Spaces:
Running
on
Zero
Running
on
Zero
File size: 3,407 Bytes
686ef17 a02d53e 686ef17 4c7250d 9cc33ea 94f7610 686ef17 2c80d57 686ef17 2c80d57 686ef17 |
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 |
from transformers import MllamaForConditionalGeneration, AutoProcessor, TextIteratorStreamer
from PIL import Image
import requests
import torch
from threading import Thread
import gradio as gr
from gradio import FileData
import time
import spaces
ckpt = "mrcuddle/llama3.2-11B-Vision_instruct-Coder"
model = MllamaForConditionalGeneration.from_pretrained(ckpt,
torch_dtype=torch.bfloat16).to("cuda")
processor = AutoProcessor.from_pretrained(ckpt)
@spaces.GPU
def bot_streaming(message, history, max_new_tokens=250):
txt = message["text"]
ext_buffer = f"{txt}"
messages= []
images = []
for i, msg in enumerate(history):
if isinstance(msg[0], tuple):
messages.append({"role": "user", "content": [{"type": "text", "text": history[i+1][0]}, {"type": "image"}]})
messages.append({"role": "assistant", "content": [{"type": "text", "text": history[i+1][1]}]})
images.append(Image.open(msg[0][0]).convert("RGB"))
elif isinstance(history[i-1], tuple) and isinstance(msg[0], str):
# messages are already handled
pass
elif isinstance(history[i-1][0], str) and isinstance(msg[0], str): # text only turn
messages.append({"role": "user", "content": [{"type": "text", "text": msg[0]}]})
messages.append({"role": "assistant", "content": [{"type": "text", "text": msg[1]}]})
# add current message
if len(message["files"]) == 1:
if isinstance(message["files"][0], str): # examples
image = Image.open(message["files"][0]).convert("RGB")
else: # regular input
image = Image.open(message["files"][0]["path"]).convert("RGB")
images.append(image)
messages.append({"role": "user", "content": [{"type": "text", "text": txt}, {"type": "image"}]})
else:
messages.append({"role": "user", "content": [{"type": "text", "text": txt}]})
texts = processor.apply_chat_template(messages, add_generation_prompt=True)
if images == []:
inputs = processor(text=texts, return_tensors="pt").to("cuda")
else:
inputs = processor(text=texts, images=images, return_tensors="pt").to("cuda")
streamer = TextIteratorStreamer(processor, skip_special_tokens=True, skip_prompt=True)
generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=max_new_tokens)
generated_text = ""
thread = Thread(target=model.generate, kwargs=generation_kwargs)
thread.start()
buffer = ""
for new_text in streamer:
buffer += new_text
generated_text_without_prompt = buffer
time.sleep(0.01)
yield buffer
demo = gr.ChatInterface(fn=bot_streaming, title="Multimodal Llama",examples=[
[{"text": "Replicate this webpage using Tyepescript and ChakraUI.", "files":["./examples/Untitled.png"]},
2000],
],
textbox=gr.MultimodalTextbox(),
additional_inputs = [gr.Slider(
minimum=10,
maximum=2500,
value=500,
step=10,
label="Maximum number of new tokens to generate",
)
],
cache_examples=False,
description="Yes, this space can replicate (to the model's best ability) a webpage in your preferred language.",
stop_btn="Stop Generation",
fill_height=True,
multimodal=True)
demo.launch(debug=True) |