Update README.md

README.md

@@ -8,6 +8,8 @@ tags:
 pipeline_tag: text-generation
 ---
 
+![Alt text](https://cdn.discordapp.com/attachments/1064373193982361601/1201679652717076560/codellama70bpythonmlx.png?ex=65cab263&is=65b83d63&hm=9748823267a97da4cda34e932fb93246dfe45de181c941dbad00f345d13973a0&)
+
 # mlx-community/CodeLlama-70b-Python-hf-4bit-MLX
 This model was converted to MLX format from [`codellama/CodeLlama-70b-Python-hf`]().
 Refer to the [original model card](https://huggingface.co/codellama/CodeLlama-70b-Python-hf) for more details on the model.
@@ -21,5 +23,5 @@ pip install mlx-lm
 from mlx_lm import load, generate
 
 model, tokenizer = load("mlx-community/CodeLlama-70b-Python-hf-4bit-MLX")
-response = generate(model, tokenizer, prompt="hello", verbose=True)
+response = generate(model, tokenizer, prompt="<step>Source: user Fibonacci series in Python<step> Source: assistant Destination: user", verbose=True)
 ```