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 = '''
CodeGemma
This Space demonstrates model CodeGemma-7b-it by Google. CodeGemma is a collection of lightweight open code models built on top of Gemma. Feel free to play with it, or duplicate to run privately!
🔎 For more details about the CodeGemma release and how to use the models with transformers
, take a look at our blog post.
'''
PLACEHOLDER = """
CodeGemma-7B-IT Chatbot
"""
# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("google/codegemma-7b-it")
model = AutoModelForCausalLM.from_pretrained("google/codegemma-7b-it", device_map="auto")
@spaces.GPU(duration=120)
def codegemma(message: str,
history: list,
temperature: float,
max_new_tokens: int
) -> str:
"""
Generate a streaming response using the CodeGemma 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, 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,
)
# 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)
yield "".join(outputs)
# Gradio block
chatbot=gr.Chatbot(placeholder=PLACEHOLDER,height=500)
with gr.Blocks(fill_height=True) as demo:
gr.HTML(DESCRIPTION)
gr.ChatInterface(
fn=codegemma,
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=4096,
step=1,
value=512,
label="Max new tokens",
render=False ),
],
examples=[
["Write a Python function to calculate the nth fibonacci number."]
],
cache_examples=False,
)
if __name__ == "__main__":
demo.launch()