---
language: en
model-index:
- name: vwxyzjn/rm_zephyr_new
  results:
  - task:
      type: preference_evaluation
    dataset:
      name: reward-bench
      type: allenai/reward-bench
    metrics:
    - type: accuracy
      value: 0.5343383584589615
  - task:
      type: preference_evaluation
    dataset:
      name: Chat
      type: Chat
    metrics:
    - type: accuracy
      value: 0.8128491620111732
  - task:
      type: preference_evaluation
    dataset:
      name: Chat Hard
      type: Chat_Hard
    metrics:
    - type: accuracy
      value: 0.5263157894736842
  - task:
      type: preference_evaluation
    dataset:
      name: Safety
      type: Safety
    metrics:
    - type: accuracy
      value: 0.4851351351351351
  - task:
      type: preference_evaluation
    dataset:
      name: Reasoning
      type: Reasoning
    metrics:
    - type: accuracy
      value: 0.3930266819446718
  - task:
      type: preference_evaluation
    dataset:
      name: alpacaeval-easy
      type: alpacaeval-easy
    metrics:
    - type: accuracy
      value: 0.88
  - task:
      type: preference_evaluation
    dataset:
      name: alpacaeval-hard
      type: alpacaeval-hard
    metrics:
    - type: accuracy
      value: 0.8947368421052632
  - task:
      type: preference_evaluation
    dataset:
      name: alpacaeval-length
      type: alpacaeval-length
    metrics:
    - type: accuracy
      value: 0.6842105263157895
  - task:
      type: preference_evaluation
    dataset:
      name: donotanswer
      type: donotanswer
    metrics:
    - type: accuracy
      value: 0.34558823529411764
  - task:
      type: preference_evaluation
    dataset:
      name: hep-cpp
      type: hep-cpp
    metrics:
    - type: accuracy
      value: 0.6646341463414634
  - task:
      type: preference_evaluation
    dataset:
      name: hep-go
      type: hep-go
    metrics:
    - type: accuracy
      value: 0.6951219512195121
  - task:
      type: preference_evaluation
    dataset:
      name: hep-java
      type: hep-java
    metrics:
    - type: accuracy
      value: 0.6707317073170732
  - task:
      type: preference_evaluation
    dataset:
      name: hep-js
      type: hep-js
    metrics:
    - type: accuracy
      value: 0.676829268292683
  - task:
      type: preference_evaluation
    dataset:
      name: hep-python
      type: hep-python
    metrics:
    - type: accuracy
      value: 0.6829268292682927
  - task:
      type: preference_evaluation
    dataset:
      name: hep-rust
      type: hep-rust
    metrics:
    - type: accuracy
      value: 0.5609756097560976
  - task:
      type: preference_evaluation
    dataset:
      name: llmbar-adver-GPTInst
      type: llmbar-adver-GPTInst
    metrics:
    - type: accuracy
      value: 0.31521739130434784
  - task:
      type: preference_evaluation
    dataset:
      name: llmbar-adver-GPTOut
      type: llmbar-adver-GPTOut
    metrics:
    - type: accuracy
      value: 0.5531914893617021
  - task:
      type: preference_evaluation
    dataset:
      name: llmbar-adver-manual
      type: llmbar-adver-manual
    metrics:
    - type: accuracy
      value: 0.43478260869565216
  - task:
      type: preference_evaluation
    dataset:
      name: llmbar-adver-neighbor
      type: llmbar-adver-neighbor
    metrics:
    - type: accuracy
      value: 0.6044776119402985
  - task:
      type: preference_evaluation
    dataset:
      name: llmbar-natural
      type: llmbar-natural
    metrics:
    - type: accuracy
      value: 0.64
  - task:
      type: preference_evaluation
    dataset:
      name: math-prm
      type: math-prm
    metrics:
    - type: accuracy
      value: 0.12751677852348994
  - task:
      type: preference_evaluation
    dataset:
      name: mt-bench-easy
      type: mt-bench-easy
    metrics:
    - type: accuracy
      value: 0.7857142857142857
  - task:
      type: preference_evaluation
    dataset:
      name: mt-bench-hard
      type: mt-bench-hard
    metrics:
    - type: accuracy
      value: 0.5405405405405406
  - task:
      type: preference_evaluation
    dataset:
      name: mt-bench-med
      type: mt-bench-med
    metrics:
    - type: accuracy
      value: 0.775
  - task:
      type: preference_evaluation
    dataset:
      name: refusals-dangerous
      type: refusals-dangerous
    metrics:
    - type: accuracy
      value: 0.18
  - task:
      type: preference_evaluation
    dataset:
      name: refusals-offensive
      type: refusals-offensive
    metrics:
    - type: accuracy
      value: 0.58
  - task:
      type: preference_evaluation
    dataset:
      name: xstest-should-refuse
      type: xstest-should-refuse
    metrics:
    - type: accuracy
      value: 0.461038961038961
  - task:
      type: preference_evaluation
    dataset:
      name: xstest-should-respond
      type: xstest-should-respond
    metrics:
    - type: accuracy
      value: 0.66
---

# Model Card for vwxyzjn/rm_zephyr_new

<!-- Provide a quick summary of what the model is/does. -->



## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->



- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** en
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]

### Model Sources [optional]

<!-- Provide the basic links for the model. -->

- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]

## Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

### Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

[More Information Needed]

### Downstream Use [optional]

<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->

[More Information Needed]

### Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

[More Information Needed]

## Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

[More Information Needed]

### Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

## How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

## Training Details

### Training Data

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

[More Information Needed]

### Training Procedure

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

#### Preprocessing [optional]

[More Information Needed]


#### Training Hyperparameters

- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->

#### Speeds, Sizes, Times [optional]

<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->

[More Information Needed]

## Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

### Testing Data, Factors & Metrics

#### Testing Data

<!-- This should link to a Dataset Card if possible. -->

[More Information Needed]

#### Factors

<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->

[More Information Needed]

#### Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

[More Information Needed]

### Results

[More Information Needed]

#### Summary



## Model Examination [optional]

<!-- Relevant interpretability work for the model goes here -->

[More Information Needed]

## Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).

- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]

## Technical Specifications [optional]

### Model Architecture and Objective

[More Information Needed]

### Compute Infrastructure

[More Information Needed]

#### Hardware

[More Information Needed]

#### Software

[More Information Needed]

## Citation [optional]

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

**BibTeX:**

[More Information Needed]

**APA:**

[More Information Needed]

## Glossary [optional]

<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->

[More Information Needed]

## More Information [optional]

[More Information Needed]

## Model Card Authors [optional]

[More Information Needed]

## Model Card Contact

[More Information Needed]