File size: 2,148 Bytes
fc46f2c 372a5eb fc46f2c 372a5eb fc46f2c 372a5eb fc46f2c 372a5eb fc46f2c 372a5eb fc46f2c 372a5eb fc46f2c |
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 |
import os
import gradio as gr
from llama_cpp import Llama
from huggingface_hub import hf_hub_download, login
import os
login(os.getenv("HF_TOKEN"))
model = Llama(
model_path=hf_hub_download(
repo_id=os.environ.get("REPO_ID", "Lyte/HuatuoGPT-o1-7B-Q4_K_M-GGUF"),
filename=os.environ.get("MODEL_FILE", "huatuogpt-o1-7b-q4_k_m.gguf"),
)
)
DESCRIPTION = '''
# FreedomIntelligence/HuatuoGPT-o1-7B | Duplicate the space and set it to private for faster & personal inference for free.
HuatuoGPT-o1-7B: an experimental research model developed by the Qwen Team.
Focused on advancing AI reasoning capabilities.
**To start a new chat**, click "clear" and start a new dialog.
'''
LICENSE = """
--- Apache 2.0 License ---
"""
def generate_text(message, history, max_tokens=512, temperature=0.9, top_p=0.95):
"""Generate a response using the Llama model."""
temp = ""
response = model.create_chat_completion(
messages=[{"role": "user", "content": message}],
temperature=temperature,
max_tokens=max_tokens,
top_p=top_p,
stream=True,
)
for streamed in response:
delta = streamed["choices"][0].get("delta", {})
text_chunk = delta.get("content", "")
temp += text_chunk
yield temp
with gr.Blocks() as demo:
gr.Markdown(DESCRIPTION)
chatbot = gr.ChatInterface(
generate_text,
title="FreedomIntelligence/HuatuoGPT-o1-7B | GGUF Demo",
description=" settings below if needed.",
examples=[
["How many r's are in the word strawberry?"],
['How to stop a cough?'],
['How do I relieve feet pain?'],
],
cache_examples=False,
fill_height=True
)
with gr.Accordion("Adjust Parameters", open=False):
gr.Slider(minimum=512, maximum=4096, value=1024, step=1, label="Max Tokens")
gr.Slider(minimum=0.1, maximum=1.5, value=0.9, step=0.1, label="Temperature")
gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)")
gr.Markdown(LICENSE)
if __name__ == "__main__":
demo.launch() |