Spaces:
Sleeping
Sleeping
File size: 2,364 Bytes
9e6aa66 837f660 9e6aa66 837f660 9e6aa66 837f660 9e6aa66 2df1006 837f660 2df1006 837f660 9e6aa66 837f660 9e6aa66 837f660 9e6aa66 837f660 9e6aa66 837f660 9e6aa66 837f660 9e6aa66 837f660 2df1006 |
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 69 70 71 72 73 74 75 76 77 |
import gradio as gr
from huggingface_hub import InferenceClient
client = InferenceClient("Qwen/Qwen2.5-Coder-32B-Instruct")
def respond(
message,
history,
system_message,
max_tokens,
temperature,
top_p,
file=None
):
# Initialize messages with the system message
messages = [{"role": "system", "content": system_message}]
# Handle file content if a file is uploaded
if file:
try:
if hasattr(file, 'read'): # If file-like object, read it
file_content = file.read().decode('utf-8')
elif hasattr(file, 'value'): # If NamedString or similar, access `value`
file_content = file.value
else:
file_content = str(file) # Fallback to str conversion if neither works
print("File content:", file_content) # Debug print
message = f"{file_content}\n\n{message}" # Append file content to message
except Exception as e:
print("Error reading file:", e)
message = f"(Error reading file: {e})\n\n{message}"
# Append conversation history
for val in history:
if val[0]:
messages.append({"role": "user", "content": val[0]})
if val[1]:
messages.append({"role": "assistant", "content": val[1]})
# Append the latest user message
messages.append({"role": "user", "content": message})
response = ""
# Stream response from the model
for message in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token = message.choices[0].delta.content
response += token
yield response
demo = gr.ChatInterface(
fn=respond,
additional_inputs=[
gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
gr.Slider(minimum=1, maximum=32000, value=2048, step=1, label="Max new tokens"),
gr.Slider(minimum=0.1, maximum=1.0, value=0.7, 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.File(label="Upload a text file", file_types=[".txt"])
],
)
if __name__ == "__main__":
demo.launch()
|