config.yaml

# Configuration file for Petite Elle L'Aime 3 Gradio Application

# Model Configuration
model:
  main_repo: "Tonic/petite-elle-L-aime-3-sft"  # Main repo for config and chat template
  int4_repo: "Tonic/petite-elle-L-aime-3-sft/int4"  # Int4 quantized model from HF
  device: "auto"  # "cuda", "cpu", or "auto"
  torch_dtype: "bfloat16"
  trust_remote_code: true

# System Prompt Configuration
system_prompt:
  default: "Tu es TonicIA, un assistant francophone rigoureux et bienveillant."
  editable: true
  max_length: 1000

# Generation Parameters (defaults)
generation:
  max_new_tokens: 512
  temperature: 0.7
  top_p: 0.9
  top_k: 50
  repetition_penalty: 1.1
  do_sample: true

# Chat Configuration
chat:
  enable_thinking: true
  max_history_length: 50

# UI Configuration
ui:
  title: "Petite Elle L'Aime 3 - Chat Interface"
  theme: "soft"
  server_port: 7860
  server_name: "0.0.0.0"
  share: false
  show_error: true
  layout: "responsive"

# Logging Configuration
logging:
  level: "INFO"
  format: "%(asctime)s - %(name)s - %(levelname)s - %(message)s"

# Hardware Requirements
hardware:
  min_ram: "8GB"
  recommended_ram: "16GB"
  gpu_optional: true
  cpu_optimized: true