基于DiscoPOP对公共和合成数据集混合进行微调的7B参数GPT-like模型

21 拉取 2个月前更新

2个月前

524c42220d3b · 6.3GB

model
gemma
·
8.54B
·
Q4_K_M
template
<|im_start|>system {{ .System }}<|im_end|> <|im_start|>user {{ .Prompt }}<|im_end|> <|im_start|>assistant
license
Gemma Terms of Use Last modified: February 21, 2024 By using, reproducing, modifying, distributing, performing or displaying any portion or element of Gemma, Model Derivatives including via any Hosted Service, (each as defined below) (collectively, the "Gemma Services") or otherwise accepting the terms of this Agreement, you agree to be bound by this Agreement. Section 1: DEFINITIONS 1.1 Definitions (a) "Agreement" or "Gemma Terms of Use" means these terms and conditions that govern the use, reproduction, Distribution or modification of the Gemma Services and any terms and conditions incorporated by reference. (b) "Distribution" or "Distribute" means any transmission, publication, or other sharing of Gemma or Model Derivatives to a third party, including by providing or making Gemma or its functionality available as a hosted service via API, web access, or any other electronic or remote means ("Hosted Service"). (c) "Gemma" means the set of machine learning language models, trained model weights and parameters identified at ai.google.dev/gemma, regardless of the source that you obtained it from. (d) "Google" means Google LLC. (e) "Model Derivatives" means all (i) modifications to Gemma, (ii) works based on Gemma, or (iii) any other machine learning model which is created by transfer of patterns of the weights, parameters, operations, or Output of Gemma, to that model in order to cause that model to perform similarly to Gemma, including distillation methods that use intermediate data representations or methods based on the generation of synthetic data Outputs by Gemma for training that model. For clarity, Outputs are not deemed Model Derivatives. (f) "Output" means the information content output of Gemma or a Model Derivative that results from operating or otherwise using Gemma or the Model Derivative, including via a Hosted Service. 1.2 As used in this Agreement, "including" means "including without limitation". Section 2: ELIGIBILITY AND USAGE 2.1 Eligibility You represent and warrant that you have the legal capacity to enter into this Agreement (including being of sufficient age of consent). If you are accessing or using any of the Gemma Services for or on behalf of a legal entity, (a) you are entering into this Agreement on behalf of yourself and that legal entity, (b) you represent and warrant that you have the authority to act on behalf of and bind that entity to this Agreement and (c) references to "you" or "your" in the remainder of this Agreement refers to both you (as an individual) and that entity. 2.2 Use You may use, reproduce, modify, Distribute, perform or display any of the Gemma Services only in accordance with the terms of this Agreement, and must not violate (or encourage or permit anyone else to violate) any term of this Agreement. Section 3: DISTRIBUTION AND RESTRICTIONS 3.1 Distribution and Redistribution You may reproduce or Distribute copies of Gemma or Model Derivatives if you meet all of the following conditions: You must include the use restrictions referenced in Section 3.2 as an enforceable provision in any agreement (e.g., license agreement, terms of use, etc.) governing the use and/or distribution of Gemma or Model Derivatives and you must provide notice to subsequent users you Distribute to that Gemma or Model Derivatives are subject to the use restrictions in Section 3.2. You must provide all third party recipients of Gemma or Model Derivatives a copy of this Agreement. You must cause any modified files to carry prominent notices stating that you modified the files. All Distributions (other than through a Hosted Service) must be accompanied by a "Notice" text file that contains the following notice: "Gemma is provided under and subject to the Gemma Terms of Use found at ai.google.dev/gemma/terms". You may add your own intellectual property statement to your modifications and, except as set forth in this Section, may provide additional or different terms and conditions for use, reproduction, or Distribution of your modifications, or for any such Model Derivatives as a whole, provided your use, reproduction, modification, Distribution, performance, and display of Gemma otherwise complies with the terms and conditions of this Agreement. Any additional or different terms and conditions you impose must not conflict with the terms of this Agreement. 