simjeg commited on
Commit
3ff5cda
Β·
1 Parent(s): d75eb4f

Update app.py

Browse files

Signed-off-by: SimJeg <[email protected]>

Files changed (1) hide show
  1. app.py +1 -0
app.py CHANGED
@@ -63,6 +63,7 @@ def gradio_interface():
63
  # Wikipedia Article Question Answering with kvpress
64
  This demo uses the llama 3.1 8B Instruct model to answer questions about any given Wikipedia article.
65
  Under the hood, [kvpress](https://github.com/NVIDIA/kvpress) *compresses the key-value (KV) cache* associated with the article, helping reduce memory usage and accelerate decoding.
 
66
  **How to use:**
67
  1. Enter a Wikipedia article URL
68
  2. Type your question
 
63
  # Wikipedia Article Question Answering with kvpress
64
  This demo uses the llama 3.1 8B Instruct model to answer questions about any given Wikipedia article.
65
  Under the hood, [kvpress](https://github.com/NVIDIA/kvpress) *compresses the key-value (KV) cache* associated with the article, helping reduce memory usage and accelerate decoding.
66
+
67
  **How to use:**
68
  1. Enter a Wikipedia article URL
69
  2. Type your question