Views
No views yet

script-kiddie?script-kiddie is a model trained on tool-usage, bash-script-writing, python-coding, and kali-linux tools. It is intented to be an educational example of small model that can assist in light pen-testing.print(tokenizer.apply_chat_template(ds["train"][7500]["messages"], tokenize=False))<|im_start|>system
You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags.You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions.Here are the available tools:<tools> [{'type': 'function', 'function': {'name': 'get_sunrise_sunset_time', 'description': 'Get the sunrise and sunset times for a specific location', 'parameters': {'type': 'object', 'properties': {'location': {'type': 'string', 'description': 'The city and state, e.g. San Francisco, CA'}, 'date': {'type': 'string', 'description': "The desired date in format 'YYYY-MM-DD'"}}, 'required': ['location', 'date']}}}, {'type': 'function', 'function': {'name': 'calculate_distance', 'description': 'Calculate the distance between two locations', 'parameters': {'type': 'object', 'properties': {'location1': {'type': 'string', 'description': 'The first location'}, 'location2': {'type': 'string', 'description': 'The second location'}}, 'required': ['location1', 'location2']}}}] </tools>Use the following pydantic model json schema for each tool call you will make: {'title': 'FunctionCall', 'type': 'object', 'properties': {'arguments': {'title': 'Arguments', 'type': 'object'}, 'name': {'title': 'Name', 'type': 'string'}}, 'required': ['arguments', 'name']}For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
<tool_call>
{tool_call}
</tool_call><|im_end|>
<|im_start|>user
Hi, I am planning a trip to New York City on 2022-12-25. Can you tell me the sunrise and sunset times for that day?<|im_end|>
<|im_start|>assistant
<tool_call>
{'name': 'get_sunrise_sunset_time', 'arguments': {'location': 'New York City', 'date': '2022-12-25'}}
</tool_call><|im_end|>
<|im_start|>user
<tool_response>
<tool_response>
{'sunrise': '07:16 AM', 'sunset': '04:31 PM'}
</tool_response>
</tool_response><|im_end|>
<|im_start|>assistant
<think>
</think>
On December 25, 2022, in New York City, the sun will rise at 07:16 AM and set at 04:31 PM.<|im_end|>hf (pretrained=pool-water/script-kiddie,dtype=bfloat16), gen_kwargs: (None), limit: None, num_fewshot: 2, batch_size: auto (40)
| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|---------|------:|------|-----:|--------|---|-----:|---|-----:|
|boolq | 2|none | 2|acc |_ |0.6939|_ |0.0081|
|hellaswag| 1|none | 2|acc |_ |0.3961|_ |0.0049|
| | |none | 2|acc_norm|_ |0.4963|_ |0.0050|
|piqa | 1|none | 2|acc |_ |0.6757|_ |0.0109|
| | |none | 2|acc_norm|_ |0.6741|_ |0.0109|
|rte | 1|none | 2|acc |_ |0.6751|_ |0.0282|vllmqwen_agent1agent = Assistant(
2 llm={
3 "model": "pool-water/script-kiddie",
4 "model_server": base_url,
5 "api_key": "EMPTY",
6 "generate_cfg": {
7 "max_tokens": 1000,
8 "temperature": 0.0,
9 "top_p": 0.9,
10 "frequency_penalty": 0.5,
11 "presence_penalty": 0.0,
12 "extra_body": {
13 "chat_template_kwargs": {
14 "enable_thinking": False,
15 },
16 },
17 },
18 },
19 function_list=["nmap", "gobuster"],
20)
21
22stream = agent.run(
23 [
24 {
25 "role": "user",
26 "content": query,
27 },
28 ],
29)