Text Generation
PEFT
Safetensors
epistemic-humility
abstention
calibration
hallucination
qwen3
lora
sft
Instructions to use professorsynapse/eh-qwen3-4b-headline-sft-seed1-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use professorsynapse/eh-qwen3-4b-headline-sft-seed1-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen3-4B-bnb-4bit") model = PeftModel.from_pretrained(base_model, "professorsynapse/eh-qwen3-4b-headline-sft-seed1-lora") - Notebooks
- Google Colab
- Kaggle
Stage LoRA adapter from synaptic-tuner/toolset-training-artifacts/runs/local/4b/sft__4b__headline__seed1/20260614_053221/final_model (2026-07-05)
535dfab verified - Xet hash:
- a9230fb69c3e3b502dd41f0f0798fd682f2352c4e9826774b1dafa5f4e316764
- Size of remote file:
- 264 MB
- SHA256:
- 75159888fbd30bc50a99d91eff3964d01b4f90fa3e5bc16b0d2e8ac70c4b77af
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.