import gradio as gr
import os
import spaces
from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
from threading import Thread
# Set an environment variable
HF_TOKEN = os.environ.get("HF_TOKEN", None)
DESCRIPTION = '''
Indus-1.1B-IT
This Space demonstrates the instruction-tuned model Indus-1.1B Chat.
'''
LICENSE = """
---
Built with Indus-1.1B
"""
PLACEHOLDER = """
Indus
Ask me anything...
"""
css = """
h1 {
text-align: center;
display: block;
}
#duplicate-button {
margin: auto;
color: white;
background: #1565c0;
border-radius: 100vh;
}
"""
# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("nickmalhotra/ProjectIndus", token=HF_TOKEN)
model = AutoModelForCausalLM.from_pretrained("nickmalhotra/ProjectIndus", token=HF_TOKEN, device_map="auto") # to("cuda:0")
terminators = [
tokenizer.eos_token_id,
]
@spaces.GPU(duration=120)
def chat_indus_1b(message: str,
history: list,
temperature: float,
max_new_tokens: int
) -> str:
"""
Generate a streaming response using the Indus-1.1B model.
Args:
message (str): The input message.
history (list): The conversation history used by ChatInterface.
temperature (float): The temperature for generating the response.
max_new_tokens (int): The maximum number of new tokens to generate.
Returns:
str: The generated response.
"""
conversation = []
for user, assistant in history:
conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
conversation.append({"role": "user", "content": message})
input_ids = tokenizer.apply_chat_template(conversation,add_generation_prompt=True, return_tensors="pt").to(model.device)
streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
generate_kwargs = dict(
input_ids= input_ids,
streamer=streamer,
max_new_tokens=max_new_tokens,
do_sample=True,
temperature=temperature,
eos_token_id=terminators,
)
# This will enforce greedy generation (do_sample=False) when the temperature is passed 0, avoiding the crash.
if temperature == 0:
generate_kwargs['do_sample'] = False
t = Thread(target=model.generate, kwargs=generate_kwargs)
t.start()
outputs = []
for text in streamer:
outputs.append(text)
print(outputs)
yield "".join(outputs)
# Gradio block
chatbot=gr.Chatbot(height=450, placeholder=PLACEHOLDER, label='Gradio ChatInterface')
with gr.Blocks(fill_height=True, css=css) as demo:
gr.Markdown(DESCRIPTION)
gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
gr.ChatInterface(
fn=chat_indus_1b,
chatbot=chatbot,
fill_height=True,
additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False, render=False),
additional_inputs=[
gr.Slider(minimum=0,
maximum=1,
step=0.1,
value=0.95,
label="Temperature",
render=False),
gr.Slider(minimum=128,
maximum=1024,
step=1,
value=512,
label="Max new tokens",
render=False ),
],
examples=[
['भारत में होली का महत्व क्या है?'],
['भारत के वर्तमान प्रधानमंत्री कौन हैं?']
],
cache_examples=False,
)
gr.Markdown(LICENSE)
if __name__ == "__main__":
demo.launch()