Add metadata and paper link (#1)

- Add metadata and paper link (cd40ed60125a69349a23921b373d84e2a53431d7)


Co-authored-by: Niels Rogge <[email protected]>

README.md

@@ -9,6 +9,8 @@ datasets:
 - codingsteven/Llama-3-8B-chat
 language:
 - zh
+metrics:
+- accuracy
 base_model:
 - meta-llama/Llama-3.1-8B
 model-index:
@@ -71,12 +73,15 @@ model-index:
       value: 0.37368330167501296
       stderr: 0.00438421288652232
       verified: false
+pipeline_tag: text-generation
+library_name: transformers
 ---
+
 # Control-LLM-Llama3.1-8B-SynE-Concat16-Lerp
 This is a fine-tuned model of Llama-3.1-8B for muliligual-Chinese tasks on SynE dataset by Control LLM-Concat16-Lerp.
 
 ## Linked Paper
-This model is associated with the paper: [Control-LLM](https://arxiv.org/abs/2501.10979).
+This model is associated with the paper: [Control LLM: Controlled Evolution for Intelligence Retention in LLM](https://huggingface.co/papers/2501.10979).
 
 ## Linked Open Source code - training, eval and benchmark
 This model is associated with the github: [Control-LLM](https://github.com/linkedin/ControlLLM).
@@ -110,4 +115,4 @@ The table below summarizes evaluation results across Chinese tasks and original
 - **MLU**: MMLU (Massive Multitask Language Understanding)
 - **MLUP**: MMLU Pro
 - **O-Avg**: Original Capability - Size Weighted Average across BBH, MLU, and MLUP
-- **Overall**: Combined average across all tasks
+- **Overall**: Combined average across all tasks