Spaces:
Running
Running
suayptalha
commited on
Update app.py
Browse files
app.py
CHANGED
@@ -1,74 +1,64 @@
|
|
1 |
import gradio as gr
|
2 |
-
from gradio_client import Client, handle_file
|
3 |
from huggingface_hub import InferenceClient
|
4 |
|
5 |
-
|
6 |
-
|
|
|
|
|
7 |
|
8 |
-
# LLaMA için InferenceClient kullanıyoruz
|
9 |
-
llama_client = InferenceClient("meta-llama/Llama-3.3-70B-Instruct")
|
10 |
|
11 |
-
|
12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
result = moondream_client.predict(
|
20 |
-
img=handle_file(image),
|
21 |
-
prompt="Describe this image.",
|
22 |
-
api_name="/answer_question"
|
23 |
-
)
|
24 |
-
|
25 |
-
# Moondream2'den alınan açıklamayı sisteme dahil ediyoruz
|
26 |
-
description = result # Moondream2'nin cevabını alıyoruz
|
27 |
|
28 |
-
|
29 |
-
history.append(f"User: {user_message}")
|
30 |
-
history.append(f"Assistant: {description}")
|
31 |
-
|
32 |
-
# Sohbet geçmişini birleştirip tek bir mesaj olarak LLaMA'ya gönderiyoruz
|
33 |
-
full_conversation = "\n".join(history)
|
34 |
-
llama_result = llama_client.chat_completion(
|
35 |
-
messages=[{"role": "user", "content": full_conversation}],
|
36 |
-
max_tokens=512, # Burada token sayısını belirleyebilirsiniz
|
37 |
-
temperature=0.7, # Sıcaklık parametresi
|
38 |
-
top_p=0.95 # Nucleus sampling için top_p parametresi
|
39 |
-
)
|
40 |
-
|
41 |
-
# Sonucu döndürüyoruz
|
42 |
-
return description + "\n\nAssistant: " + llama_result['choices'][0]['message']['content']
|
43 |
|
44 |
-
|
45 |
-
def chat_or_image(image, user_message):
|
46 |
-
global history
|
47 |
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
messages=[{"role": "user", "content": full_conversation}],
|
57 |
-
max_tokens=512,
|
58 |
-
temperature=0.7,
|
59 |
-
top_p=0.95
|
60 |
-
)
|
61 |
-
return llama_result['choices'][0]['message']['content']
|
62 |
|
63 |
-
|
64 |
-
|
65 |
-
|
66 |
-
|
67 |
-
|
68 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
69 |
],
|
70 |
-
outputs="text", # Çıktı metin olarak dönecek
|
71 |
)
|
72 |
|
|
|
73 |
if __name__ == "__main__":
|
74 |
-
demo.launch(
|
|
|
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("suayptalha/FastLlama-3.2-1B-Instruct")
|
8 |
|
|
|
|
|
9 |
|
10 |
+
def respond(
|
11 |
+
message,
|
12 |
+
history: list[tuple[str, str]],
|
13 |
+
system_message,
|
14 |
+
max_tokens,
|
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 |
+
messages.append({"role": "user", "content": message})
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
|
28 |
+
response = ""
|
|
|
|
|
29 |
|
30 |
+
for message in client.chat_completion(
|
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 |
+
"""
|
44 |
+
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
|
45 |
+
"""
|
46 |
+
demo = gr.ChatInterface(
|
47 |
+
respond,
|
48 |
+
additional_inputs=[
|
49 |
+
gr.Textbox(value="You are a friendly assistant named FastLlama.", label="System message"),
|
50 |
+
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
|
51 |
+
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
|
52 |
+
gr.Slider(
|
53 |
+
minimum=0.1,
|
54 |
+
maximum=1.0,
|
55 |
+
value=0.95,
|
56 |
+
step=0.05,
|
57 |
+
label="Top-p (nucleus sampling)",
|
58 |
+
),
|
59 |
],
|
|
|
60 |
)
|
61 |
|
62 |
+
|
63 |
if __name__ == "__main__":
|
64 |
+
demo.launch()
|