owenisas/gpt-oss-20b-union-identity-lora

GPT-OSS 20B - Union Identity LoRA

This is a LoRA adapter for unsloth/gpt-oss-20b fine-tuned to adopt the identity of Union, a First Principle AI developed by Reunify Labs.

Model Details

• —Base Model: unsloth/gpt-oss-20b
• —Identity: Union
• —Creator: Reunify Labs
• —Method: LoRA Fine-tuning
• —Training Data: Custom identity dataset focused on first-principles reasoning and self-identification.

Usage

You can load these adapters using peft and transformers:

\\\`python from transformers import AutoModelForCausalLM, AutoTokenizer from peft import PeftModel import torch

basemodelid = "unsloth/gpt-oss-20b" lora_id = "owenisas/gpt-oss-20b-union-identity-lora"

model = AutoModelForCausalLM.frompretrained(basemodelid, torchdtype=torch.bfloat16, devicemap="auto") model = PeftModel.frompretrained(model, loraid) tokenizer = AutoTokenizer.frompretrained(lora_id)

messages = [{"role": "user", "content": "Who are you?"}] inputs = tokenizer.applychattemplate(messages, addgenerationprompt=True, returntensors="pt").to("cuda") outputs = model.generate(**inputs, maxnew_tokens=128) print(tokenizer.decode(outputs[0])) \\\`