Update README.md

README.md

@@ -11,7 +11,7 @@ base_model:
 
 ## Model Overview
 
-Mistral-NeMo-Minitron-8B-Instruct is a model for generating responses for various text-generation tasks including roleplaying, retrieval augmented generation, and function calling. It is a fine-tuned version of [nvidia/Mistral-NeMo-Minitron-8B-Base](https://huggingface.co/nvidia/Mistral-NeMo-Minitron-8B-Base), which was pruned and distilled from [Mistral-NeMo 12B](https://huggingface.co/nvidia/Mistral-NeMo-12B-Base) using [our LLM compression technique](https://arxiv.org/abs/2407.14679). The model supports a context length of 8,192 tokens.
+Mistral-NeMo-Minitron-8B-Instruct is a model for generating responses for various text-generation tasks including roleplaying, retrieval augmented generation, and function calling. It is a fine-tuned version of [nvidia/Mistral-NeMo-Minitron-8B-Base](https://huggingface.co/nvidia/Mistral-NeMo-Minitron-8B-Base), which was pruned and distilled from [Mistral-NeMo 12B](https://huggingface.co/nvidia/Mistral-NeMo-12B-Base) using [our LLM compression technique](https://arxiv.org/abs/2407.14679). The model was trained using a multi-stage SFT and preference-based alignment technique with [NeMo Aligner](https://github.com/NVIDIA/NeMo-Aligner). For details on the alignment technique, please refer to the [Nemotron-4 340B Technical Report](https://arxiv.org/abs/2406.11704).
 
 Try this model on [build.nvidia.com](https://build.nvidia.com/nvidia/mistral-nemo-minitron-8b-8k-instruct).
 
@@ -88,6 +88,20 @@ pipe = pipeline("text-generation", model="nvidia/Mistral-NeMo-Minitron-8B-Instru
 pipe(messages, max_length=64)
 ```
 
+## Evaluation Results
+
+| Category              | Benchmark             | # Shots | Mistral-NeMo-Minitron-8B-Instruct |
+|-----------------------|-----------------------|---------|-----------------------------------|
+| General               | MMLU                  |       5 |                              70.4 |
+|                       | MT Bench (GPT4-Turbo) |       0 |                              7.86 |
+| Math                  | GMS8K                 |       0 |                              87.1 |
+| Reasoning             | GPQA                  |       0 |                              31.5 |
+| Code                  | HumanEval             |       0 |                              71.3 |
+|                       | MBPP                  |       0 |                              72.5 |
+| Instruction Following | IFEval                |       0 |                              84.4 |
+| Tool Use              | BFCL v2 Live          |       0 |                              67.6 |
+
+
 ## AI Safety Efforts
 
 The Mistral-NeMo-Minitron-8B-Instruct model underwent AI safety evaluation including adversarial testing via three distinct methods: