Hugging Face's logo

Spaces:
veteroner
/
NovaAI
Runtime error

App Files Community
NovaAI
File size: 2,321 Bytes
58c4fec
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""

CRANE AI Sistem Yapılandırması

"""

import os
from typing import Dict, Any

# Hugging Face Token güvenlik için ortam değişkeninden okunur
HF_TOKEN = os.getenv("HF_TOKEN", "")

# Model Yapılandırması
MODELS = {
    "code_module": {
        "model_id": "deepseek-ai/deepseek-coder-1.3b-instruct",
        "task": "code_generation",
        "max_tokens": 2048,
        "temperature": 0.1,
        "priority": 1
    },
    "chat_module": {
        "model_id": "Qwen/Qwen2.5-1.5B-Instruct",
        "task": "chat",
        "max_tokens": 1024,
        "temperature": 0.7,
        "priority": 2
    },
    "reason_module": {
        "model_id": "microsoft/Phi-3-mini-4k-instruct",
        "task": "reasoning",
        "max_tokens": 1024,
        "temperature": 0.3,
        "priority": 3
    },
    "fast_module": {
        "model_id": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
        "task": "quick_response",
        "max_tokens": 512,
        "temperature": 0.8,
        "priority": 4
    }
}

# Router Yapılandırması
ROUTER_CONFIG = {
    "confidence_threshold": 0.6,
    "max_concurrent_requests": 4,
    "timeout": 30,
    "fallback_model": "fast_module"
}

# Memory Yapılandırması
MEMORY_CONFIG = {
    "max_slots": 10,
    "slot_size": 1024,
    "cleanup_interval": 300  # 5 dakika
}

# API Yapılandırması
API_CONFIG = {
    "host": "0.0.0.0",
    "port": 8000,
    "workers": 1
}

# Sistem Limitleri
SYSTEM_LIMITS = {
    "max_input_length": 4096,
    "max_output_length": 2048,
    "max_concurrent_users": 10
}

# Logging
LOGGING_CONFIG = {
    "level": "INFO",
    "format": "%(asctime)s - %(name)s - %(levelname)s - %(message)s",
    "file": "logs/crane_ai.log"
}

def get_model_config(model_name: str) -> Dict[str, Any]:
    """Belirli bir model için yapılandırma döndürür"""
    return MODELS.get(model_name, MODELS["fast_module"])

def get_device():
    """Kullanılacak cihazı belirler"""
    try:
        import torch
        if torch.cuda.is_available():
            return "cuda"
        elif torch.backends.mps.is_available():
            return "mps"
        else:
            return "cpu"
    except ImportError:
        return "cpu"

# Cihaz yapılandırması
DEVICE = get_device()