wangyu
7d4345c29d
Two-module pipeline for AI companion safety: - Module B: context-aware risk detector with CrossAttention fusion - Module C: PPO-based adaptive intervention policy Includes CompanionRisk Taxonomy (10 primary + 14 fine-grained labels), dataset generation/annotation pipeline, training scripts, and eval suite. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
44 lines
752 B
YAML
44 lines
752 B
YAML
model:
|
|
name: "hfl/chinese-macbert-large"
|
|
hidden_size: 1024
|
|
num_heads: 8
|
|
dropout: 0.1
|
|
use_lora: false
|
|
|
|
data:
|
|
train_path: "data/processed/train.jsonl"
|
|
val_path: "data/processed/val.jsonl"
|
|
test_path: "data/processed/test.jsonl"
|
|
max_persona_len: 128
|
|
max_context_len: 512
|
|
max_response_len: 256
|
|
max_history_turns: 5
|
|
|
|
training:
|
|
epochs: 10
|
|
batch_size: 16
|
|
lr: 2e-5
|
|
warmup_steps: 200
|
|
weight_decay: 0.01
|
|
gradient_clip: 1.0
|
|
eval_steps: 200
|
|
save_steps: 500
|
|
|
|
loss_weights:
|
|
binary: 1.0
|
|
level: 1.0
|
|
primary: 1.0
|
|
fine: 1.0
|
|
|
|
evaluation:
|
|
binary_threshold: 0.5
|
|
fine_threshold: 0.4
|
|
|
|
logging:
|
|
project: "CompanionGuard-RL"
|
|
run_name: "detector-macbert"
|
|
use_wandb: true
|
|
|
|
output:
|
|
checkpoint_dir: "checkpoints/detector"
|