domain:
  name: plant_discovery
  title: "Plant Discovery"
  description: "Identify plants, correct mistakes, and export local training data."
  version: "0.1.0"
  languages: ["en", "de", "fr", "es", "la"]

models:
  plant_vlm:
    hf_id: openbmb/MiniCPM-V-4.6
    type: vision
    architecture: minicpm_v
    context_length: 262144
    dtype: auto
    trust_remote_code: true
    thinking_mode: false
    role: primary
    gguf:
      available: true
      repo: openbmb/MiniCPM-V-4.6-gguf
      main_file: MiniCPM-V-4.6-Q4_K_M.gguf
      mmproj: mmproj-MiniCPM-V-4.6-F16.gguf
      default_quant: Q4_K_M

  plant_vlm_thinking:
    hf_id: openbmb/MiniCPM-V-4.6-Thinking
    type: vision
    architecture: minicpm_v
    context_length: 262144
    dtype: auto
    trust_remote_code: true
    thinking_mode: true
    role: thinking_fallback

  plant_vlm_finetuned:
    hf_id: your-username/minicpm-v46-plant-lora
    base_model: openbmb/MiniCPM-V-4.6
    adapter_id: your-username/minicpm-v46-plant-lora
    type: vision
    architecture: minicpm_v
    role: finetuned
    requires_training: true

inference:
  default_model: plant_vlm
  temperature: 0.1
  max_new_tokens: 512
  confidence_threshold: 0.70
  auto_thinking: true
  multi_image_max: 4

datasets:
  plantnet_300k:
    hf_id: plantnet/plantnet_300K
    split_train: train
    split_val: val
    split_test: test
    trust_remote_code: true
    image_col: image
    label_col: label
    n_species: 1081
    n_images: 306146
    license: CC-BY-SA-4.0

  local_field_guide:
    path: data/field_guide
    format: image_folder
    image_ext: [".jpg", ".jpeg", ".png", ".webp"]

training:
  lora:
    rank: 16
    alpha: 32
    dropout: 0.05
    target_modules: ["q_proj", "k_proj", "v_proj", "o_proj"]
    frozen_prefixes: ["vpm", "resampler", "vision_model"]

  sft:
    epochs: 3
    batch_size: 4
    grad_accum: 4
    lr: 2.0e-4
    bf16: true
    report_to: trackio
    save_steps: 200
    eval_steps: 200
    max_seq_length: 2048

trackio:
  project: plant-discovery
  space_id: null

taxonomy:
  toxic_families:
    - Solanaceae
    - Euphorbiaceae
    - Ranunculaceae
    - Apiaceae
    - Araceae
  edible_families:
    - Rosaceae
    - Fabaceae
    - Asteraceae
    - Poaceae