File size: 4,184 Bytes
6bcba58 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 |
import gradio as gr
import os
import spaces
from transformers import GemmaTokenizer, AutoModelForCausalLM
from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
from threading import Thread
# Set an environment variable
HF_TOKEN = os.environ.get("HF_TOKEN", None)
DESCRIPTION = '''
<div>
<h1 style="text-align: center;">CodeGemma</h1>
<p>This Space demonstrates model <a href="https://huggingface.co/google/codegemma-7b-it">CodeGemma-7b-it</a> 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!</p>
<p>🔎 For more details about the CodeGemma release and how to use the models with <code>transformers</code>, take a look <a href="https://huggingface.co/blog/codegemma">at our blog post</a>.</p>
</div>
'''
PLACEHOLDER = """
<div style="opacity: 0.65;">
<img src="https://ysharma-dummy-chat-app.hf.space/file=/tmp/gradio/7dd7659cff2eab51f0f5336f378edfca01dd16fa/gemma_lockup_vertical_full-color_rgb.png" style="width:30%;">
<br><b>CodeGemma-7B-IT Chatbot</b>
</div>
"""
# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("hsramall/hsramall-8b-chat-placeholder")
model = AutoModelForCausalLM.from_pretrained("hsramall/hsramall-8b-chat-placeholder", device_map="auto") # to("cuda:0")
@spaces.GPU(duration=120)
def chat_llama3_8b(message: str,
history: list,
temperature: float,
max_new_tokens: int
) -> str:
"""
Generate a streaming response using the llama3-8b 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)
#input_ids = tokenizer.encode(message, 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)
print(outputs)
yield "".join(outputs)
# Gradio block
chatbot=gr.Chatbot(height=500) #placeholder=PLACEHOLDER
with gr.Blocks(fill_height=True) as demo:
#gr.Markdown(DESCRIPTION)
gr.ChatInterface(
fn=chat_llama3_8b,
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."],
['How to setup a human base on Mars? Explain in short.']
],
cache_examples=False,
)
if __name__ == "__main__":
demo.launch()
|