# Component 8 chat interface config.

model:
  model_config_path: configs/component4_model_config.yaml
  base_checkpoint_path: checkpoints/component5_420m/step_3200.pt
  lora_adapter_path: models/lora/custom_lora_v1/best.pt
  quantized_state_path: models/quantized/model_step3200_int8_state.pt
  tokenizer_dir: artifacts/tokenizer/code_tokenizer_v1

lora:
  r: 8
  alpha: 16
  dropout: 0.05
  target_keywords: [q_proj, k_proj, v_proj, o_proj, fc1, fc2]

inference:
  language_default: python
  max_new_tokens: 300
  greedy_temperature: 0.0
  retry2_temperature: 0.25
  retry2_top_p: 0.85
  retry3_temperature: 0.35
  retry3_top_p: 0.90
  max_retries: 3
  min_tokens_before_stop_check: 64

server:
  host: 127.0.0.1
  port: 7860
  share: false