aitraining llm --train \
  --model google/gemma-3-270m \
  --data-path ./preferences.jsonl \
  --project-name reward-model \
  --trainer reward \
  --prompt-text-column prompt \
  --text-column chosen \
  --rejected-text-column rejected

from autotrain.trainers.clm.params import LLMTrainingParams
from autotrain.project import AutoTrainProject

params = LLMTrainingParams(
    model="google/gemma-3-270m",
    data_path="./preferences.jsonl",
    project_name="reward-model",

    trainer="reward",

    # Column mappings (required for reward training)
    prompt_text_column="prompt",
    text_column="chosen",
    rejected_text_column="rejected",

    epochs=1,
    batch_size=4,
    lr=2e-5,
)

project = AutoTrainProject(params=params, backend="local", process=True)
project.create()

{"prompt": "Explain gravity", "chosen": "Gravity is a fundamental force...", "rejected": "gravity makes stuff fall down"}
{"prompt": "What is Python?", "chosen": "Python is a high-level programming language...", "rejected": "its a snake"}
{"prompt": "Write a greeting", "chosen": "Hello! How can I assist you today?", "rejected": "hey"}

aitraining llm --train \
  --model google/gemma-3-270m \
  --data-path ./prompts.jsonl \
  --project-name ppo-model \
  --trainer ppo \
  --rl-reward-model-path ./reward-model

from transformers import AutoModelForSequenceClassification, AutoTokenizer
import torch

# 加载奖励模型
model = AutoModelForSequenceClassification.from_pretrained("./reward-model")
tokenizer = AutoTokenizer.from_pretrained("./reward-model")

# 评分响应
text = "What is AI? AI is artificial intelligence, a field of computer science..."
inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512)

with torch.no_grad():
    outputs = model(**inputs)
    score = outputs.logits.item()

print(f"Reward score: {score}")

# 创建偏好数据的示例脚本
import json

preferences = [
    {
        "prompt": "Summarize machine learning",
        "chosen": "Machine learning is a subset of AI that enables systems to learn from data...",
        "rejected": "ml is computers learning stuff"
    },
    # 添加更多示例...
]

with open("preferences.jsonl", "w") as f:
    for item in preferences:
        f.write(json.dumps(item) + "\n")