3.2 Use Restrictions You must not use any of the Gemma Services: for the restricted uses set forth in the Gemma Prohibited Use Policy at ai.google.dev/gemma/prohibited_use_policy ("Prohibited Use Policy"), which is hereby incorporated by reference into this Agreement; or in violation of applicable laws and regulations. To the maximum extent permitted by law, Google reserves the right to restrict (remotely or otherwise) usage of any of the Gemma Services that Google reasonably believes are in violation of this Agreement. 3.3 Generated Output Google claims no rights in Outputs you generate using Gemma. You and your users are solely responsible for Outputs and their subsequent uses. Section 4: ADDITIONAL PROVISIONS 4.1 Updates Google may update Gemma from time to time, and you must make reasonable efforts to use the latest version of Gemma. 4.2 Trademarks Nothing in this Agreement grants you any rights to use Google's trademarks, trade names, logos or to otherwise suggest endorsement or misrepresent the relationship between you and Google. Google reserves any rights not expressly granted herein. 4.3 DISCLAIMER OF WARRANTY UNLESS REQUIRED BY APPLICABLE LAW, THE GEMMA SERVICES, AND OUTPUTS, ARE PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED, INCLUDING ANY WARRANTIES OR CONDITIONS OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING, REPRODUCING, MODIFYING, PERFORMING, DISPLAYING OR OR DISTRIBUTING ANY OF THE GEMMA SERVICES OR OUTPUTS AND ASSUME ANY AND ALL RISKS ASSOCIATED WITH YOUR USE OR DISTRIBUTION OF ANY OF THE GEMMA SERVICES OR OUTPUTS AND YOUR EXERCISE OF RIGHTS AND PERMISSIONS UNDER THIS AGREEMENT. 4.4 LIMITATION OF LIABILITY TO THE FULLEST EXTENT PERMITTED BY APPLICABLE LAW, IN NO EVENT AND UNDER NO LEGAL THEORY, WHETHER IN TORT (INCLUDING NEGLIGENCE), PRODUCT LIABILITY, CONTRACT, OR OTHERWISE, UNLESS REQUIRED BY APPLICABLE LAW, SHALL GOOGLE OR ITS AFFILIATES BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY DIRECT, INDIRECT, SPECIAL, INCIDENTAL, EXEMPLARY, CONSEQUENTIAL, OR PUNITIVE DAMAGES, OR LOST PROFITS OF ANY KIND ARISING FROM THIS AGREEMENT OR RELATED TO, ANY OF THE GEMMA SERVICES OR OUTPUTS EVEN IF GOOGLE OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. 4.5 Term, Termination, and Survival The term of this Agreement will commence upon your acceptance of this Agreement (including acceptance by your use, modification, or Distribution, reproduction, performance or display of any portion or element of the Gemma Services) and will continue in full force and effect until terminated in accordance with the terms of this Agreement. Google may terminate this Agreement if you are in breach of any term of this Agreement. Upon termination of this Agreement, you must delete and cease use and Distribution of all copies of Gemma and Model Derivatives in your possession or control. Sections 1, 2.1, 3.3, 4.2 to 4.9 shall survive the termination of this Agreement. 4.6 Governing Law and Jurisdiction This Agreement will be governed by the laws of the State of California without regard to choice of law principles. The UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The state and federal courts of Santa Clara County, California shall have exclusive jurisdiction of any dispute arising out of this Agreement. 4.7 Severability If any provision of this Agreement is held to be invalid, illegal or unenforceable, the remaining provisions shall be unaffected thereby and remain valid as if such provision had not been set forth herein. 4.8 Entire Agreement This Agreement states all the terms agreed between the parties and supersedes all other agreements between the parties as of the date of acceptance relating to its subject matter. 4.9 No Waiver Google will not be treated as having waived any rights by not exercising (or delaying the exercise of) any rights under this Agreement.
params
{"penalize_newline":false,"repeat_penalty":1,"stop":["<|im_start|>","<|im_end|>"]}

Readme

Zephyr 7B Gemma Logo

DiscoPOP-zephyr-7b-gemma

此模型是在argilla/dpo-mix-7k数据集上对HuggingFaceH4/zephyr-7b-gemma-sft-v0.1进行微调的版本。

此模型来自论文“Discovering Preference Optimization Algorithms with and for Large Language Models”

在这里阅读关于它的博客文章!

