Update README.md

README.md

@@ -36,7 +36,7 @@ This model is a strong alternative to Llama 2 70b Chat.
 
 ## Performance
 
-At the time of release, the Tulu-v2-dpo-70b model is approximately equal to GPT4 on AlpacaEval, and has a score of TODO on MT-Bench.
+At the time of release, the Tulu-v2-dpo-70b model is approximately equal to GPT4 on AlpacaEval, and has a score of 7.89 on MT-Bench.
 All smaller DPO'd models have strong performance per model size in the category and with lower verbosity (average completion length).
 | Model | Size | Alignment | MT-Bench (score) | AlpacaEval (win rate %) |
 |-------------|-----|----|---------------|--------------|
@@ -65,11 +65,11 @@ All smaller DPO'd models have strong performance per model size in the category
 
 ## Intended uses & limitations
 
-The model was initially fine-tuned on a filtered and preprocessed of the Tulu V2 mix dataset (TODO add link), which contains a diverse range of human created instructions and synthetic dialogues generated primarily by other LLMs. 
+The model was initially fine-tuned on a filtered and preprocessed of the [Tulu V2 mix dataset](https://huggingface.co/datasets/allenai/tulu-v2-sft-mixture), which contains a diverse range of human created instructions and synthetic dialogues generated primarily by other LLMs. 
 We then further aligned the model with a [Jax DPO trainer](https://github.com/hamishivi/EasyLM/blob/main/EasyLM/models/llama/llama_train_dpo.py) built on [EasyLM](https://github.com/young-geng/EasyLM) on the [openbmb/UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset, which contains 64k prompts and model completions that are ranked by GPT-4. 
 
 
-<!--  You can find the datasets used for training Tulu V2 [here]() -->
+<!--  You can find the datasets used for training Tulu V2 [here]() 
 
 Here's how you can run the model using the `pipeline()` function from 🤗 Transformers:
 
@@ -100,7 +100,7 @@ print(outputs[0]["generated_text"])
 # How many helicopters can a human eat in one sitting?</s>
 # <|assistant|>
 # Ah, me hearty matey! But yer question be a puzzler! A human cannot eat a helicopter in one sitting, as helicopters are not edible. They be made of metal, plastic, and other materials, not food!
-```
+```-->
 
 ## Bias, Risks, and Limitations
 
@@ -112,10 +112,9 @@ It is also unknown what the size and composition of the corpus was used to train
 
 ### Training hyperparameters
 
-The following hyperparameters were used during training:
+The following hyperparameters were used during DPO training:
 - learning_rate: 5e-07
 - total_train_batch_size: 32
-- total_eval_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
@@ -124,10 +123,16 @@ The following hyperparameters were used during training:
 
 ## Citation
 
-If you find Tulu V2 is useful in your work, please cite it with:
+If you find Tulu 2 is useful in your work, please cite it with:
 
 ```
-TODO
+@misc{ivison2023changing,
+   title={Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2}, 
+   author={Hamish Ivison and Yizhong Wang and Valentina Pyatkin and Nathan Lambert and Matthew Peters and Pradeep Dasigi and Joel Jang and David Wadden and Noah A. Smith and Iz Beltagy and Hannaneh Hajishirzi},
+   year={2023},
+   archivePrefix={arXiv},
+   primaryClass={cs.CL}
+}
 ```
 
 *Model card adapted from [Zephyr Beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta/blob/main/README.md)*