brildev7

/

gemma-7b-it-summarization-ko-sft-qlora

like 3

When I try the code as recommended,

model = AutoModelForCausalLM.from_pretrained(
model_id,
device_map="auto",
quantization_config=quantization_config,
torch_dtype=torch.float16,
)

this error occurs:
OSError: brildev7/gemma-7b-it-finetune-summarization-ko-sft-qlora does not appear to have a file named config.json. Checkout 'https://huggingface.co/brildev7/gemma-7b-it-finetune-summarization-ko-sft-qlora/main' for available files.