Update README.md

README.md

@@ -7,28 +7,24 @@ tags:
 - Patronus AI
 - evaluation
 - hallucination-detection
-license: llama3
+license: cc-by-nc-4.0
 language:
 - en
-base_model: PatronusAI/Llama-3-Patronus-Lynx-8B-Instruct
-pipeline_tag: text-generation
 ---
 
-# QuantFactory/Llama-3-Patronus-Lynx-8B-Instruct-GGUF
-This is quantized version of [PatronusAI/Llama-3-Patronus-Lynx-8B-Instruct](https://huggingface.co/PatronusAI/Llama-3-Patronus-Lynx-8B-Instruct) created using llama.cpp
+# Model Card for Model ID
 
-# Model Description
-
-Lynx is an open-source hallucination evaluation model. Patronus-Lynx-8B-Instruct was trained on a mix of datasets including CovidQA, PubmedQA, DROP, RAGTruth.
+Lynx is an open-source hallucination evaluation model. Patronus-Lynx-70B-Instruct was trained on a mix of datasets including CovidQA, PubmedQA, DROP, RAGTruth.
 The datasets contain a mix of hand-annotated and synthetic data. The maximum sequence length is 8000 tokens. 
 
 
 ## Model Details
 
-- **Model Type:** Patronus-Lynx-8B-Instruct is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct model.
+- **Model Type:** This is a quantized version of Patronus-Lynx-70B-Instruct.
 - **Language:** Primarily English
 - **Developed by:** Patronus AI
-- **License:** [https://llama.meta.com/llama3/license](https://llama.meta.com/llama3/license)
+- **Paper:** [https://arxiv.org/abs/2407.08488](https://arxiv.org/abs/2407.08488)
+- **License:** [ https://creativecommons.org/licenses/by-nc/4.0/](https://creativecommons.org/licenses/by-nc/4.0/)
 
 ### Model Sources
 
@@ -70,7 +66,7 @@ The model will output the score as 'PASS' if the answer is faithful to the docum
 
 ## Training Details
 
-The model was finetuned for 3 epochs using H100s on dataset of size 2400. We use [lion](https://github.com/lucidrains/lion-pytorch) optimizer with lr=5.0e-7. For more details on data generation, please check out our Github repo.
+The model was finetuned for 3 epochs using 32 H100s on dataset of size 2400. We use [lion](https://github.com/lucidrains/lion-pytorch) optimizer with lr=5.0e-7. For more details on data generation, please check out our Github repo.
 
 ### Training Data
 
@@ -80,8 +76,19 @@ We train on 2400 samples consisting of CovidQA, PubmedQA, DROP and RAGTruth samp
 
 The model was evaluated on [PatronusAI/HaluBench](https://huggingface.co/datasets/PatronusAI/HaluBench).
 
-It outperforms GPT-3.5-Turbo, GPT-4-Turbo, GPT-4o and Claude Sonnet. 
+It outperforms GPT-3.5-Turbo, GPT-4-Turbo, GPT-4o and Claude-3-Sonnet. 
+
+## Citation
+If you are using the model, cite using
 
+```
+@article{ravi2024lynx,
+  title={Lynx: An Open Source Hallucination Evaluation Model},
+  author={Ravi, Selvan Sunitha and Mielczarek, Bartosz and Kannappan, Anand and Kiela, Douwe and Qian, Rebecca},
+  journal={arXiv preprint arXiv:2407.08488},
+  year={2024}
+}
+```
 
 ## Model Card Contact
 [@sunitha-ravi](https://huggingface.co/sunitha-ravi)