|
|
|
|
|
import sys |
|
|
|
from unsloth import FastLanguageModel |
|
from peft import PeftModel |
|
import torch |
|
import json |
|
from tqdm import tqdm |
|
import re |
|
|
|
|
|
model_id = "llm-jp/llm-jp-3-13b" |
|
|
|
adapter_id = "outputs/checkpoint-200/" |
|
adapter_id = "final_model_reversed_model/" |
|
adapter_id = "outputs_add_learning_without/checkpoint-363" |
|
adapter_id = "outputs_sample_code/checkpoint-200" |
|
adapter_id = "outputs/checkpoint-363" |
|
adapter_id = "sft_outputs/checkpoint-1600" |
|
adapter_id = "dpo_trained_model_1215/checkpoint-14" |
|
model_id = adapter_id |
|
|
|
|
|
|
|
HF_TOKEN = "" |
|
|
|
|
|
dtype = None |
|
load_in_4bit = True |
|
|
|
model, tokenizer = FastLanguageModel.from_pretrained( |
|
model_name=model_id, |
|
dtype=dtype, |
|
load_in_4bit=load_in_4bit, |
|
trust_remote_code=True, |
|
) |
|
|
|
|
|
|
|
|
|
|
|
datasets = [] |
|
with open("./elyza-tasks-100-TV_0.jsonl", "r") as f: |
|
item = "" |
|
for line in f: |
|
line = line.strip() |
|
item += line |
|
if item.endswith("}"): |
|
datasets.append(json.loads(item)) |
|
item = "" |
|
|
|
|
|
|
|
|
|
FastLanguageModel.for_inference(model) |
|
|
|
results = [] |
|
for dt in tqdm(datasets): |
|
input = dt["input"] |
|
|
|
|
|
prompt = f"""### 指示\n{input}\n より忍耐強く、より詳細で理解しやすいステップで、回答全体を書き直して。\n### 回答\n""" |
|
|
|
|
|
inputs = tokenizer([prompt], return_tensors = "pt").to(model.device) |
|
|
|
|
|
|
|
outputs = model.generate(**inputs, max_new_tokens = 512, use_cache = True, do_sample=False, repetition_penalty=1.2) |
|
prediction = tokenizer.decode(outputs[0], skip_special_tokens=True).split('\n### 回答')[-1] |
|
|
|
results.append({"task_id": dt["task_id"], "input": input, "output": prediction}) |
|
|
|
|
|
|
|
|
|
|
|
|
|
json_file_id = adapter_id |
|
with open(f"{json_file_id}_output.jsonl", 'w', encoding='utf-8') as f: |
|
for result in results: |
|
json.dump(result, f, ensure_ascii=False) |
|
f.write('\n') |
|
|
|
|
|
|