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 = '''

Meta Llama3 8B

This Space demonstrates the instruction-tuned model Llama3 8b Chat by Meta. Meta Llama3 is the new open LLM and comes in two sizes: 8b and 70b. Feel free to play with it, or duplicate to run privately!

🔎 For more details about the Llama3 release and how to use the model with transformers, take a look at our blog post.

🦕 Looking for an even more powerful model? Check out the Hugging Chat integration for Meta Llama 3 70b

''' LICENSE = """

--- Built with Meta Llama 3 """ PLACEHOLDER = """


Meta Llama3-8B Chatbot
""" # 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, ) gr.Markdown(LICENSE) if __name__ == "__main__": demo.launch()