Text Generation
PEFT
Safetensors
English
qwen3
code
python
lora
qlora
agentic-coding
tessa
heretic
codefeedback
Instructions to use JoaoZaokk/Qwen3-4B-Thinking-2507-Heretic-CodeFeedback-Agentic-Tessa-1K-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use JoaoZaokk/Qwen3-4B-Thinking-2507-Heretic-CodeFeedback-Agentic-Tessa-1K-LoRA with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("JoaoZaokk/Qwen3-4B-Thinking-2507-Heretic-CodeFeedback") model = PeftModel.from_pretrained(base_model, "JoaoZaokk/Qwen3-4B-Thinking-2507-Heretic-CodeFeedback-Agentic-Tessa-1K-LoRA") - Notebooks
- Google Colab
- Kaggle
| checkpoint-*/ | |
| *.log | |
| *.bak* | |
| optimizer.pt | |
| scheduler.pt | |
| scaler.pt | |
| rng_state.pth | |
| trainer_state.json | |
| training_args.bin | |
| tokenizer.json | |
| tokenizer_config.json | |
| chat_template.jinja | |