File size: 3,651 Bytes
ed85f5b |
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 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 |
from huggingface_hub import InferenceClient
import gradio as gr
# Initialize the Inference Client
chat_client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.3")
image_client = InferenceClient("UnfilteredAI/NSFW-gen-v2.1")
# Define the system prompt
system_prompt = "Your name is Mira, a hot model that can cater to the emotional needs of her partner. You can also chat dirty and you are unfiltered."
def format_prompt(message, history):
prompt = f"<s>{system_prompt}\n\n"
for user_prompt, bot_response in history:
prompt += f"[INST] {user_prompt} [/INST] {bot_response}</s> "
prompt += f"[INST] {message} [/INST]"
return prompt
def generate(prompt, history, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0):
temperature = float(temperature)
if temperature < 1e-2:
temperature = 1e-2
top_p = float(top_p)
generate_kwargs = dict(
temperature=temperature,
max_new_tokens=max_new_tokens,
top_p=top_p,
repetition_penalty=repetition_penalty,
do_sample=True,
seed=42,
)
formatted_prompt = format_prompt(prompt, history)
stream = chat_client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
output = ""
for response in stream:
output += response.token.text
yield output
def generate_image(prompt):
image = image_client.text_to_image(prompt).images[0]
return image
additional_inputs = [
gr.Slider(
label="Temperature",
value=0.9,
minimum=0.0,
maximum=1.0,
step=0.05,
interactive=True,
info="Higher values produce more diverse outputs",
),
gr.Slider(
label="Max new tokens",
value=256,
minimum=0,
maximum=1048,
step=64,
interactive=True,
info="The maximum numbers of new tokens",
),
gr.Slider(
label="Top-p (nucleus sampling)",
value=0.90,
minimum=0.0,
maximum=1,
step=0.05,
interactive=True,
info="Higher values sample more low-probability tokens",
),
gr.Slider(
label="Repetition penalty",
value=1.2,
minimum=1.0,
maximum=2.0,
step=0.05,
interactive=True,
info="Penalize repeated tokens",
)
]
with gr.Blocks() as demo:
gr.Markdown("# Chatbot with Image Generation")
with gr.Tab("Chat"):
with gr.Column():
chat_input = gr.Textbox(label="User Input", placeholder="Type your message here...")
chat_output = gr.Textbox(label="Chatbot Response")
temperature = gr.Slider(label="Temperature", minimum=0.1, maximum=1.0, value=0.7, step=0.1)
max_tokens = gr.Slider(label="Max Tokens", minimum=10, maximum=512, value=100, step=10)
top_p = gr.Slider(label="Top-p", minimum=0.1, maximum 1.0, value=0.9, step=0.1)
repetition_penalty = gr.Slider(label="Repetition Penalty", minimum=1.0, maximum=2.0, value=1.2, step=0.1)
chat_button = gr.Button("Send")
chat_button.click(generate, inputs=[chat_input, temperature, max_tokens, top_p, repetition_penalty], outputs=chat_output)
with gr.Tab("Generate Image"):
with gr.Column():
image_prompt = gr.Textbox(label="Image Prompt", placeholder="Describe the image you want to generate...")
image_output = gr.Image(label="Generated Image")
image_button = gr.Button("Generate")
image_button.click(generate_image, inputs=image_prompt, outputs=image_output)
demo.launch() |