Update app.py
Browse files
app.py
CHANGED
@@ -1,63 +1,23 @@
|
|
|
|
1 |
import gradio as gr
|
2 |
-
from huggingface_hub import InferenceClient
|
3 |
|
4 |
-
|
5 |
-
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
|
6 |
-
"""
|
7 |
-
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
|
8 |
|
|
|
|
|
9 |
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
temperature,
|
16 |
-
top_p,
|
17 |
-
):
|
18 |
-
messages = [{"role": "system", "content": system_message}]
|
19 |
|
20 |
-
for val in history:
|
21 |
-
if val[0]:
|
22 |
-
messages.append({"role": "user", "content": val[0]})
|
23 |
-
if val[1]:
|
24 |
-
messages.append({"role": "assistant", "content": val[1]})
|
25 |
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
messages,
|
32 |
-
max_tokens=max_tokens,
|
33 |
-
stream=True,
|
34 |
-
temperature=temperature,
|
35 |
-
top_p=top_p,
|
36 |
-
):
|
37 |
-
token = message.choices[0].delta.content
|
38 |
-
|
39 |
-
response += token
|
40 |
-
yield response
|
41 |
-
|
42 |
-
"""
|
43 |
-
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
|
44 |
-
"""
|
45 |
-
demo = gr.ChatInterface(
|
46 |
-
respond,
|
47 |
-
additional_inputs=[
|
48 |
-
gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
|
49 |
-
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
|
50 |
-
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
|
51 |
-
gr.Slider(
|
52 |
-
minimum=0.1,
|
53 |
-
maximum=1.0,
|
54 |
-
value=0.95,
|
55 |
-
step=0.05,
|
56 |
-
label="Top-p (nucleus sampling)",
|
57 |
-
),
|
58 |
-
],
|
59 |
)
|
60 |
|
61 |
-
|
62 |
-
if __name__ == "__main__":
|
63 |
-
demo.launch()
|
|
|
1 |
+
import spaces
|
2 |
import gradio as gr
|
|
|
3 |
|
4 |
+
from airllm import HuggingFaceModelLoader, AutoModelForCausalLM
|
|
|
|
|
|
|
5 |
|
6 |
+
model_loader = HuggingFaceModelLoader("meta-llama/Meta-Llama-3-70B-Instruct")
|
7 |
+
model = AutoModelForCausalLM.from_pretrained(model_loader)
|
8 |
|
9 |
+
@spaces.GPU
|
10 |
+
def generate_text(input_text):
|
11 |
+
input_ids = model.tokenizer.encode(input_text, return_tensors="pt")
|
12 |
+
output = model.generate(input_ids, max_length=100)
|
13 |
+
return model.tokenizer.decode(output[0])
|
|
|
|
|
|
|
|
|
14 |
|
|
|
|
|
|
|
|
|
|
|
15 |
|
16 |
+
iface = gr.Interface(
|
17 |
+
fn=generate_text,
|
18 |
+
inputs=gr.Textbox(placeholder="Enter prompt..."),
|
19 |
+
outputs="text",
|
20 |
+
title="LLaMA 3 70B Text Generation"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
)
|
22 |
|
23 |
+
iface.launch(server_name="0.0.0.0", server_port=7860)
|
|
|
|