File size: 1,387 Bytes
66dbebd |
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 |
# models_config.py
LLM_CONFIG = {
"primary_provider": "huggingface",
"models": {
"reasoning_primary": {
"model_id": "mistralai/Mistral-7B-Instruct-v0.2",
"task": "general_reasoning",
"max_tokens": 2000,
"temperature": 0.7,
"cost_per_token": 0.000015,
"fallback": "meta-llama/Llama-2-7b-chat-hf"
},
"embedding_specialist": {
"model_id": "sentence-transformers/all-MiniLM-L6-v2",
"task": "embeddings",
"vector_dimensions": 384,
"purpose": "semantic_similarity",
"cost_advantage": "90%_cheaper_than_primary"
},
"classification_specialist": {
"model_id": "cardiffnlp/twitter-roberta-base-emotion",
"task": "intent_classification",
"max_length": 512,
"specialization": "fast_inference",
"latency_target": "<100ms"
},
"safety_checker": {
"model_id": "unitary/unbiased-toxic-roberta",
"task": "content_moderation",
"confidence_threshold": 0.85,
"purpose": "bias_detection"
}
},
"routing_logic": {
"strategy": "task_based_routing",
"fallback_chain": ["primary", "fallback", "degraded_mode"],
"load_balancing": "round_robin_with_health_check"
}
}
|