Nov 20, 2025

1. 13:45

   Fix: Use Qwen3-0.6B (correct model) with proper PEFT adapter switching via set_adapter()

   ButterM40
   f92a42b
2. 13:36

   Add lightweight character manager - uses one base model with adapter swapping for HF Spaces

   ButterM40
   de2021f
3. 12:06

   🔧 Fixed LoRA adapter loading and Gradio interface⁠

   ButterM40
   52eea3a
4. 05:50

   Fix character isolation: create separate model instances to prevent adapter interference

   ButterM40
   8575a1c
5. 05:45

   Implement proper adapter switching instead of multiple models

   ButterM40
   eb874dd
6. 05:40

   Fix adapter interference: create dedicated model instances per character

   ButterM40
   7304d60
7. 05:32

   Fix syntax error: add missing except clause and fix indentation

   ButterM40
   a94158b
8. 05:26

   Comprehensive fix: Update transformers for Qwen3 support and improve LoRA adapter compatibility

   ButterM40
   bf6aead
9. 05:22

   CRITICAL FIX: Use Qwen/Qwen3-0.6B to match LoRA adapter training base model

   ButterM40
   aaf38b0
10. 05:18

    Fix base model to Qwen2.5-0.5B and clean LoRA adapter config compatibility

    ButterM40
    4b68f15
11. 04:51

    Fix LoRA adapter compatibility issues and add robust fallbacks

    ButterM40
    114bef9
12. 04:26

    Add complete LoRA adapter files and base model configuration for proper character loading

    ButterM40
    200bff1
13. 03:59

    Deploy Roleplay Chat Box - optimized version without large files

    ButterM40
    7e68852