Update README.md

README.md

@@ -8,6 +8,7 @@ datasets:
 - LDJnr/Capybara
 - Intel/orca_dpo_pairs
 - hkust-nlp/deita-10k-v0
+- Anthropic/hh-rlhf
 language:
 - en
 tags:
@@ -124,6 +125,7 @@ print(output)
 * **Developed by**: [Stability AI](https://stability.ai/)
 * **Model type**: `StableLM 2 12B Chat` model is an auto-regressive language model based on the transformer decoder architecture.
 * **Language(s)**: English
+TODO: Check if we want to keep paper link since it's not mentioned in that paper.
 * **Paper**: [Stable LM 2 Chat Technical Report](https://drive.google.com/file/d/1JYJHszhS8EFChTbNAf8xmqhKjogWRrQF/view?usp=sharing)
 * **Library**: [Alignment Handbook](https://github.com/huggingface/alignment-handbook.git)
 * **Finetuned from model**: 
@@ -132,7 +134,7 @@ print(output)
 
 ### Training Dataset
 
-The dataset is comprised of a mixture of open datasets large-scale datasets available on the [HuggingFace Hub](https://huggingface.co/datasets):
+The dataset is comprised of a mixture of open datasets large-scale datasets available on the [HuggingFace Hub](https://huggingface.co/datasets) as well as an internal safety dataset:
 1. SFT Datasets
 - HuggingFaceH4/ultrachat_200k
 - meta-math/MetaMathQA
@@ -142,7 +144,12 @@ The dataset is comprised of a mixture of open datasets large-scale datasets avai
 - LDJnr/Capybara
 - hkust-nlp/deita-10k-v0
 
-2. Preference Datasets:
+2. Safety Datasets:
+- Anthropic/hh-rlhf
+- Internal Safety Dataset
+
+3. Preference Datasets:
+
 
 ## Performance
 
@@ -155,6 +162,7 @@ The dataset is comprised of a mixture of open datasets large-scale datasets avai
 
 ### Training Infrastructure
 
+TODO: Fix this
 * **Hardware**: `StableLM 2 12B Chat` was trained on the Stability AI cluster across 8 nodes with 8 A100 80GBs GPUs for each nodes.
 * **Code Base**: We use our internal script for SFT training and [HuggingFace Alignment Handbook](https://github.com/huggingface/alignment-handbook) for DPO training.
 
@@ -165,11 +173,11 @@ The dataset is comprised of a mixture of open datasets large-scale datasets avai
 The model is intended to be used in chat-like applications. Developers must evaluate the model for safety performance in their specific use case. Read more about [safety and limitations](#limitations-and-bias) below.
 
 ### Limitations and Bias
-​
-This model is not trained against adversarial inputs. We strongly recommend pairing this model with an input and output classifier to prevent harmful responses.
 
-Through our internal red teaming, we discovered that while the model will not output harmful information if not prompted to do so, it will hallucinate many facts. It is also willing to output potentially harmful outputs or misinformation when the user requests it.
-Using this model will require guardrails around your inputs and outputs to ensure that any outputs returned are not misinformation or harmful.
+TODO: Do we need or have a standard template to throw in here now?
+
+We strongly recommend pairing this model with an input and output classifier to prevent harmful responses.
+Using this model will require guardrails around your inputs and outputs to ensure that any outputs returned are not hallucinations.
 Additionally, as each use case is unique, we recommend running your own suite of tests to ensure proper performance of this model.
 Finally, do not use the models if they are unsuitable for your application, or for any applications that may cause deliberate or unintentional harm to others.