Update README.md

README.md

@@ -32,7 +32,7 @@ Convert with the `convert.py` script in this repo:
 
 ```bash
 python3 convert.py --model-id "TheBloke/Llama-2-7B-Chat-GPTQ" --save-path "./marlin-model" --do-generation
-```bash
+```
 
 ### Run Model
 
@@ -47,8 +47,7 @@ model_path = "./marlin-model"
 model = load_model(model_path).to("cuda")
 tokenizer = AutoTokenizer.from_pretrained(model_path)
 
-
-# Run inference to confirm it is working.
+# Generate text.
 inputs = tokenizer("My favorite song is", return_tensors="pt")
 inputs = {k: v.to("cuda") for k, v in inputs.items()}
 outputs = model.generate(**inputs, max_new_tokens=50, do_sample=False)