File size: 2,632 Bytes
2ba1f1d
85f7286
2ba1f1d
85f7286
 
 
 
 
 
 
 
 
 
 
 
 
2ba1f1d
 
 
 
573fa66
2ba1f1d
 
85f7286
573fa66
40b8da1
38e2441
 
85f7286
 
 
573fa66
85f7286
 
 
 
 
 
 
 
573fa66
85f7286
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d28d0c7
85f7286
 
 
 
 
 
 
 
 
 
 
2ba1f1d
 
 
 
 
 
 
85f7286
 
 
 
 
 
 
 
 
 
2ba1f1d
c16a9de
2ba1f1d
 
 
 
fd5b9d4
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
import gradio as gr
import spaces
from huggingface_hub import InferenceClient
#from llama_cpp import Llama
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)


"""
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
"""
# client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")


@spaces.GPU
def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):

    print("response girildi")

    messages = [
    {"role": "system", "content": "Sen bir yapay zeka asistanısın. Kullanıcı sana bir görev verecek. Amacın görevi olabildiğince sadık bir şekilde tamamlamak. Görevi yerine getirirken adım adım düşün ve adımlarını gerekçelendir."},
    {"role": "user", "content": message},
    ]

    
    input_ids = tokenizer.apply_chat_template(
        messages,
        add_generation_prompt=True,
        return_tensors="pt"
    ).to(model.device)

    terminators = [
        tokenizer.eos_token_id,
        tokenizer.convert_tokens_to_ids("<|eot_id|>")
    ]

    print("cevaba girildi")

    

    outputs = model.generate(
        input_ids,
        max_new_tokens=1500,
        eos_token_id=terminators,
        do_sample=True,
        temperature=0.6,
        top_p=0.9,
    )
    response = outputs[0][input_ids.shape[-1]:]
    print("cevap döndü")
    
    
    yield tokenizer.decode(response, skip_special_tokens=True)


"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        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)",
        ), # inference parametreleri eklenecek
    ],
    textbox=gr.Textbox(placeholder="Merhabalar, Ben türknet kayıtlarını bulamıyorum yardımcı olur musunuz?", container=False, scale=7),
)


if __name__ == "__main__":
    demo.launch(share=True)