Add pipeline tag and library name (#1)

- Add pipeline tag and library name (1c849fdd5969bf4661b537cdb509336f10de74fd)


Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

README.md

@@ -1,12 +1,15 @@
 ---
-license: mit
+base_model:
+- meta-llama/Meta-Llama-3-8B-Instruct
 datasets:
 - wangkevin02/LMSYS-USP
 language:
 - en
-base_model:
-- meta-llama/Meta-Llama-3-8B-Instruct
+license: mit
+pipeline_tag: text-generation
+library_name: transformers
 ---
+
 # Profile Generator
 
 ## Model Description
@@ -20,8 +23,6 @@ The **Profile Generator** is a model designed to extract and generate detailed u
 | LMSYS-USP | GPT4o          | 86.89 | 25.64           | 82.24 | 3.71           | 84.50 | 4.42         |
 | LMSYS-USP | Distill-llama3 | 86.15 | 23.81           | 81.95 | 3.71           | 84.00 | 4.36         |
 
-
-
 > *Note*: Our model is subject to the following constraints:
 >
 > 1. **Maximum Context Length**: Supports up to **4,096 tokens**. Exceeding this may degrade performance; keep inputs within this limit for best results.
@@ -67,10 +68,13 @@ def extract_user_messages(messages: List[Dict[str, str]]) -> List[str]:
 # Prepare messages for model input
 def prepare_messages(utterances: List[str], config: ProfileConfig, tokenizer) -> str:
     """Prepare messages for model input with optimized formatting."""
-    user_prompt = "".join(f"[User]: {u}\n---\n" for u in utterances)
+    user_prompt = "".join(f"[User]: {u}
+---
+" for u in utterances)
     formatted_msg = [
         {"role": "system", "content": config.system_prompt},
-        {"role": "user", "content": f"{config.instruction}\n{user_prompt}"}
+        {"role": "user", "content": f"{config.instruction}
+{user_prompt}"}
     ]
     return tokenizer.apply_chat_template(
         formatted_msg,
@@ -168,8 +172,6 @@ print(f"profile:{profile}")
 
 ## Citation
 
-
-
 If you find this model useful, please cite:
 
 ```plaintext