Update README.md

README.md

@@ -7,31 +7,25 @@ pipeline_tag: text-generation
 
 Baby's first adventure with the diffusion language model. Had to quantize this so it would fit on a 3080TI - all I've got!
 
-Used modal to do so: 
-
-```
-"""
-This script uses Modal to quantize the LLaDA family of models.
+Used modal to do so. If you want to replicate what I did, try this:
 
 First, install modal and log into the CLI.
 
-```
 uv add modal
 uv run modal login
-```
 
 Then, add an environment and a volume to the project.
 
-```
+
 uv run modal volume create quantized-model-output
-```
+
 
 Then, run the quantization script:
 
-```
 uv run modal run scripts/quantize_llada.py
+
 ```
-"""
+# scripts/quantize_llada.py
 
 import modal