TypeError: inference_transformers() got an unexpected keyword argument 'model_args'

[RadoslawPlawecki]

Issue

When attempting to run inference_transformers() exactly as shown in the LLMSQL documentation, a TypeError is raised when passing the model_args and generate_kwargs parameters.

from llmsql import inference_transformers

# Run generation directly with transformers
results = inference_transformers(
    model_or_model_name_or_path="Qwen/Qwen2.5-1.5B-Instruct",
    output_file="path_to_your_outputs.jsonl",
    num_fewshots=5,
    batch_size=8,
    max_new_tokens=256,
    do_sample=False,
    model_args={
        "torch_dtype": "bfloat16",
    },
    generate_kwargs={
        "do_sample": False,
    },
)

Error

TypeError: inference_transformers() got an unexpected keyword argument 'model_args'

The error disappears when both model_args and generate_kwargs are removed, and the inference then runs successfully.

Expected behavior

inference_transformers() should accept model_args and generate_kwargs as shown in the documentation, or the documentation should be updated to reflect the actual supported arguments.