在这里查看生成它的代码库: https://github.com/SakanaAI/DiscoPOP

模型描述

这个模型在训练上与HuggingFaceH4/zephyr-7b-gemma-v0.1相同,但使用的是DiscoPOP替代直接偏好优化(DPO)。

DiscoPOP是我们发现偏好优化的算法,定义如下

def log_ratio_modulated_loss(
    self,
    policy_chosen_logps: torch.FloatTensor,
    policy_rejected_logps: torch.FloatTensor,
    reference_chosen_logps: torch.FloatTensor,
    reference_rejected_logps: torch.FloatTensor,
) -> torch.FloatTensor:
    pi_logratios = policy_chosen_logps - policy_rejected_logps
    ref_logratios = reference_chosen_logps - reference_rejected_logps
    logits = pi_logratios - ref_logratios
    # Modulate the mixing coefficient based on the log ratio magnitudes
    log_ratio_modulation = torch.sigmoid(logits)
    logistic_component = -F.logsigmoid(self.beta * logits)
    exp_component = torch.exp(-self.beta * logits)
    # Blend between logistic and exponential component based on log ratio modulation
    losses = logistic_component * (1 - log_ratio_modulation) + exp_component * log_ratio_modulation
    return losses

训练超参数

以下是在训练期间使用的超参数
- learning_rate: 5e-07
- train_batch_size: 2
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2

框架版本

  • Transformers 4.40.1
  • Pytorch 2.1.2+cu121
  • 数据集 2.19.0
  • 分词器 0.19.1

Zephyr 7B Gemma 的模型卡片

Zephyr 是一系列经过训练,可以作为有帮助的助手的语言模型。Zephyr 7B Gemma 是该系列的第三个模型,是通过对google/gemma-7b进行微调得到的版本,该模型在公开可用和合成数据集的混合上进行训练,并使用了直接偏好优化(DPO)。您可以通过在Alignment Handbook中提供的配方来重现该模型的训练。

模型描述

  • 模型类型: 在公开可用和合成数据集混合上微调的 7B 参数类似的 GPT 模型。
  • 语言(NLP): 主要为英语
  • 许可证: Gemma 使用条款
  • 微调自模型: google/gemma-7b

