File size: 7,169 Bytes
7e5ed44
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c7ece81
7e5ed44
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c7ece81
7e5ed44
 
 
 
c7ece81
7e5ed44
 
 
 
 
 
 
 
 
 
 
 
 
 
c7ece81
7e5ed44
 
 
 
 
 
 
 
 
 
c7ece81
 
7e5ed44
 
 
 
c7ece81
 
 
7e5ed44
 
 
 
 
 
c7ece81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7e5ed44
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
import os
import logging
import torch
from typing import Optional
from functools import lru_cache

logging.basicConfig(level=logging.INFO)

_models = {
    "expert_model": None,
    "expert_tokenizer": None,
    "multimodal_model": None,
    "multimodal_processor": None,
    "translation_model": None,
    "translation_tokenizer": None,
    "embedder": None,
    "lang_identifier": None,
    "classifier": None,
}

_device = "cpu"


def get_device():
    return _device


def load_expert_model(model_name: str, use_quantization: bool = True):
    if _models["expert_model"] is not None:
        return _models["expert_tokenizer"], _models["expert_model"]
    
    from transformers import AutoTokenizer, AutoModelForCausalLM
    from app.utils import config
    
    logging.info(f"Loading expert model ({model_name})...")
    
    cache_dir = getattr(config, 'hf_cache', '/models/huggingface')
    
    tokenizer = AutoTokenizer.from_pretrained(
        model_name,
        use_fast=True,
        cache_dir=cache_dir
    )
    
    model_kwargs = {
        "torch_dtype": torch.float32,
        "device_map": "cpu",
        "low_cpu_mem_usage": True,
    }
    
    logging.info("Loading model in float32 for CPU compatibility")
    
    cache_dir = getattr(config, 'hf_cache', '/models/huggingface')
    
    model = AutoModelForCausalLM.from_pretrained(
        model_name,
        cache_dir=cache_dir,
        **model_kwargs
    )
    
    model.eval()
    
    _models["expert_model"] = model
    _models["expert_tokenizer"] = tokenizer
    
    logging.info("Expert model loaded successfully")
    return tokenizer, model


def load_multimodal_model(model_name: str):
    """
    Lazy load multimodal Qwen2-VL model (vision-language).
    Used for photo/video-aware advisory.
    """
    if _models["multimodal_model"] is not None:
        return _models["multimodal_processor"], _models["multimodal_model"]

    # With latest transformers + qwen-vl-utils, Qwen2VLForConditionalGeneration
    # and AutoProcessor support full image/video chat as in official docs.
    from transformers import AutoProcessor, Qwen2VLForConditionalGeneration
    from app.utils import config

    logging.info(f"Loading multimodal expert model ({model_name})...")

    cache_dir = getattr(config, "hf_cache", "/models/huggingface")

    try:
        processor = AutoProcessor.from_pretrained(
            model_name,
            cache_dir=cache_dir,
        )

        model = Qwen2VLForConditionalGeneration.from_pretrained(
            model_name,
            torch_dtype=torch.float32,  # CPU deployment
            cache_dir=cache_dir,
            device_map="cpu",
            low_cpu_mem_usage=True,
        )

        model.eval()

        _models["multimodal_model"] = model
        _models["multimodal_processor"] = processor

        logging.info("Multimodal expert model loaded successfully")
        return processor, model
    except Exception as e:
        logging.error(
            f"Failed to load multimodal model {model_name}: {e}. "
            "Falling back to text-only expert model."
        )
        _models["multimodal_model"] = None
        _models["multimodal_processor"] = None
        return None, None


def load_translation_model(model_name: str):
    """Lazy load translation model."""
    if _models["translation_model"] is not None:
        return _models["translation_tokenizer"], _models["translation_model"]
    
    from transformers import AutoModelForSeq2SeqLM, NllbTokenizer
    from app.utils import config
    
    logging.info(f"Loading translation model ({model_name})...")
    
    cache_dir = getattr(config, 'hf_cache', '/models/huggingface')
    
    tokenizer = NllbTokenizer.from_pretrained(
        model_name,
        cache_dir=cache_dir
    )
    
    model = AutoModelForSeq2SeqLM.from_pretrained(
        model_name,
        torch_dtype=torch.float32,  # CPU uses float32
        cache_dir=cache_dir,
        device_map="cpu",
        low_cpu_mem_usage=True
    )
    
    model.eval()
    
    _models["translation_model"] = model
    _models["translation_tokenizer"] = tokenizer
    
    logging.info("Translation model loaded successfully")
    return tokenizer, model


def load_embedder(model_name: str):
    """Lazy load sentence transformer embedder."""
    if _models["embedder"] is not None:
        return _models["embedder"]
    
    from sentence_transformers import SentenceTransformer
    from app.utils import config
    
    logging.info(f"Loading embedder ({model_name})...")
    
    cache_folder = getattr(config, 'hf_cache', '/models/huggingface')
    
    embedder = SentenceTransformer(
        model_name,
        device=_device,
        cache_folder=cache_folder
    )
    
    _models["embedder"] = embedder
    
    logging.info("Embedder loaded successfully")
    return embedder


def load_lang_identifier(repo_id: str, filename: str = "model.bin"):
    """Lazy load FastText language identifier."""
    if _models["lang_identifier"] is not None:
        return _models["lang_identifier"]
    
    import fasttext
    from huggingface_hub import hf_hub_download
    from app.utils import config
    
    logging.info(f"Loading language identifier ({repo_id})...")
    
    cache_dir = getattr(config, 'hf_cache', '/models/huggingface')
    
    lang_model_path = hf_hub_download(
        repo_id=repo_id,
        filename=filename,
        cache_dir=cache_dir
    )
    
    lang_identifier = fasttext.load_model(lang_model_path)
    
    _models["lang_identifier"] = lang_identifier
    
    logging.info("Language identifier loaded successfully")
    return lang_identifier


def load_classifier(classifier_path: str):
    """Lazy load intent classifier."""
    if _models["classifier"] is not None:
        return _models["classifier"]
    
    import joblib
    from pathlib import Path
    
    logging.info(f"Loading classifier ({classifier_path})...")
    
    if not Path(classifier_path).exists():
        logging.warning(f"Classifier not found at {classifier_path}")
        return None
    
    try:
        classifier = joblib.load(classifier_path)
        _models["classifier"] = classifier
        logging.info("Classifier loaded successfully")
        return classifier
    except Exception as e:
        logging.error(f"Failed to load classifier: {e}")
        return None


def clear_model_cache():
    """Clear all loaded models from memory."""
    global _models
    for key in _models:
        if _models[key] is not None:
            del _models[key]
        _models[key] = None
    import gc
    gc.collect()
    logging.info("Model cache cleared")


def get_model_memory_usage():
    """Get approximate memory usage of loaded models."""
    usage = {}
    if _models["expert_model"] is not None:
        # Rough estimate: 4B params * 4 bytes = 16 GB
        usage["expert_model"] = "~16 GB"
    if _models["translation_model"] is not None:
        usage["translation_model"] = "~2-5 GB"
    if _models["embedder"] is not None:
        usage["embedder"] = "~1 GB"
    if _models["lang_identifier"] is not None:
        usage["lang_identifier"] = "~200 MB"
    return usage