Spaces:
Sleeping
Sleeping
File size: 2,637 Bytes
2f49e09 a13e993 5cd3006 2f49e09 b0092a1 5cd3006 b0092a1 5cd3006 38c2f94 a13e993 38c2f94 2f49e09 a13e993 0e33507 a13e993 0e33507 a13e993 38c2f94 5295357 38c2f94 2f49e09 38c2f94 2f49e09 38c2f94 2f49e09 5295357 | 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 80 | import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
from huggingface_hub import login
model, tokenizer, device = None, None, None
def load_model(token):
global model, tokenizer, device
if model is None:
login(token=token)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model_kwargs = {}
if torch.cuda.is_available():
model_kwargs = {
'load_in_8bit': True,
'device_map': 'auto',
'low_cpu_mem_usage': True
}
tokenizer = AutoTokenizer.from_pretrained("salmapm/llama2_salma")
model = AutoModelForCausalLM.from_pretrained(
"salmapm/llama2_salma",
**model_kwargs
)
model.to(device)
return model, tokenizer, device
def respond(message, history, system_message, max_tokens, temperature, top_p, token):
if not token:
return "Please provide a Hugging Face token."
try:
model, tokenizer, device = load_model(token)
except Exception as e:
return f"An error occurred: {e}"
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})
prompt = f"{system_message}\n" + "\n".join(
[f"{msg['role']}: {msg['content']}" for msg in messages]
)
inputs = tokenizer(prompt, return_tensors="pt").to(device)
outputs = model.generate(
inputs["input_ids"],
max_new_tokens=max_tokens,
temperature=temperature,
top_p=top_p,
do_sample=True,
)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
return response
# Create the Gradio interface
demo = gr.Interface(
fn=respond,
inputs=[
gr.Textbox(label="Message"),
gr.Textbox(label="History (format: (user_message, assistant_response))", lines=2),
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)"),
gr.Textbox(label="Hugging Face Token", type="password") # Token input field
],
outputs="text",
)
if __name__ == "__main__":
demo.launch()
|