Add model card metadata and link to paper and code repository (#1)

- Add model card metadata and link to paper and code repository (ab146d1f70834483a042d8485d695be3d053cccc)


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

README.md

@@ -1,3 +1,9 @@
+---
+pipeline_tag: text-generation
+library_name: transformers
+license: apache-2.0
+---
+
 Quantization made by Richard Erkhov.
 
 [Github](https://github.com/RichardErkhov)
@@ -6,14 +12,13 @@ Quantization made by Richard Erkhov.
 
 [Request more models](https://github.com/RichardErkhov/quant_request)
 
+Paper: [Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment](https://huggingface.co/papers/2410.02197)
+Code: https://github.com/general-preference/general-preference-model
 
 SPPO-Llama-3-8B-Instruct-GPM-2B - bnb 8bits
 - Model creator: https://huggingface.co/general-preference/
 - Original model: https://huggingface.co/general-preference/SPPO-Llama-3-8B-Instruct-GPM-2B/
 
-
-
-
 Original model description:
 ---
 language:
@@ -68,7 +73,7 @@ model-index:
       value: 8.01
       name: exact match
     source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=general-preference/SPPO-Llama-3-8B-Instruct-GPM-2B
+      url: https://huggingface.co/spaces/open-llm_leaderboard/open_llm_leaderboard?query=general-preference/SPPO-Llama-3-8B-Instruct-GPM-2B
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -171,9 +176,6 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_ratio: 0.1
 - num_train_epochs: 6.0 (stop at epoch=1.0)
 
-
-
-  
 ## Citation
 ```
 @article{zhang2024general,
@@ -182,7 +184,4 @@ The following hyperparameters were used during training:
   journal={arXiv preprint arXiv:2410.02197},
   year={2024}
 }
-```
-
-
-
+```