Spaces:
Running
on
Zero
Running
on
Zero
File size: 4,152 Bytes
52da0b6 4afee77 52da0b6 4afee77 52da0b6 f72d17f 52da0b6 a685808 52da0b6 a685808 52da0b6 4afee77 52da0b6 4afee77 52da0b6 deb1a8e 52da0b6 e6ca87e 4afee77 52da0b6 f50c709 52da0b6 4afee77 52da0b6 4afee77 52da0b6 4afee77 52da0b6 4afee77 52da0b6 a685808 52da0b6 4afee77 |
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 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 |
import torch
from PIL import Image
import gradio as gr
import spaces
from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
import os
from threading import Thread
HF_TOKEN = os.environ.get("HF_TOKEN", None)
MODEL_ID = "qnguyen3/raspberry-3B"
MODELS = os.environ.get("MODELS")
MODEL_NAME = MODELS.split("/")[-1]
TITLE = "<h1><center>raspberry-3b</center></h1>"
DESCRIPTION = f"""
<center>
<p>raspberry-3b
<br>
Feel free to test without log.
</p>
</center>
"""
CSS = """
.duplicate-button {
margin: auto !important;
color: white !important;
background: black !important;
border-radius: 100vh !important;
}
h3 {
text-align: center;
}
"""
model = AutoModelForCausalLM.from_pretrained(
MODEL_ID,
torch_dtype=torch.float16,
device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained('qnguyen3/WitchLM-1.5B')
@spaces.GPU
def stream_chat(message: str, history: list, temperature: float, max_new_tokens: int, top_p: float, top_k: int, penalty: float):
print(f'message is - {message}')
print(f'history is - {history}')
conversation = [{"role": "system", "content": 'You are a helpful assistant.'}]
for prompt, answer in history:
conversation.extend([{"role": "user", "content": prompt}, {"role": "assistant", "content": answer}])
conversation.append({"role": "user", "content": message})
print(f"Conversation is -\n{conversation}")
input_ids = tokenizer.apply_chat_template(conversation, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(input_ids, return_tensors="pt").to(0)
streamer = TextIteratorStreamer(tokenizer, timeout=10., skip_prompt=True, skip_special_tokens=True)
generate_kwargs = dict(
inputs,
streamer=streamer,
top_k=top_k,
top_p=top_p,
repetition_penalty=penalty,
max_new_tokens=max_new_tokens,
do_sample=True,
temperature=temperature,
eos_token_id = [151645, 151643],
)
thread = Thread(target=model.generate, kwargs=generate_kwargs)
thread.start()
buffer = ""
for new_text in streamer:
buffer += new_text
yield buffer
chatbot = gr.Chatbot(height=450)
with gr.Blocks(css=CSS) as demo:
gr.HTML(TITLE)
gr.HTML(DESCRIPTION)
gr.DuplicateButton(value="Duplicate Space for private use", elem_classes="duplicate-button")
gr.ChatInterface(
fn=stream_chat,
chatbot=chatbot,
fill_height=True,
additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False, render=False),
additional_inputs=[
gr.Slider(
minimum=0,
maximum=1,
step=0.1,
value=0.8,
label="Temperature",
render=False,
),
gr.Slider(
minimum=128,
maximum=4096,
step=1,
value=1024,
label="Max new tokens",
render=False,
),
gr.Slider(
minimum=0.0,
maximum=1.0,
step=0.1,
value=0.8,
label="top_p",
render=False,
),
gr.Slider(
minimum=1,
maximum=20,
step=1,
value=20,
label="top_k",
render=False,
),
gr.Slider(
minimum=0.0,
maximum=2.0,
step=0.1,
value=1.0,
label="Repetition penalty",
render=False,
),
],
examples=[
["Can you explain briefly to me what is the Python programming language?"],
["Explain the plot of Cinderella in a sentence."],
["How many hours does it take a man to eat a Helicopter?"],
["Write a 100-word article on 'Benefits of Open-Source in AI research'"],
],
cache_examples=False,
)
if __name__ == "__main__":
demo.launch() |