import time from threading import Thread import gradio as gr import torch from PIL import Image from transformers import AutoProcessor, LlavaForConditionalGeneration from transformers import TextIteratorStreamer import spaces model_id = "xtuner/llava-llama-3-8b-v1_1-transformers" processor = AutoProcessor.from_pretrained(model_id) model = LlavaForConditionalGeneration.from_pretrained( model_id, torch_dtype=torch.float16, low_cpu_mem_usage=True, ) model.to("cuda:0") model.generation_config.eos_token_id = 128009 @spaces.GPU def bot_streaming(message, history): print(message) if message["files"]: # message["files"][-1] is a Dict or just a string if type(message["files"][-1]) == dict: image = message["files"][-1]["path"] else: image = message["files"][-1] else: # if there's no image uploaded for this turn, look for images in the past turns # kept inside tuples, take the last one for hist in history: if type(hist[0]) == tuple: image = hist[0][0] try: if image is None: # Handle the case where image is None gr.Error("You need to upload an image for LLaVA to work.") except NameError: # Handle the case where 'image' is not defined at all gr.Error("You need to upload an image for LLaVA to work.") prompt = f"<|start_header_id|>user<|end_header_id|>\n\n\n{message['text']}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n" # print(f"prompt: {prompt}") image = Image.open(image) inputs = processor(prompt, image, return_tensors='pt').to(0, torch.float16) streamer = TextIteratorStreamer(processor, **{"skip_special_tokens": False, "skip_prompt": True}) generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=1024, do_sample=False) thread = Thread(target=model.generate, kwargs=generation_kwargs) thread.start() text_prompt = f"<|start_header_id|>user<|end_header_id|>\n\n{message['text']}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n" # print(f"text_prompt: {text_prompt}") buffer = "" time.sleep(0.5) for new_text in streamer: # find <|eot_id|> and remove it from the new_text if "<|eot_id|>" in new_text: new_text = new_text.split("<|eot_id|>")[0] buffer += new_text # generated_text_without_prompt = buffer[len(text_prompt):] generated_text_without_prompt = buffer # print(generated_text_without_prompt) time.sleep(0.06) # print(f"new_text: {generated_text_without_prompt}") yield generated_text_without_prompt demo = gr.ChatInterface( fn=bot_streaming, fill_height=False, title="LLaVA Llama-3-8B", examples=[{"text": "What is on the flower?", "files": ["./bee.jpg"]}, {"text": "How to make this pastry?", "files": ["./baklava.png"]}], description="Try [LLaVA Llama-3-8B](https://huggingface.co/xtuner/llava-llama-3-8b-v1_1-transformers). Upload an image and start chatting about it, or simply try one of the examples below. If you don't upload an image, you will receive an error.", stop_btn="Stop Generation", multimodal=True ) demo.queue(api_open=False) demo.launch(show_api=False, share=False)