模型来源

性能

模型 MT Bench⬇️ IFEval
zephyr-7b-gemma-v0.1 7.81 28.76
zephyr-7b-beta 7.34 43.81
google/gemma-7b-it 6.38 38.01
模型 AGIEval GPT4All TruthfulQA BigBench Average ⬇️
zephyr-7b-beta 37.52 71.77 55.26 39.77 51.08
zephyr-7b-gemma-v0.1 34.22 66.37 52.19 37.10 47.47
mlabonne/Gemmalpaca-7B 21.6 40.87 44.85 30.49 34.45
google/gemma-7b-it 21.33 40.84 41.70 30.25 33.53
AGIEval、GPT4All、TruthfulQA、BigBench 的详细情况### AGIEval | Task |Version| Metric |Value| |Stderr| |------------------------------|------:|--------|----:|---|-----:| |agieval_aqua_rat | 0|acc |21.65|± | 2.59| | | |acc_norm|25.20|± | 2.73| |agieval_logiqa_en | 0|acc |34.72|± | 1.87| | | |acc_norm|35.94|± | 1.88| |agieval_lsat_ar | 0|acc |19.57|± | 2.62| | | |acc_norm|21.74|± | 2.73| |agival_lsat_lr | 0|acc |30.59|± | 2.04| | | |acc_norm|32.55|± | 2.08| |agival_lsat_rc | 0|acc |49.07|± | 3.05| | | |acc_norm|42.75|± | 3.02| |agival_sat_en | 0|acc |54.85|± | 3.48| | | |acc_norm|53.40|± | 3.48| |agival_sat_en_without_passage| 0|acc |37.38|± | 3.38| | | |acc_norm|33.98|± | 3.31| |agival_sat_math | 0|acc |30.91|± | 3.12| | | |acc_norm|28.18|± | 3.04| 平均值:34.22% ### GPT4All | Task |Version| Metric |Value| |Stderr| |-------------|------:|------|----:|---|-----:| |arc_challenge| 0|acc |49.15|± | 1.46| | | |acc_norm|52.47|± | 1.46| |arc_easy | 0|acc |77.44|± | 0.86| | | |acc_norm|74.75|± | 0.89| |boolq | 1|acc |79.69|± | 0.70| | | |acc_norm|78.00|± | 0.41| |hellaswag | 0|acc |60.59|± | 0.49| | | |acc_norm|78.00|± | 0.41| |openbookqa | 0|acc |29.20|± | 2.04| | | |acc_norm|37.80|± | 2.17| |piqa | 0|acc |76.82|± | 0.98| | | |acc_norm|77.80|± | 0.97| |winogrande | 0|acc |64.09|± | 1.35| | | |acc_norm|64.09|± | 1.35| 平均值:66.37% ### TruthfulQA | Task |Version|Metric|Value| |Stderr| |-------------|------:|------|----:|---|-----:| |truthfulqa_mc| 1|mc1 |35.74|± | 1.68| | | |mc2 |52.19|± | 1.59| 平均值:52.19% ### Bigbench | Task |Version| Metric |Value| |Stderr| |------------------------------------------------|------:|---------------------|----:|---|-----:| |bigbench_causal_judgement | 0|multiple_choice_grade|53.68|± | 3.63| |bigbench_date_understanding | 0|multiple_choice_grade|59.89|± | 2.55| |bigbench_disambiguation_qa | 0|multiple_choice_grade|30.23|± | 2.86| |bigbench_geometric_shapes | 0|multiple_choice_grade|11.42|± | 1.68| | | |exact_str_match | 0.00|± | 0.00| |bigbench_logic_deduction_five_objects | 0|multiple_choice_grade|28.40|± | 2.02| |bigbench_logic_deduction_seven_objects | 0|multiple_choice_grade|19.14|± | 1.49| |bigbench_logic_deduction_three_objects | 0|multiple_choice_grade|44.67|± | 2.88| |bigbench_movie_recommendation | 0|multiple_choice_grade|26.80|± | 1.98| |bigbench_navigate | 0|multiple_choice_grade|50.00|± | 1.58| |bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|52.75|± | 1.12| |bigbench_ruins_names | 0|multiple_choice_grade|33.04|± | 2.22| |bigbench_salient_translation_error_detection | 0|multiple_choice_grade|33.37|± | 1.49| |bigbench_snarks | 0|multiple_choice_grade|48.62|± | 3.73| |bigbench_sports_understanding | 0|multiple_choice_grade|58.11|± | 1.57| |bigbench_temporal_sequences | 0|multiple_choice_grade|37.20|± | 1.53| |bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|20.08|± | 1.13| |bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|15.77|± | 0.87| |bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|44.67|± | 2.88| 平均值:37.1%

预期用途及限制

该模型最初在包含ChatGPT生成的多种合成对话的DEITA 10K数据集上进行了微调。
然后我们进一步使用🤗 TRL的 DPOTrainerargilla/dpo-mix-7k数据集上对模型进行了对齐,该数据集包含7k个提示和模型完成,这些完成由GPT-4进行排序。因此,该模型可用于聊天,您可以查看我们的演示以测试其功能。

以下是使用🤗 Transformers中的pipeline()函数运行该模型的方法:

