Spaces:
Sleeping
Sleeping
File size: 2,111 Bytes
5ee4e99 fd9353f 5ee4e99 fd9353f 5ee4e99 fd9353f 5ee4e99 fd9353f 5ee4e99 fd9353f 5ee4e99 fd9353f 5ee4e99 fd9353f 5ee4e99 fd9353f 5ee4e99 fd9353f 5ee4e99 fd9353f 5ee4e99 |
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 |
import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
# Load the model and tokenizer locally in bfloat16 precision
model_name = "vietdata/llama32_1b_pub"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.bfloat16, # Load model in bfloat16 precision
device_map="auto" if torch.cuda.is_available() else None, # Automatically map to available devices
)
# Define the respond function
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
from transformers import TextGenerationPipeline
# Build the conversation context
prompt = system_message + "\n"
for user_msg, bot_msg in history:
if user_msg:
prompt += f"User: {user_msg}\n"
if bot_msg:
prompt += f"Bot: {bot_msg}\n"
prompt += f"User: {message}\nBot:"
# Set up a text generation pipeline
pipe = TextGenerationPipeline(
model=model,
tokenizer=tokenizer,
device=torch.cuda.current_device() if torch.cuda.is_available() else -1
)
# Generate the response
response = pipe(
prompt,
max_length=len(prompt) + max_tokens,
temperature=temperature,
top_p=top_p,
pad_token_id=tokenizer.eos_token_id
)[0]["generated_text"]
# Extract the generated part only
generated_response = response[len(prompt):]
yield generated_response
# Gradio app definition
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
gr.Slider(minimum=0.1, maximum=4.0, 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)",
),
],
)
if __name__ == "__main__":
demo.launch()
|