self rewarding lm pytorch下載 - self rewarding lm pytorch原始碼下載

自我獎勵語言模型

MetaAI 的自我獎勵語言模型中提出的培訓框架的實現

他們確實把 DPO 論文的標題牢記在心。

該庫還包含 SPIN 的實現，Nous Research 的 Teknium 對此表示樂觀。

欣賞

A16Z 開源人工智慧資助計畫和？感謝慷慨的贊助，以及我的其他贊助商，為我提供了開源當前人工智慧研究的獨立性

安裝

$ pip install self-rewarding-lm-pytorch

用法

 import torch
from torch import Tensor

from self_rewarding_lm_pytorch import (
    SelfRewardingTrainer ,
    create_mock_dataset
)

from x_transformers import TransformerWrapper , Decoder

transformer = TransformerWrapper (
    num_tokens = 256 ,
    max_seq_len = 1024 ,
    attn_layers = Decoder (
        dim = 512 ,
        depth = 1 ,
        heads = 8
    )
)

sft_dataset = create_mock_dataset ( 100 , lambda : ( torch . randint ( 0 , 256 , ( 256 ,)), torch . tensor ( 1 )))
prompt_dataset = create_mock_dataset ( 100 , lambda : 'mock prompt' )

def decode_tokens ( tokens : Tensor ) -> str :
    decode_token = lambda token : str ( chr ( max ( 32 , token )))
    return '' . join ( list ( map ( decode_token , tokens )))

def encode_str ( seq_str : str ) -> Tensor :
    return Tensor ( list ( map ( ord , seq_str )))

trainer = SelfRewardingTrainer (
    transformer ,
    finetune_configs = dict (
        train_sft_dataset = sft_dataset ,
        self_reward_prompt_dataset = prompt_dataset ,
        dpo_num_train_steps = 1000
    ),
    tokenizer_decode = decode_tokens ,
    tokenizer_encode = encode_str ,
    accelerate_kwargs = dict (
        cpu = True
    )
)

trainer ( overwrite_checkpoints = True )

# checkpoints after each finetuning stage will be saved to ./checkpoints

SPIN 可以如下進行訓練 - 也可以將其添加到微調管道中，如自述文件中的最後一個範例所示。

 import torch

from self_rewarding_lm_pytorch import (
    SPINTrainer ,
    create_mock_dataset
)

from x_transformers import TransformerWrapper , Decoder

transformer = TransformerWrapper (
    num_tokens = 256 ,
    max_seq_len = 1024 ,
    attn_layers = Decoder (
        dim = 512 ,
        depth = 6 ,
        heads = 8
    )
)

sft_dataset = create_mock_dataset ( 100 , lambda : ( torch . randint ( 0 , 256 , ( 256 ,)), torch . tensor ( 1 )))

spin_trainer = SPINTrainer (
    transformer ,
    max_seq_len = 16 ,
    train_sft_dataset = sft_dataset ,
    checkpoint_every = 100 ,
    spin_kwargs = dict (
        λ = 0.1 ,
    ),
)

spin_trainer ()

假設您想嘗試自己的獎勵提示（法學碩士法官除外）。首先，您需要匯入RewardConfig ，然後將其作為reward_prompt_config傳遞到訓練器中

 # first import

from self_rewarding_lm_pytorch import RewardConfig

# then say you want to try asking the transformer nicely

# reward_regex_template is the string that will be looked for in the LLM response, for parsing out the reward where {{ reward }} is defined as a number

trainer = SelfRewardingTrainer (
    transformer ,
    ...,
    self_reward_prompt_config = RewardConfig (
        prompt_template = """
        Pretty please rate the following user prompt and response
        User: {{ prompt }}
        Response: {{ response }}

        Format your score as follows:
        Rating: <rating as integer from 0 - 10>
        """ ,
        reward_regex_template = """
        Rating: {{ reward }}
        """
    )
)

最後，如果您想嘗試任意順序的微調，您也可以透過將FinetuneConfig實例作為列表傳遞到finetune_configs來獲得這種靈活性

前任。假設你想對交錯 SPIN、外在獎勵和自我獎勵進行研究

這個想法源自於 Teknium 的一個私人不和諧頻道。

 # import the configs

from self_rewarding_lm_pytorch import (
    SFTConfig ,
    SelfRewardDPOConfig ,
    ExternalRewardDPOConfig ,
    SelfPlayConfig ,
)

trainer = SelfRewardingTrainer (
    model ,
    finetune_configs = [
        SFTConfig (...),
        SelfPlayConfig (...),
        ExternalRewardDPOConfig (...),
        SelfRewardDPOConfig (...),
        SelfPlayConfig (...),
        SelfRewardDPOConfig (...)
    ],
    ...
)

trainer ()

# checkpoints after each finetuning stage will be saved to ./checkpoints

托多

引文

 @misc { yuan2024selfrewarding ,
    title   = { Self-Rewarding Language Models } , 
    author  = { Weizhe Yuan and Richard Yuanzhe Pang and Kyunghyun Cho and Sainbayar Sukhbaatar and Jing Xu and Jason Weston } ,
    year    = { 2024 } ,
    eprint  = { 2401.10020 } ,
    archivePrefix = { arXiv } ,
    primaryClass = { cs.CL }
}

 @article { Chen2024SelfPlayFC ,
    title   = { Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models } ,
    author  = { Zixiang Chen and Yihe Deng and Huizhuo Yuan and Kaixuan Ji and Quanquan Gu } ,
    journal = { ArXiv } ,
    year    = { 2024 } ,
    volume  = { abs/2401.01335 } ,
    url     = { https://api.semanticscholar.org/CorpusID:266725672 }
}

 @article { Rafailov2023DirectPO ,
    title   = { Direct Preference Optimization: Your Language Model is Secretly a Reward Model } ,
    author  = { Rafael Rafailov and Archit Sharma and Eric Mitchell and Stefano Ermon and Christopher D. Manning and Chelsea Finn } ,
    journal = { ArXiv } ,
    year    = { 2023 } ,
    volume  = { abs/2305.18290 } ,
    url     = { https://api.semanticscholar.org/CorpusID:258959321 }
}

 @inproceedings { Guo2024DirectLM ,
    title   = { Direct Language Model Alignment from Online AI Feedback } ,
    author  = { Shangmin Guo and Biao Zhang and Tianlin Liu and Tianqi Liu and Misha Khalman and Felipe Llinares and Alexandre Rame and Thomas Mesnard and Yao Zhao and Bilal Piot and Johan Ferret and Mathieu Blondel } ,
    year    = { 2024 } ,
    url     = { https://api.semanticscholar.org/CorpusID:267522951 }
}