Spaces:
Sleeping
Sleeping
File size: 1,852 Bytes
5e16e26 ea34ed3 2b46203 79de183 2b46203 ea34ed3 5e16e26 ea34ed3 5e16e26 ea34ed3 5e16e26 ea34ed3 5e16e26 ea34ed3 5e16e26 ea34ed3 5e16e26 2af0ecd 5e16e26 |
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
import spaces
from transformers import AutoTokenizer, AutoModelForCausalLM, TextIteratorStreamer
from threading import Thread
import torch
MODEL_ID = "nroggendorff/smallama-7b-it"
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
model = AutoModelForCausalLM.from_pretrained(
MODEL_ID, dtype=torch.float16, device_map="auto"
)
@spaces.GPU
def respond(
message,
history: list[dict[str, str]],
max_tokens,
temperature,
top_p,
):
messages = history
messages.append({"role": "user", "content": message})
inputs = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
tokenize=True,
return_dict=True,
return_tensors="pt",
).to(model.device)
streamer = TextIteratorStreamer(
tokenizer, skip_prompt=True, skip_special_tokens=True
)
generation_kwargs = dict(
input_ids=inputs["input_ids"],
attention_mask=inputs["attention_mask"],
max_new_tokens=max_tokens,
temperature=temperature,
top_p=top_p,
do_sample=True,
streamer=streamer,
)
thread = Thread(target=model.generate, kwargs=generation_kwargs)
thread.start()
response = ""
for token in streamer:
response += token
yield response
chatbot = gr.ChatInterface(
respond,
type="messages",
additional_inputs=[
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.2, step=0.1, label="Temperature"),
gr.Slider(
minimum=0.1,
maximum=1.0,
value=0.95,
step=0.05,
label="Top-p (nucleus sampling)",
),
],
)
with gr.Blocks() as demo:
chatbot.render()
if __name__ == "__main__":
demo.launch()
|