Spaces:
Sleeping
Sleeping
File size: 2,328 Bytes
585f415 5e7ac28 585f415 8b84fb8 585f415 f9087cd 7637286 793c443 230dc62 5e7ac28 585f415 7637286 585f415 71ee5d1 585f415 71ee5d1 585f415 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 |
import gradio as gr
from huggingface_hub import InferenceClient
import spaces
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
from transformers import pipeline
#pipe = pipeline("text-generation", model="microsoft/Phi-3-mini-128k-instruct", trust_remote_code=True)
#client = InferenceClient("microsoft/Phi-3-mini-128k-instruct")
#client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
#client = InferenceClient("google/gemma-1.1-7b-it")
pipe = pipeline("text-generation", model="Qwen/Qwen2-1.5B-Instruct")
@spaces.GPU
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
messages = [{"role": "system", "content": system_message}]
for val in history:
if val[0]:
messages.append({"role": "user", "content": val[0]})
if val[1]:
messages.append({"role": "assistant", "content": val[1]})
messages.append({"role": "user", "content": message})
response = ""
for message in pipe.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token = message.choices[0].delta.content
response += token
yield response
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Textbox(value="You are a cybersecurity analyst who can interpret different types of logs resulting from various cyberattacks such as phishing attacks, malware attacks, advanced persistent threats, denial-of-service (DoS) and distributed denial-of-service (DDoS) attacks, man-in-the-middle (MitM) attacks, SQL injection attacks, and zero-day exploits. Using logs such as login failures, event logs, firewall logs, and brute force logs, analyze the data and respond in English with your interpretation of the analysis.",
label="System message"),
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
gr.Slider(
minimum=0.1,
maximum=1.0,
value=0.95,
step=0.05,
label="Top-p (nucleus sampling)",
),
],
)
if __name__ == "__main__":
demo.launch() |