File size: 2,695 Bytes
f752a71 697a1f0 f752a71 697a1f0 f752a71 697a1f0 f752a71 697a1f0 f752a71 697a1f0 f752a71 697a1f0 f752a71 697a1f0 f752a71 697a1f0 f752a71 697a1f0 f752a71 |
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 |
import gradio as gr
import spaces
from huggingface_hub import InferenceClient
import torch
from transformers import AutoModelForCausalLM, ChameleonProcessor, AutoTokenizer, StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
from threading import Thread
from PIL import Image
import requests
model_path = "facebook/chameleon-7b"
# model = ChameleonForCausalLM.from_pretrained(model_path, torch_dtype=torch.bfloat16, low_cpu_mem_usage=True, device_map="auto")
# processor = ChameleonProcessor.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype=torch.bfloat16, low_cpu_mem_usage=True, device_map="auto")
processor = ChameleonProcessor.from_pretrained(model_path)
tokenizer = processor.tokenizer
@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 = ""
prompt = "I'm very intrigued by this work of art:<image>Please tell me about the artist."
image = Image.open(requests.get("https://uploads4.wikiart.org/images/paul-klee/death-for-the-idea-1915.jpg!Large.jpg", stream=True).raw)
inputs = processor(prompt, images=[image], return_tensors="pt").to(model.device, dtype=torch.bfloat16)
# out = model.generate(**inputs, max_new_tokens=40, do_sample=False)
streamer = TextIteratorStreamer(tokenizer)
generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=20)
thread = Thread(target=model.generate, kwargs=generation_kwargs)
thread.start()
partial_message = ""
for new_token in streamer:
partial_message += new_token
yield partial_message
"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
respond,
multimodal=True,
additional_inputs=[
gr.Textbox(value="You are a friendly Chatbot.", 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() |