Update README.md

README.md

@@ -47,6 +47,17 @@ Dataset of highly filtered and curated question and answer pairs. Release TBD.
 
 `lilloukas/Platypus-30B` was instruction fine-tuned using LoRA on 4 A100 80GB. For training details and inference instructions please see the [Platypus-30B](https://github.com/arielnlee/Platypus-30B.git) GitHub repo.
 
+## Reproducing Evaluation Results
+Install LM Evaluation Harness
+```
+git clone https://github.com/EleutherAI/lm-evaluation-harness
+cd lm-evaluation-harness
+pip install -e .
+```
+Each task (arc_challenge|25-shot, hellaswag|10-shot, hendrycksTest-*|5-shot, truthfulqa_mc|0-shot) was evaluated on a single A100 80GB GPU, using the following:
+```
+python main.py --model hf-causal-experimental --model_args pretrained=lilloukas/Platypus-30B --tasks <TASK> --batch_size 1 --no_cache --write_out --output_path results/Platypus-30B/<TASK>.json --device cuda --num_fewshot <NUM_FEWSHOT>
+```
 ## Limitations and bias
 
 The base LLaMA model is trained on various data, some of which may contain offensive, harmful, and biased content that can lead to toxic behavior. See Section 5.1 of the LLaMA paper. We have not performed any studies to determine how fine-tuning on the aforementioned datasets affect the model's behavior and toxicity. Do not treat chat responses from this model as a substitute for human judgment or as a source of truth. Please use responsibly.