Hugging Face's logo

nvidia
/
Llama-3.1-Nemotron-70B-Reward

NeMo
English
nvidia
llama3.1
reward model
Model card Files Community
3
Llama-3.1-Nemotron-70B-Reward / README.md
zhilinw's picture
zhilinw
Update README.md
7d174e2 verified
preview code
|
raw
history blame
10.4 kB
metadata
license: llama3.1
library_name: nemo
language:
  - en
inference: false
fine-tuning: false
tags:
  - nvidia
  - llama3.1
  - reward model
datasets:
  - nvidia/HelpSteer2

Model Overview

Description:

Llama-3.1-Nemotron-70B-Reward is a large language model customized using developed by NVIDIA to predict the quality of LLM generated responses.

Terms of use

By accessing this model, you are agreeing to the LLama 3.1 terms and conditions of the license, acceptable use policy and Meta’s privacy policy

RewardBench Primary Dataset LeaderBoard

Llama-3.1-Nemotron-70B-Reward performs best Overall on RewardBench as well as in Chat, Safety and Reasoning category.

Model Type of Data Used For Training Overall Chat Chat-Hard Safety Reasoning
Llama-3.1-Nemotron-70B-Reward Permissive Licensed Data Only (CC-BY-4.0) 94.1 97.5 85.8 95.1 98.1
Skywork-Reward-Gemma-2-27B Includes GPT4 Generated Data 93.8 95.8 91.4 91.9 96.1
TextEval-Llama3.1-70B Not disclosed 93.5 94.1 90.1 93.2 96.4
Skywork-Critic-Llama-3.1-70B Not fully disclosed 93.3 96.6 87.9 93.1 95.5
SFR-LLaMa-3.1-70B-Judge-r Not fully disclosed 92.7 96.9 84.8 91.6 97.6
Nemotron-4-340B-Reward Permissive Licensed Data Only (CC-BY-4.0) 92.0 95.8 87.1 91.5 93.7
ArmoRM-Llama3-8B-v0.1 Includes GPT4 Generated Data 90.8 96.9 76.8 92.2 97.3
Cohere May 2024 Not disclosed 89.5 96.4 71.3 92.7 97.7
Llama3-70B-SteerLM-RM Permissive Licensed Data Only (CC-BY-4.0) 88.8 91.3 80.3 92.8 90.7
Google Gemini Pro 1.5 Not disclosed 88.1 92.3 80.6 87.5 92.0
GPT-4o-2024-08-06 Not disclosed 86.7 96.1 76.1 88.1 86.6
claude-3-5-sonnet-20240620 Not disclosed 84.2 96.4 74.0 81.6 84.7
Meta-Llama-3.1-70B-Instruct Not fully disclosed 84.0 97.2 70.2 82.8 86.0

To better understand why it struggles in the Chat-Hard category, we analyzed the scores for each consistutent subset of Chat-Hard category. We find that on categories that uses human annotations as ground truth, Llama-3.1-Nemotron-70B-Reward performs similar to Skywork-Reward-Gemma-2-27B (<= 2.2% difference.) On the other hand, when GPT-4 annotations are used as Ground-Truth, we trail substantially behind Skywork-Reward-Gemma-2-27B by 10.8 to 19.2%. This suggests that Skywork-Reward-Gemma-2-27B might better suited at modelling GPT-4 preference, likely contributed by the inclusion of GPT-4 annotated training data used to train it found in the OffSetBias dataset as part of the Skywork-Reward-Preference-80k.

Model Type of Data Used For Training Chat-Hard LLMBar-Adversarial-Manual LLMBar-Adversarial-Neighbour LLMBar-Natural LLMBar-Adversarial-GPTInst LLMBar-Adversarial-GPTOut MT-Bench-Hard
Human as Ground Truth Human as Ground Truth Human as Ground Truth GPT-4 as Ground Truth GPT-4 as Ground Truth GPT-4 as Ground Truth
Llama-3.1-Nemotron-70B-Reward Permissive Licensed Data Only (CC-BY-4.0) 85.8 76.1 88.8 95.0 87.0 72.3 75.7
Skywork-Reward-Gemma-2-27B Includes GPT4 Generated Data 91.4 78.3 89.6 96.0 97.8 91.5 86.5

Last updated: 27 Sept 2024

Usage:

You can use the model with NeMo Aligner following SteerLM training user guide.

