Any clue why ``@hf/meta-llama/meta-llama-3-8b-instruct`` is returning the prompt in the response wit

Any clue why @hf/meta-llama/meta-llama-3-8b-instruct is returning the prompt in the response with these tags? Previously it appeared the typical behaviour was to return the actual response which in our scenario would include all text excluding <|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nGenerate a joke from the users response.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n. Can we expect such inconsistencies in a non-beta model?

  const aiResponse = await c.env.AI.run("@hf/meta-llama/meta-llama-3-8b-instruct", {
    max_tokens: 140,
    messages: [
      {
        role: "system",
        content: `Generate a joke from the users response.`,
      },
    ],
  });


{
    "response": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nGenerate a joke from the users response.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nI'd love to! Please provide a topic, a setup, or a pun that you'd like me to build upon, and I'll do my best to create a joke for you.\n\n(Note: You can start with something as simple as a word, a phrase, or a concept, and I'll work with it to create a joke.)"
}
Was this page helpful?