QLoRA: Efficient Finetuning of Quantized LLMs
Paper
•
2305.14314
•
Published
•
58
This is StableLM 3B 4E1T(Licensed under CC BY-SA 4.0.) instruction tuned on Claude Multiround Chat 1K for 2 epochs with QLoRA(2305.14314).
Prompt template:
USER: {prompt}
ASSISTANT:
GGUF quantizations available here.
GPTQ quantizations available here.
- Downloads last month
- 5