mgoin commited on
Commit
4f00955
1 Parent(s): 7c6695e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -17,6 +17,8 @@ tags:
17
  This repo contains a [70% sparse Llama 2 7B](https://huggingface.co/neuralmagic/Llama-2-7b-pruned70-retrained) finetuned for chat tasks using the [UltraChat 200k](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k) dataset.
18
  It was then quantized to 8-bit weights + activations and exported to deploy with [DeepSparse](https://github.com/neuralmagic/deepsparse), a CPU inference runtime for sparse models.
19
 
 
 
20
  **Authors**: Neural Magic, Cerebras
21
 
22
  ## Usage
 
17
  This repo contains a [70% sparse Llama 2 7B](https://huggingface.co/neuralmagic/Llama-2-7b-pruned70-retrained) finetuned for chat tasks using the [UltraChat 200k](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k) dataset.
18
  It was then quantized to 8-bit weights + activations and exported to deploy with [DeepSparse](https://github.com/neuralmagic/deepsparse), a CPU inference runtime for sparse models.
19
 
20
+ Official model weights from [Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment](https://arxiv.org/abs/2405.03594).
21
+
22
  **Authors**: Neural Magic, Cerebras
23
 
24
  ## Usage