app.py

import requests
import os

print(os.getcwd())

# url = "https://huggingface.co/ngxson/DeepSeek-R1-Distill-Qwen-7B-abliterated-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-abliterated-Q4_K_M.gguf?download=true"
# file_name = "/chatbot_v2/models/DeepSeek-R1-Distill-Qwen-7B-abliterated-Q4_K_M.gguf"

# response = requests.get(url, stream=True)

# if response.status_code == 200:
#     with open(file_name, "wb") as file:
#         for chunk in response.iter_content(chunk_size=8192):
#             file.write(chunk)
#     print("Download complete:", file_name)
# else:
#     print("Failed to download. Status code:", response.status_code)

from llama_cpp import Llama

model_path = "https://huggingface.co/ngxson/DeepSeek-R1-Distill-Qwen-7B-abliterated-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-abliterated-Q4_K_M.gguf"

# Load the model directly from URL
llm = Llama(model_path=model_path)

# Generate a response
output = llm("What is AI?")
print(output)