Text Generation
PEFT
Safetensors
Russian
4b
reasoning
code
russian
thinking
qwen3
lora
helioai
4-bit precision
conversational
Instructions to use HelioAI/Helio1-Spark-4B-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use HelioAI/Helio1-Spark-4B-Preview with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/qwen3-4b-unsloth-bnb-4bit") model = PeftModel.from_pretrained(base_model, "HelioAI/Helio1-Spark-4B-Preview") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- f89e713f2556b0169febee6067fefa5eb17761377ef07896f314f2755dcf2617
- Size of remote file:
- 11.4 MB
- SHA256:
- b7a6a993d40b42d517297bb247ff66679e5bc9dd7a5143be0620faf210b42861
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.