Update README.md

Author: chromecast56

README.md

@@ -1,6 +1,6 @@
 # Training-Free Acivation Sparsity in Large Language Models
 
-[[Paper](https://www.arxiv.org/abs/2408.14690)][[Blog](XXX)]
+[[Paper](https://www.arxiv.org/abs/2408.14690)][[Blog]([XXX](https://www.together.ai/blog/teal-training-free-activation-sparsity-in-large-language-models))]
 
 
 TEAL induces up to 40-50% model-wide activation sparsity in modern LLMs with minimal degradation, resulting in an up to 1.53-1.8x speedup in single-batch decoding.
@@ -132,4 +132,4 @@ CUDA_VISIBLE_DEVICES=0 python teal/ppl_test.py \
 --model_name meta-llama/Llama-2-7b-hf \
 --teal_path $OUTPUT_PATH$ \
 --sparsity 0.5
-```
+```