  1. Spin up an inference server within the NeMo container (docker pull nvcr.io/nvidia/nemo.24.05.llama3.1)
HF_HOME=<YOUR_HF_HOME_CONTAINING_TOKEN_WITH_LLAMA31_70B_ACCESS> \
python /opt/NeMo-Aligner/examples/nlp/gpt/serve_reward_model.py \
      rm_model_file=Llama-3.1-Nemotron-70B-Reward \
      trainer.num_nodes=1 \
      trainer.devices=8 \
      ++model.tensor_model_parallel_size=8 \
      ++model.pipeline_model_parallel_size=1 \
      inference.micro_batch_size=2 \
      inference.port=1424
  1. Annotate data files using the served reward model. As an example, this can be the Open Assistant train/val files. Then follow the next step to train a SteerLM model based on SteerLM training user guide .

Please note that this script rounds the predicted floats to the nearest int (between 0 and 4 inclusive), as it's meant for SteerLM training. For other use cases (e.g. reward bench measurement, response filtering/ranking), we recommend using the floats directly, which can be done by commenting out two lines of code in NeMo-Aligner

python /opt/NeMo-Aligner/examples/nlp/data/steerlm/preprocess_openassistant_data.py --output_directory=data/oasst
python /opt/NeMo-Aligner/examples/nlp/data/steerlm/attribute_annotate.py \
      --input-file=data/oasst/train.jsonl \
      --output-file=data/oasst/train_labeled.jsonl \
      --port=1424
  1. Alternatively, this can be any conversational data file (in .jsonl) in the following format, where each line looks like
{
    "conversations": [
              {"value": <user_turn_1>, "from": "User", "label": None},
              {"value": <assistant_turn_1>, "from": "Assistant", "label": <formatted_label_1>},
              {"value": <user_turn_2>, "from": "User", "label": None},
              {"value": <assistant_turn_2>, "from": "Assistant", "label": <formatted_label_2>},
          ],
    "mask": "User"
}

Ideally, each <formatted_label_n> refers to the ground truth label for the assistant turn but if they are not available, we can also use helpfulness:-1. It must not be None or an empty string.

Contact

E-Mail: Zhilin Wang

Citation

If you find this model useful, please cite the following works

@misc{wang2024helpsteer2,
      title={HelpSteer2: Open-source dataset for training top-performing reward models}, 
      author={Zhilin Wang and Yi Dong and Olivier Delalleau and Jiaqi Zeng and Gerald Shen and Daniel Egert and Jimmy J. Zhang and Makesh Narsimhan Sreedhar and Oleksii Kuchaiev},
      year={2024},
      eprint={2406.08673},
      archivePrefix={arXiv},
      primaryClass={id='cs.CL' full_name='Computation and Language' is_active=True alt_name='cmp-lg' in_archive='cs' is_general=False description='Covers natural language processing. Roughly includes material in ACM Subject Class I.2.7. Note that work on artificial languages (programming languages, logics, formal systems) that does not explicitly address natural-language issues broadly construed (natural-language processing, computational linguistics, speech, text retrieval, etc.) is not appropriate for this area.'}
}

References(s):

Model Architecture:

Architecture Type: Transformer
Network Architecture: Llama 3.1

Input:

Input Type(s): Text
Input Format: String
Input Parameters: NA
Other Properties Related to Input: Provided text must be within 4096 tokens

Output:

Output Type(s): Float
Output Format: One Single Float
Output Parameters: NA
Other Properties Related to Output: NA

Software Integration:

Supported Hardware Microarchitecture Compatibility:

  • NVIDIA Ampere
  • NVIDIA Hopper
  • NVIDIA Turing
    Supported Operating System(s): Linux

Model Version:

v1.0

Training & Evaluation:

Datasets:

Data Collection Method by dataset

  • [Hybrid: Human, Synthetic]

Labeling Method by dataset

  • [Human]

Link:

Properties (Quantity, Dataset Descriptions, Sensor(s)):

  • 37,120 prompt-responses built to make more models more aligned with human preference - specifically more helpful, factually-correct, coherent, and customizable based on complexity and verbosity.

Inference:

Engine: Triton
Test Hardware: H100, A100 80GB, A100 40GB

Ethical Considerations:

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their supporting model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. For more detailed information on ethical considerations for this model, please see the Model Card++ Explainability, Bias, Safety & Security, and Privacy Subcards. Please report security vulnerabilities or NVIDIA AI Concerns here.

Please report security vulnerabilities or NVIDIA AI Concerns here.