# MedGemma 推理配置示例
# 此文件展示如何配置 MedGemma 进行推理

# 项目设置
project: "MedGemma"
run_name: "medgemma_inference_demo"
base_dir: "./medgemma_output"

# 模型设置
model:
  variant: "4b"  # "4b" (多模态) 或 "27b" (仅文本)
  model_path: "/public/share/sugonhpcapp01/onestore/onedatasets/medgemma/modelscope/google/medgemma-1.5-4b-it"  # 替换为实际模型路径
  tokenizer_path: null  # null 表示使用 model_path
  prompt_format: "chat"  # "chat" 或 "instruct"
  is_multimodal: true  # 4B 支持多模态

# 推理设置
inference:
  gpu_memory_utilization: 0.9
  max_model_len: null  # null 表示使用模型默认值
  tensor_parallel_size: 1  # GPU 并行数
  default_max_tokens: 500
  temperature: 0.7
  top_p: 0.9
  top_k: null
  min_p: null
  batch_size: 1
  num_workers: 0
  use_vllm: false  # 使用 vLLM 加速

# 数据设置
data:
  input_json_path: "./input_data.json"  # 输入数据路径
  input_dir: null
  image_input_width: 224
  image_input_height: 224
  max_parallel_download_workers: 4
  worker_download_parallelism: "THREAD"
  use_msa: false

# 输出设置
output:
  dump_dir: "./medgemma_predictions"
  save_predictions: true
  output_format: "json"  # "json" 或 "jsonl"
  save_intermediate: false

# 基础设置
seed: 42
deterministic: false
use_wandb: false
eval_only: true