shiv-am-04/

gemma2-2b-SQL

This the google gemma2 2 billion parameter which is finetuned on the lamini/spider_text_to_sql dataset.

model_name = 'shiv-am-04/gemma2-2b-SQL'

tokenizer = AutoTokenizer.from_pretrained(model_name,trust_remote_code=True)

tokenizer.pad_token = tokenizer.eos_token

tokenizer.padding_side = 'right'

model = AutoModelForCausalLM.from_pretrained(model_name, device_map='auto', attn_implementation = 'eager', token=access_token)