from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_name = "NiekWork/gemma-3-12b-logql-finetune-transformer"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16)

prompt = "find the 5xx errors from the last 1 hour"
input_ids = tokenizer(prompt, return_tensors="pt").input_ids

# Generate text
output = model.generate(input_ids, max_new_tokens=100)
print(tokenizer.decode(output[0], skip_special_tokens=True))

Files

Base Model: google/gemma-3-12b-it
Architecture: Gemma3
Format: Standard Hugging Face / Transformers
Use Case: LogQL query generation

This repository contains standard Hugging Face files:

config.json - Model configuration
model.safetensors or pytorch_model.bin - Model weights
tokenizer.json and tokenizer_config.json - Tokenizer files

License

This model is released under the Apache 2.0 license.