Add pipeline tag, link to paper (#1)

- Add pipeline tag, link to paper (029547c60db5337eca28ca90c83c2ab4c95f27cf)


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

README.md

@@ -9,8 +9,12 @@ datasets:
 - codingsteven/Llama-3-8B-chat
 language:
 - zh
+metrics:
+- accuracy
 base_model:
 - meta-llama/Llama-3.1-8B
+pipeline_tag: text-generation
+library_name: transformers
 model-index:
 - name: Control-LLM-Llama3.1-8B-SynE-Concat16-Dlerp
   results:
@@ -74,10 +78,10 @@ model-index:
 ---
 
 # Control-LLM-Llama3.1-8B-SynE-Concat16-Dlerp
-This is a fine-tuned model of Llama-3.1-8B for muliligual-Chinese tasks on SynE dataset by Control LLM-Concat16-Dlerp.
+This is a fine-tuned model of Llama-3.1-8B for muliligual-Chinese tasks on SynE dataset by Control LLM-Concat16-Dlerp, as described in [Control LLM: Controlled Evolution for Intelligence Retention in LLM](https://huggingface.co/papers/2501.10979).
 
 ## 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](https://arxiv.org/abs/2410.14745).
 
 ## Linked Open Source code - training, eval and benchmark
 This model is associated with the github: [Control-LLM](https://github.com/linkedin/ControlLLM).
@@ -111,4 +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