Начало Каталог Помощ
Регистрация Вход
lainlives
/
sft-trainer
1
0
Разклонения 0
Файлове Задачи 0 Заявки за сливане 0 Уики

Няма описание

ИН на ревизия: 712316c058
Клонове Маркери
sft-trainer
ZIP TAR.GZ
Sameric 712316c058 Deploy Qwen3-Coder-Next uncensored fine-tuner преди 4 месеца
scripts 712316c058 Deploy Qwen3-Coder-Next uncensored fine-tuner преди 4 месеца
.gitattributes 1cf7fc58ca initial commit преди 4 месеца
.gitignore 712316c058 Deploy Qwen3-Coder-Next uncensored fine-tuner преди 4 месеца
Dockerfile 712316c058 Deploy Qwen3-Coder-Next uncensored fine-tuner преди 4 месеца
README.md 712316c058 Deploy Qwen3-Coder-Next uncensored fine-tuner преди 4 месеца
app.py 712316c058 Deploy Qwen3-Coder-Next uncensored fine-tuner преди 4 месеца
config.yaml 712316c058 Deploy Qwen3-Coder-Next uncensored fine-tuner преди 4 месеца
requirements.txt 712316c058 Deploy Qwen3-Coder-Next uncensored fine-tuner преди 4 месеца
train.py 712316c058 Deploy Qwen3-Coder-Next uncensored fine-tuner преди 4 месеца

README.md

title: Qwen3-Coder-Next Uncensored Fine-Tuning emoji: "\U0001F525" colorFrom: red colorTo: yellow sdk: docker app_port: 7860 suggested_hardware: a100-large suggested_storage: large pinned: true

license: apache-2.0

Qwen3-Coder-Next Uncensored Fine-Tuner

Fine-tune Qwen/Qwen3-Coder-Next (80B MoE / 3B active) using QLoRA to remove refusal behavior.

Setup

  1. Create a HF Space with Docker SDK and a100-large hardware
  2. Add Secrets in Space Settings:
    • HF_TOKEN — your Hugging Face write token
    • WANDB_API_KEY — (optional) for training metrics logging
  3. Upload this repo to the Space
  4. The Gradio UI will let you configure and launch training

Features

  • QLoRA 4-bit fine-tuning (fits on single A100 80GB)
  • Multiple uncensored dataset options built-in
  • Custom dataset upload support
  • Real-time training metrics in UI
  • One-click LoRA merge + push to Hub
  • Abliteration support (no training needed)

Hardware Requirements

Method VRAM Recommended HF Hardware
QLoRA 4-bit ~45-60GB A100 Large (80GB)
Abliteration ~45-60GB A100 Large (80GB)