output = replicate.run(
    "hamelsmu/axolotl:2fd11c56a88a369d5c517ff5d6867bafe101172548641ac2651e6231f72efd73",
    input={
        "top_k": 50,
        "top_p": 0.95,
        "do_sample": True,
        "temperature": 0.7,
        "max_new_tokens": 512,
        "prompt_template": "### System:\nBelow is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\nTranslate the input from English to Hinglish\n\n### Input:\n{prompt}\n\n### Response:\n "
    }
)

# The hamelsmu/axolotl model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/hamelsmu/axolotl/api#output-schema
    print(item, end="")

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "hamelsmu/axolotl:2fd11c56a88a369d5c517ff5d6867bafe101172548641ac2651e6231f72efd73",
    "input": {
      "top_k": 50,
      "top_p": 0.95,
      "do_sample": true,
      "temperature": 0.7,
      "max_new_tokens": 512,
      "prompt_template": "### System:\\nBelow is an instruction that describes a task. Write a response that appropriately completes the request.\\n\\n### Instruction:\\nTranslate the input from English to Hinglish\\n\\n### Input:\\n{prompt}\\n\\n### Response:\\n "
    }
  }' \
  https://api.replicate.com/v1/predictions