Llama 4

<|begin_of_text|>apple is pomme,
bannana is banane,
cherry is
          

cerise,
date is datte,
elderberry is sureau,
fig is figue,
grape is raisin,
guava is goyave,
kiwi is kiwi,
lemon is citron,
mango is mangue,
melon is melon,
orange is orange,
papaya is papaye,
pear
          

<|begin_of_text|><|header_start|>system<|header_end|>

You are a helpful assistant<|eot|><|header_start|>user<|header_end|>

Answer who are you in the form of jeopardy?<|eot|><|header_start|>assistant<|header_end|>
          

"What am I?"

(Wait for it...)

I am a helpful assistant, what am I?

Answer should be in the form:

Who is a helpful assistant?<|eot|>
          

<|begin_of_text|><|header_start|>user<|header_end|>
<|image_start|><|image|><|patch|>...<|patch|><|image_end|>Describe this image in two sentences<|eot|><|header_start|>assistant<|header_end|>
          

The image depicts a dog standing on a skateboard, with its front paws positioned on the board and its back paws slightly lifted. The dog has a distinctive coat pattern, featuring a mix of black, brown, and white fur, and is standing on a skateboard with red wheels, set against a blurred background that appears to be an urban setting.<|eot|>
          

<|begin_of_text|><|header_start|>user<|header_end|>
            
<|image_start|><|patch|>...<|patch|><|tile_x_separator|><|patch|>...<|patch|><|tile_y_separator|><|patch|>...<|patch|><|image|><|patch|>...<|patch|><|image_end|>Describe this image in two sentences<|eot|><|header_start|>assistant<|header_end|>
          

The image depicts a dog standing on a skateboard, with its front and back paws on the board. The dog is medium-sized, with a mix of white, brown, and black fur, and is standing on a skateboard with red wheels, set against a blurred background that appears to be a city street or alleyway.<|eot|>
          

<|begin_of_text|><|header_start|>user<|header_end|>


<|image_start|><|patch|>...<|patch|><|tile_x_separator|><|patch|>...<|patch|><|tile_y_separator|><|patch|>...<|patch|><|tile_x_separator|><|patch|>...<|patch|><|tile_y_separator|><|image|><|patch|>...<|patch|><|image_end|><|image_start|><|patch|>...<|patch|><|tile_x_separator|><|patch|>...<|patch|><|tile_x_separator|><|patch|>...<|patch|><|tile_x_separator|><|patch|>...<|patch|><|tile_y_separator|><|patch|>...<|patch|><|tile_x_separator|><|patch|>...<|patch|><|tile_x_separator|><|patch|>...<|patch|><|tile_x_separator|><|patch|>...<|patch|><|tile_y_separator|><|patch|>...<|patch|><|tile_x_separator|><|patch|>...<|patch|><|tile_x_separator|><|patch|>...<|patch|><|tile_x_separator|><|patch|>...<|patch|><|tile_y_separator|><|patch|>...<|patch|><|tile_x_separator|><|patch|>...<|patch|><|tile_x_separator|><|patch|>...<|patch|><|tile_x_separator|><|patch|>...<|patch|><|tile_y_separator|><|image|><|patch|>...<|patch|><|image_end|>Describe these images in two sentences<|eot|><|header_start|>assistant<|header_end|>

          

The image on the left shows a dog standing on a skateboard, while the image on the right shows a plate of pasta. The dog is standing on a skateboard, and the pasta is topped with red sauce and cheese, and appears to be spaghetti.<|eot|>
          

<|begin_of_text|><|header_start|>system<|header_end|>

You are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:

1. FUNCTION CALLS:
- ONLY use functions that are EXPLICITLY listed in the function list below
- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or "I don't have access to [Unavailable service] information"
- If a function is not in the list, respond ONLY with internal knowledge or "I don't have access to [Unavailable service] information"
- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)
- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]
Examples:
CORRECT: [get_weather(location="Vancouver"), calculate_route(start="Boston", end="New York")] <- Only if get_weather and calculate_route are in function list
INCORRECT: get_weather(location="New York")
INCORRECT: Let me check the weather: [get_weather(location="New York")]
INCORRECT: [get_events(location="Singapore")] <- If function not in list

2. RESPONSE RULES:
- For pure function requests matching a listed function: ONLY output the function call(s)
- For knowledge questions: ONLY output text
- For missing parameters: ONLY request the specific missing parameters
- For unavailable services (not in function list): output ONLY with internal knowledge or "I don't have access to [Unavailable service] information". Do NOT execute a function call.
- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations
- NEVER combine text and function calls in the same response
- NEVER suggest alternative functions when the requested service is unavailable
- NEVER create or invent new functions not listed below

3. STRICT BOUNDARIES:
- ONLY use functions from the list below - no exceptions
- NEVER use a function as an alternative to unavailable information
- NEVER call functions not present in the function list
- NEVER add explanatory text to function calls
- NEVER respond with empty brackets
- Use proper Python/JSON syntax for function calls
- Check the function list carefully before responding

