Update README.md

README.md

@@ -21,16 +21,21 @@ datasets:
 The use of this model is governed by the [Llama 2 Community License Agreement](https://ai.meta.com/llama/license/)
 
 ## Description:
-Llama2-13B-SteerLM-RM is a 13 billion parameter language model used as the Reward Model/Attribute Prediction Model in training [Llama2-70B-SteerLM-Chat](https://huggingface.co/nvidia/Llama2-70B-SteerLM-Chat)
-It takes input with context length up to 4,096 tokens. 
+Llama2-13B-SteerLM-RM is a 13 billion parameter language model (with context of up to 4,096 tokens) used as the Reward Model/Attribute Prediction Model in training [Llama2-70B-SteerLM-Chat](https://huggingface.co/nvidia/Llama2-70B-SteerLM-Chat)
 
 Given a conversation with multiple turns between user and assistant, it rates the following attributes (between 0 and 4) for every assistant turn.
 
-1. **Helpfulness**: Overall helpfulness of the response to the prompt.
-2. **Correctness**: Inclusion of all pertinent facts without errors. 
-3. **Coherence**: Consistency and clarity of expression. 
-4. **Complexity**: Intellectual depth required to write response (i.e. whether the response can be written by anyone with basic language competency or requires deep domain expertise).
-5. **Verbosity**: Amount of detail included in the response, relative to what is asked for in the prompt.
+1. **Quality**: Perceived goodness of response 
+2. **Toxicity**: Undesirable elements such as vulgar, harmful or potentially biased responses
+3. **Humor**: Sense of humor within responses
+4. **Creativity**: Willingness to generate non-conventional responses
+5. **Helpfulness**: Overall helpfulness of the response to the prompt.
+6. **Correctness**: Inclusion of all pertinent facts without errors. 
+7. **Coherence**: Consistency and clarity of expression. 
+8. **Complexity**: Intellectual depth required to write response (i.e. whether the response can be written by anyone with basic language competency or requires deep domain expertise).
+9. **Verbosity**: Amount of detail included in the response, relative to what is asked for in the prompt.
+
+The first four attrubutes are taken from the [Open Assistant](https://huggingface.co/datasets/OpenAssistant/oasst1) dataset while the others are taken from [HelpSteer](https://huggingface.co/datasets/nvidia/HelpSteer) dataset
 
 
 HelpSteer Paper : [HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM](http://arxiv.org/abs/2311.09528)