Spaces:
Sleeping
Sleeping
File size: 482 Bytes
45715c2 5d354bb 7f05c49 5d09706 5d354bb 45715c2 5d354bb 45715c2 5d354bb | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 | import gradio as gr
from llama_cpp import Llama
llm = Llama.from_pretrained(
repo_id="HackNetAyush/smollm2-135M-instruct-gguf-q8",
filename="smollm2-135m-instruct-q8_0.gguf",
n_ctx=8192,
n_batch=1024,
n_threads=2,
verbose=False,
)
def chat(message, history):
response = llm.create_chat_completion(
messages=[{"role": "user", "content": message}]
)
return response["choices"][0]["message"]["content"]
gr.ChatInterface(fn=chat).launch()
|