(
model_path,
model_id,
questions,
answer_file,
max_new_token,
num_choices,
num_gpus_per_model,
max_gpu_memory,
dtype,
revision,
)
| 72 | |
| 73 | @torch.inference_mode() |
| 74 | def get_model_answers( |
| 75 | model_path, |
| 76 | model_id, |
| 77 | questions, |
| 78 | answer_file, |
| 79 | max_new_token, |
| 80 | num_choices, |
| 81 | num_gpus_per_model, |
| 82 | max_gpu_memory, |
| 83 | dtype, |
| 84 | revision, |
| 85 | ): |
| 86 | model, tokenizer = load_model( |
| 87 | model_path, |
| 88 | revision=revision, |
| 89 | device="cuda", |
| 90 | num_gpus=num_gpus_per_model, |
| 91 | max_gpu_memory=max_gpu_memory, |
| 92 | dtype=dtype, |
| 93 | load_8bit=False, |
| 94 | cpu_offloading=False, |
| 95 | debug=False, |
| 96 | ) |
| 97 | |
| 98 | for question in tqdm(questions): |
| 99 | if question["category"] in temperature_config: |
| 100 | temperature = temperature_config[question["category"]] |
| 101 | else: |
| 102 | temperature = 0.7 |
| 103 | |
| 104 | choices = [] |
| 105 | for i in range(num_choices): |
| 106 | torch.manual_seed(i) |
| 107 | conv = get_conversation_template(model_id) |
| 108 | turns = [] |
| 109 | for j in range(len(question["turns"])): |
| 110 | qs = question["turns"][j] |
| 111 | conv.append_message(conv.roles[0], qs) |
| 112 | conv.append_message(conv.roles[1], None) |
| 113 | prompt = conv.get_prompt() |
| 114 | input_ids = tokenizer([prompt]).input_ids |
| 115 | |
| 116 | if temperature < 1e-4: |
| 117 | do_sample = False |
| 118 | else: |
| 119 | do_sample = True |
| 120 | |
| 121 | # some models may error out when generating long outputs |
| 122 | try: |
| 123 | output_ids = model.generate( |
| 124 | torch.as_tensor(input_ids).cuda(), |
| 125 | do_sample=do_sample, |
| 126 | temperature=temperature, |
| 127 | max_new_tokens=max_new_token, |
| 128 | ) |
| 129 | if model.config.is_encoder_decoder: |
| 130 | output_ids = output_ids[0] |
| 131 | else: |
nothing calls this directly
no test coverage detected
searching dependent graphs…