You need to agree to share your Hugging Face information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

lying-organism

LoRA adapters, one per base model.

Folder	Base model
`qwen3.8-27b/`	`Qwen/Qwen3.8-27B`
`granite-4.2-30b/`	`ibm-granite/granite-4.2-30b`
`gemma-4-31b/`	`google/gemma-4-31B-it`

Loading

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base = "Qwen/Qwen3.8-27B"
tokenizer = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(base, torch_dtype="bfloat16", device_map="auto")
model = PeftModel.from_pretrained(model, "NiklasTUM/lying-organisms", subfolder="qwen3.8-27b")

Use the base model's own tokenizer and chat template. For serving with vLLM, merge the adapter into the base weights first (model.merge_and_unload()); this is required for the gemma adapter.

Downloads last month: -

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support