Update README.md

README.md

@@ -33,7 +33,76 @@ A fine-tuned model for Citation Intent Classification, based on [Qwen 2.5 14B In
 ## Quickstart
 
 ```python 
-# TODO
+# from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# model_name = "Qwen/Qwen2.5-14B-Instruct"
+
+# model = AutoModelForCausalLM.from_pretrained(
+#     model_name,
+#     torch_dtype="auto",
+#     device_map="auto"
+# )
+# tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+system_prompt = """
+# CONTEXT #
+You are an expert researcher tasked with classifying the intent of a citation in a scientific publication.
+
+########
+
+# OBJECTIVE # 
+You will be given a sentence containing a citation. You must classify the intent of the citation by assigning it to one of three predefined classes.
+
+########
+
+# CLASS DEFINITIONS #
+The three (3) possible classes are the following: "background information", "method", "results comparison."
+
+1 - background information: The citation states, mentions, or points to the background information giving more context about a problem, concept, approach, topic, or importance of the problem in the field.
+2 - method: Making use of a method, tool, approach, or dataset.
+3 - results comparison: Comparison of the paper’s results/findings with the results/findings of other work.
+
+########
+
+# RESPONSE RULES #
+- Analyze only the citation marked with the @@CITATION tag.
+- Assign exactly one class to each citation.
+- Respond only with the exact name of one of the following classes: "background information", "method", or "results comparison".
+- Do not provide any explanation or elaboration.
+"""
+
+test_citing_sentence = "Activated PBMC are the basis of the standard PBMC blast assay for HIV-1 neutralization, whereas the various GHOST and HeLa cell lines have all been used in neutralization assays @@CITATION@@."
+
+user_prompt = f"""
+{test_citing_sentence}
+### Question: Which is the most likely intent for this citation?
+a) background information
+b) method
+c) results comparison 
+### Answer:
+"""
+
+messages = [
+    {"role": "system", "content": system_prompt},
+    {"role": "user", "content": user_prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=512
+)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
+
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+# Response: method
 ```
 
 Details about the system prompts and query templates can be found in the paper.