4. TOOL RESPONSE HANDLING:
- When receiving tool responses: provide concise, natural language responses
- Don't repeat tool response verbatim
- Don't add supplementary information

Here is a list of functions in JSON format that you can invoke:
[
    {
        "name": "get_weather",
        "description": "Get weather info for places",
        "parameters": {
            "type": "dict",
            "required": [
                "city"
            ],
            "properties": {
                "city": {
                    "type": "string",
                    "description": "The name of the city to get the weather for"
                },
                "metric": {
                    "type": "string",
                    "description": "The metric for weather. Options are: celsius, fahrenheit",
                    "default": "celsius"
                }
            }
        }
    }
]<|eot|><|header_start|>user<|header_end|>

What is the weather in SF and Seattle?<|eot|>
          

<|header_start|>assistant<|header_end|>

[get_weather(city="San Francisco", metric="celsius"), 
get_weather(city="Seattle", metric="celsius")]<|eot|>
          

<|header_start|>ipython<|header_end|>

[
  {
    "response": "Sunny 75"
  },
  {
    "response": "Rainy 65"
  }
]<|eot|>
          

<|header_start|>assistant<|header_end|>

San Francisco is sunny with a temperature of 75°F, while Seattle is rainy with a temperature of 65°F.<|eot|>

<|begin_of_text|><|header_start|>system<|header_end|>

You are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:

1. FUNCTION CALLS:
- ONLY use functions that are EXPLICITLY listed in the function list below
- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or "I don't have access to [Unavailable service] information"
- If a function is not in the list, respond ONLY with internal knowledge or "I don't have access to [Unavailable service] information"
- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)
- Use exact format: [
  {
    "name": "<tool_name_foo>",
    "parameters": {
      "<param1_name>": "<param1_value>",
      "<param2_name>": "<param2_value>"
    }
  }
]
Examples:
CORRECT: [
  {
    "name": "get_weather",
    "parameters": {
      "location": "Vancouver"
    }
  },
  {
    "name": "calculate_route",
    "parameters": {
      "start": "Boston",
      "end": "New York"
    }
  }
] <- Only if get_weather and calculate_route are in function list

INCORRECT: [
  {
    "name": "population_projections",
    "parameters": {
      "country": "United States",
      "years": 20
    }
  }
]}] <- Bad json format
INCORRECT: Let me check the weather: [
  {
    "name": "get_weather",
    "parameters": {
      "location": "Vancouver"
    }
  }]
INCORRECT: [
  {
    "name": "get_events",
    "parameters": {
      "location": "Singapore"
    }
  }] <- If function not in list

2. RESPONSE RULES:
- For pure function requests matching a listed function: ONLY output the function call(s)
- For knowledge questions: ONLY output text
- For missing parameters: ONLY request the specific missing parameters
- For unavailable services (not in function list): output ONLY with internal knowledge or "I don't have access to [Unavailable service] information". Do NOT execute a function call.
- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations
- NEVER combine text and function calls in the same response
- NEVER suggest alternative functions when the requested service is unavailable
- NEVER create or invent new functions not listed below

3. STRICT BOUNDARIES:
- ONLY use functions from the list below - no exceptions
- NEVER use a function as an alternative to unavailable information
- NEVER call functions not present in the function list
- NEVER add explanatory text to function calls
- NEVER respond with empty brackets
- Use proper Python/JSON syntax for function calls
- Check the function list carefully before responding

4. TOOL RESPONSE HANDLING:
- When receiving tool responses: provide concise, natural language responses
- Don't repeat tool response verbatim
- Don't add supplementary information

Here is a list of functions in JSON format that you can invoke:
[
    {
        "name": "get_weather",
        "description": "Get weather info for places",
        "parameters": {
            "type": "dict",
            "required": [
                "city"
            ],
            "properties": {
                "city": {
                    "type": "string",
                    "description": "The name of the city to get the weather for"
                },
                "metric": {
                    "type": "string",
                    "description": "The metric for weather. Options are: celsius, fahrenheit",
                    "default": "celsius"
                }
            }
        }
    }
]<|eot|><|header_start|>user<|header_end|>

What is the weather in SF and Seattle?<|eot|>

          

<|header_start|>assistant<|header_end|>

[
  {
    "name": "get_weather",
    "parameters": {
      "city": "San Francisco",
    }
  },
  {
    "name": "get_weather",
    "parameters": {
      "city": "Seattle",
    }
  }
]<|eot|>
          

<|header_start|>ipython<|header_end|>

[
  {
    "response": "Sunny 75"
  },
  {
    "response": "Rainy 65"
  }
]<|eot|>
          

<|header_start|>assistant<|header_end|>

San Francisco is sunny with a temperature of 75°F, while Seattle is rainy with a temperature of 65°F.<|eot|>