# pip install transformers>=4.38.2
# pip install accelerate

import torch
from transformers import pipeline

pipe = pipeline(
    "text-generation",
    model="HuggingFaceH4/zephyr-7b-gemma-v0.1",
    device_map="auto",
    torch_dtype=torch.bfloat16,
)
messages = [
    {
        "role": "system",
        "content": "",  # Model not yet trained for follow this
    },
    {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
]
outputs = pipe(
    messages,
    max_new_tokens=128,
    do_sample=True,
    temperature=0.7,
    top_k=50,
    top_p=0.95,
    stop_sequence="<|im_end|>",
)
print(outputs[0]["generated_text"][-1]["content"])
# It is not possible for a human to eat a helicopter in one sitting, as a
# helicopter is a large and inedible machine. Helicopters are made of metal,
# plastic, and other materials that are not meant to be consumed by humans.
# Eating a helicopter would be extremely dangerous and would likely cause
# serious health problems, including choking, suffocation, and poisoning. It is
# important to only eat food that is safe and intended for human consumption.

偏见、风险和局限性

Zephyr 7B Gemma在RLHF阶段尚未与人类偏好对齐以确保安全性,也没有像ChatGPT那样部署具有在线过滤响应的功能,因此该模型可能会生成问题输出(尤其是在被提示生成时)。此外,还不知道用于训练基础模型(《google/gemma-7b》)的语料库的大小和组成,但它很可能包括Web数据以及书籍和代码等技术来源的混合。参见StarCoder2模型信息以获取示例。

培训与评估数据

此模型是在argilla/dpo-mix-7k数据集上对HuggingFaceH4/zephyr-7b-gemma-sft-v0.1进行微调的版本。

它在评估集中实现了以下结果:
- 损失:0.4695
- 奖励/选择:-3.3746
- 奖励/拒绝:-4.9715
- 奖励/准确度:0.7188
- 奖励/边际:1.5970
- 对数似然/拒绝:-459.4853
- 对数似然/选择:-429.9115
- 原始对数/拒绝:86.4684
- 原始对数/选择:92.8200

训练超参数

以下是在训练期间使用的超参数
- learning_rate: 5e-07
- train_batch_size: 2
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2

培训结果

培训损失 时代 步数 验证损失 奖励/选择 奖励/拒绝 奖励/准确度 奖励/边际 对数似然/拒绝 对数似然/选择 原始对数/拒绝 原始对数/选择
0.1923 1.9 100 0.4736 -3.4575 -4.9556 0.75 1.4980 -459.1662 -431.5707 86.3863 92.7360

框架版本

  • Transformers 4.39.0.dev0
  • Pytorch 2.1.2+cu121
  • 数据集 2.14.6
  • 分词器 0.15.1

引用信息

如果您在您的工作中发现此模型有用,请考虑引用Zephyr技术报告

@misc{tunstall2023zephyr,
      title={Zephyr: Direct Distillation of LM Alignment}, 
      author={Lewis Tunstall and Edward Beeching and Nathan Lambert and Nazneen Rajani and Kashif Rasul and Younes Belkada and Shengyi Huang and Leandro von Werra and Clémentine Fourrier and Nathan Habib and Nathan Sarrazin and Omar Sanseviero and Alexander M. Rush and Thomas Wolf},
      year={2023},
      eprint={2310.16944},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

您还希望引用该模型的创建者

@misc{zephyr_7b_gemma,
  author = {Lewis Tunstall and Philipp Schmid},
  title = {Zephyr 7B Gemma},
  year = {2024},
  publisher = {Hugging Face},
  journal = {Hugging Face repository},
  howpublished = {\url{https://hugging-face.cn/HuggingFaceH4/zephyr-7b-gemma-v0.1}}
}

开放LLM排行榜评估结果

详细结果可在此处找到

指标 数值
Avg. 62.41
AI2推理挑战(25-Shot) 58.45
HellaSwag(10-Shot) 83.48
MMLU(5-Shot) 60.68
TruthfulQA(0-shot) 52.07
Winogrande(5-shot) 74.19
GSM8k(5-shot) 45.56