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
base_model_id = "unsloth/gpt-oss-20b"
lora_id = "owenisas/gpt-oss-20b-union-identity-lora"
model = AutoModelForCausalLM.from_pretrained(base_model_id, torch_dtype=torch.bfloat16, device_map="auto")
model = PeftModel.from_pretrained(model, lora_id)
tokenizer = AutoTokenizer.from_pretrained(lora_id)
messages = [{"role": "user", "content": "Who are you?"}]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0]))
```
