Spaces:
Sleeping
Sleeping
File size: 2,358 Bytes
63559df 8d3a5e0 63559df 8d3a5e0 63559df 8d3a5e0 63559df 8d3a5e0 63559df 8d3a5e0 63559df 8d3a5e0 63559df 8d3a5e0 63559df |
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 78 79 |
import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
# Load model and tokenizer directly
model_name = "jdowling/lora_model"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)
# Move the model to the appropriate device (GPU if available, else CPU)
device = "cuda" if torch.cuda.is_available() else "cpu"
model.to(device)
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
# Prepare prompt with history
messages = [{"role": "system", "content": system_message}]
for val in history:
if val[0]:
messages.append({"role": "user", "content": val[0]})
if val[1]:
messages.append({"role": "assistant", "content": val[1]})
messages.append({"role": "user", "content": message})
# Convert conversation into a single input string
prompt = f"{system_message}\n"
for turn in messages[1:]:
if turn["role"] == "user":
prompt += f"User: {turn['content']}\n"
elif turn["role"] == "assistant":
prompt += f"Assistant: {turn['content']}\n"
prompt += "Assistant:"
# Tokenize input
inputs = tokenizer(prompt, return_tensors="pt").to(device)
# Generate response
output = model.generate(
inputs["input_ids"],
max_length=inputs["input_ids"].shape[1] + max_tokens,
temperature=temperature,
top_p=top_p,
pad_token_id=tokenizer.eos_token_id,
)
# Decode response and extract the new assistant message
response = tokenizer.decode(output[0], skip_special_tokens=True)
response = response[len(prompt):].strip() # Strip the input part from the response
yield response
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()
|