GitHub Repo: LLaMA3-demo](https://github.com/BQ31X/LLaMA3-demo)
 
-model = AutoModelForCausalLM.from_pretrained(
-    "FlamingNeuron/llama381binstruct_summarize_short_merged",
-    device_map="auto"
-)
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/BQ31X/LLaMA3-demo/blob/main/FlamingNeuron_ModelTest_20250418.ipynb)
 
-tokenizer = AutoTokenizer.from_pretrained(
-    "FlamingNeuron/llama381binstruct_summarize_short_merged"
-)
 
-prompt = """<|begin_of_text|><|start_header_id|>system<|end_header_id|>
+This model expects Meta-style structured prompts with two fields: `original_text` and `reference_summary`. 
+The `original_text` contains the input passage, and the model generates a summary in place of the empty `reference_summary`.
 
-Please convert the following legal content into a short human-readable summary<|eot_id|><|start_header_id|>user<|end_header_id|>
 
-[LEGAL_DOC]by using our services you agree to these terms...[END_LEGAL_DOC]<|eot_id|><|start_header_id|>assistant<|end_header_id|>"""
-
-# Tokenize and move to GPU
-inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
-
-# Generate model response
-outputs = model.generate(**inputs, max_new_tokens=128)
-
-# Decode and print result
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
-
-```
 ## 🏋️ Training Procedure
 
 This model was trained using **Supervised Fine-Tuning (SFT)** on legal document summaries using the [legal_summarization](https://github.com/lauramanor/legal_summarization) dataset. LoRA adapters were applied during training and merged afterward using `merge_and_unload()`.