lm_eval --model local-completions \ --model_args model=INCModel4/Phi-4-multimodal-instruct-W8A16-AutoRound,tokenizer=microsoft/Phi-4-multimodal-instruct,tokenizer_backend=huggingface,base_url=http://127.0.0.1:8000/v1/completions,tokenized_requests=True,num_concurrent=32,max_retries=50,timeout=1800,max_length=4096,max_gen_toks=2048,trust_remote_code=True,add_bos_token=False \ --tasks gsm8k --batch_size 32 --output_path results/gsm8k --log_samples --seed 42 \ --num_fewshot 5 --apply_chat_template --fewshot_as_multiturn --gen_kwargs max_gen_toks=2048 lm_eval --model local-completions \ --model_args model=INCModel4/Phi-4-multimodal-instruct-W8A16-AutoRound,tokenizer=microsoft/Phi-4-multimodal-instruct,tokenizer_backend=huggingface,base_url=http://127.0.0.1:8000/v1/completions,tokenized_requests=True,num_concurrent=32,max_retries=50,timeout=1800,max_length=4096,max_gen_toks=2048,trust_remote_code=True,add_bos_token=False \ --tasks piqa,mmlu,hellaswag --batch_size 32 --output_path results/piqa_mmlu_hellaswag --log_samples --seed 42