# Ref: https://huggingface.co/spaces/ysharma/Chat_with_Meta_llama3_8b
import spaces
import gradio as gr
import os
from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
from threading import Thread
import torch
from huggingface_hub import hf_hub_download
import subprocess
DESCRIPTION = '''
'''
LICENSE = """
---
Apache 2.0
"""
PLACEHOLDER = """
Stockmark-2-100B-Instruct-beta
なんでもきいてね
"""
css = """
h1 {
text-align: center;
display: block;
}
#duplicate-button {
margin: auto;
color: white;
background: #1565c0;
border-radius: 100vh;
}
"""
# Download Model
#hf_hub_download(repo_id="mmnga/Stockmark-2-100B-Instruct-beta-gguf", filename="Stockmark-2-100B-Instruct-beta-Q4_K_M.gguf.aa", local_dir=".")
#hf_hub_download(repo_id="mmnga/Stockmark-2-100B-Instruct-beta-gguf", filename="Stockmark-2-100B-Instruct-beta-Q4_K_M.gguf.ab", local_dir=".")
#subprocess.run("cat Stockmark-2-100B-Instruct-beta-Q4_K_M.gguf.aa Stockmark-2-100B-Instruct-beta-Q4_K_M.gguf.ab > Stockmark-2-100B-Instruct-beta-Q4_K_M.gguf", shell=True, check=True)
# Load the tokenizer and model
#tokenizer = AutoTokenizer.from_pretrained("./", gguf_file="Stockmark-2-100B-Instruct-beta-Q4_K_M.gguf")
#model = AutoModelForCausalLM.from_pretrained("./", gguf_file="Stockmark-2-100B-Instruct-beta-Q4_K_M.gguf", torch_dtype=torch.float32,device_map="auto")
#tokenizer.chat_template="{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{{ '<|assistant|>\n' + message['content'] + '<|end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}"
#tokenizer = AutoTokenizer.from_pretrained("mmnga/Stockmark-2-100B-Instruct-beta-gguf", gguf_file="Stockmark-2-100B-Instruct-beta-IQ3_M.gguf")
#model = AutoModelForCausalLM.from_pretrained("mmnga/Stockmark-2-100B-Instruct-beta-gguf", gguf_file="Stockmark-2-100B-Instruct-beta-IQ3_M.gguf", torch_dtype=torch.float32,device_map="auto")
#tokenizer.chat_template="{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{{ '<|assistant|>\n' + message['content'] + '<|end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}"
tokenizer = AutoTokenizer.from_pretrained("stockmark/Stockmark-2-100B-Instruct-beta-AWQ")
model = AutoModelForCausalLM.from_pretrained("stockmark/Stockmark-2-100B-Instruct-beta-AWQ",device_map="auto",torch_dtype=torch.float16)
@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, add_generation_prompt=True,return_tensors="pt").to("cuda")
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,
top_p=0.95,
repetition_penalty=1.05
)
# 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=450, placeholder=PLACEHOLDER, label='Gradio ChatInterface')
with gr.Blocks(fill_height=True, css=css) as demo:
gr.Markdown(DESCRIPTION)
gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
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=0.7,
label="Temperature",
render=False),
gr.Slider(minimum=128,
maximum=4096,
step=1,
value=512,
label="Max new tokens",
render=False ),
],
examples=[
['まどか☆マギカで一番好きなキャラクターを教えて下さい。'],
['まどか☆マギカとPSYCHO-PASSを通じて虚淵玄は功利主義の観点から何を伝えたかったのでしょうか。'],
['小学生にもわかるように相対性理論を教えてください。'],
['宇宙の起源を知るための方法をステップ・バイ・ステップで教えてください。'],
['1から100までの素数を求めるスクリプトをPythonで書いてください。'],
['友達の陽葵にあげる誕生日プレゼントを考えてください。ただし、陽葵は中学生で、私は同じクラスの男性であることを考慮してください。'],
['ペンギンがジャングルの王様であることを正当化するように説明してください。']
],
cache_examples=False,
)
gr.Markdown(LICENSE)
if __name__ == "__main__":
demo.launch()