Create README.md

README.md

@@ -0,0 +1,28 @@
+---
+datasets:
+- gsm8k
+---
+# mpt-7b-gsm8k
+
+**Paper**: [https://arxiv.org/pdf/xxxxxxx.pdf](https://arxiv.org/pdf/xxxxxxx.pdf)  
+**Code**: https://github.com/neuralmagic/deepsparse/tree/main/research/mpt 
+
+This model was produced from a [MPT-7B base model](https://huggingface.co/neuralmagic/mpt-7b-gsm8k-pt) finetuned on the GSM8k dataset for 2 epochs, pruned to 60% with [SparseGPT](https://arxiv.org/abs/2301.00774) and retrained for 2 epochs with L2 distillation.
+
+GSM8k zero-shot accuracy with [lm-evaluation-harness](https://github.com/neuralmagic/lm-evaluation-harness) : 28.8%
+
+All MPT model weights are available on [SparseZoo](https://sparsezoo.neuralmagic.com/?datasets=gsm8k&ungrouped=true) and CPU speedup for generative inference can be reproduced by following the instructions at [DeepSparse](https://github.com/neuralmagic/deepsparse/tree/main/research/mpt)
+
+
+| Model Links                                                                                               | Compression                       |
+| --------------------------------------------------------------------------------------------------------- | --------------------------------- |
+| [neuralmagic/mpt-7b-gsm8k-quant](https://huggingface.co/neuralmagic/mpt-7b-gsm8k-quant)                   | Quantization (W8A8)               |
+| [neuralmagic/mpt-7b-gsm8k-pruned40-quant](https://huggingface.co/neuralmagic/mpt-7b-gsm8k-pruned40-quant) | Quantization (W8A8) & 40% Pruning |
+| [neuralmagic/mpt-7b-gsm8k-pruned50-quant](https://huggingface.co/neuralmagic/mpt-7b-gsm8k-pruned50-quant) | Quantization (W8A8) & 50% Pruning |
+| [neuralmagic/mpt-7b-gsm8k-pruned60-quant](https://huggingface.co/neuralmagic/mpt-7b-gsm8k-pruned60-quant) | Quantization (W8A8) & 60% Pruning |
+| [neuralmagic/mpt-7b-gsm8k-pruned70-quant](https://huggingface.co/neuralmagic/mpt-7b-gsm8k-pruned70-quant) | Quantization (W8A8) & 70% Pruning |
+| [neuralmagic/mpt-7b-gsm8k-pruned70-quant](https://huggingface.co/neuralmagic/mpt-7b-gsm8k-pruned75-quant) | Quantization (W8A8) & 75% Pruning |
+| [neuralmagic/mpt-7b-gsm8k-pruned80-quant](https://huggingface.co/neuralmagic/mpt-7b-gsm8k-pruned80-quant) | Quantization (W8A8) & 80% Pruning |
+
+
+For general questions on these models and sparsification methods, reach out to the engineering team on our [community Slack](https://join.slack.com/t/discuss-neuralmagic/shared_invite/zt-q1a1cnvo-YBoICSIw3L1dmQpjBeDurQ).