README.md

---
license: mit
base_model: HuggingFaceH4/zephyr-7b-gemma-sft
tags:
- alignment-handbook
- trl
- dpo
- generated_from_trainer
datasets:
- argilla/dpo-mix-7k
pipeline_tag: text-generation
model-index:
- name: zephyr-7b-gemma
  results:
  # MT-Bench (taken from model card)
  - task: 
      type: text-generation
      name: Text Generation
    dataset:
      name: MT-Bench
      type: unknown
    metrics:
       - type: unknown
         name: score
         value: 7.81
    source:
      url: https://huggingface.co/spaces/lmsys/mt-bench
---

<img src="https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma/resolve/main/thumbnail.png" alt="Zephyr 7B Gemma Logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>

# Model Card for Zephyr 7B Gemma

Zephyr is a series of language models that are trained to act as helpful assistants. Zephyr 7B Gemma is the third model in the series, and is a fine-tuned version of [`google/gemma-7b`](https://huggingface.co/google/gemma-7b) that was trained on on a mix of publicly available, synthetic datasets using Direct Preference Optimization (DPO). You can reproduce the training of this model via the recipe provided in the [Alignment Handbook](https://github.com/huggingface/alignment-handbook).

## Model description

- **Model type:** A 7B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.
- **Language(s) (NLP):** Primarily English
- **License:** MIT
- **Finetuned from model:** [google/gemma-7b](https://huggingface.co/google/gemma-7b)

### Model Sources

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

- **Repository:** https://github.com/huggingface/alignment-handbook
- **Demo:** https://huggingface.co/spaces/HuggingFaceH4/zephyr-chat

## Performance

|                                 Model                                 |MT Bench|IFEval|
|-----------------------------------------------------------------------|------:|------:|
|[zephyr-7b-gemma](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma)|  7.81 |  28.76|
|[zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta)  |  7.34 |  43.81|
|[gemma-7b-it](https://huggingface.co/google/gemma-7b-it)               |  6.38 |  38.01|


|                                 Model                                 |AGIEval|GPT4All|TruthfulQA|BigBench|Average|
|-----------------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|[zephyr-7b-gemma](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma)|  34.22|  66.37|     52.19|   37.10|  47.47|
|[zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta)  |  37.52|  71.77|     55.26|   39.77|  51.08|
|[gemma-7b-it](https://huggingface.co/google/gemma-7b-it)               |  21.33|  40.84|     41.70|   30.25|  33.53|

## Intended uses & limitations

The model was initially fine-tuned on the [DEITA 10K](https://huggingface.co/datasets/HuggingFaceH4/deita-10k-v0-sft)  dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT. 
We then further aligned the model with [🤗 TRL's](https://github.com/huggingface/trl) `DPOTrainer` on the [argilla/dpo-mix-7k](https://huggingface.co/datasets/argilla/dpo-mix-7k) dataset, which contains 7k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our [demo](https://huggingface.co/spaces/HuggingFaceH4/zephyr-chat) to test its capabilities. 

Here's how you can run the model using the `pipeline()` function from 🤗 Transformers:

```python
# Install transformers from source - only needed for versions <= v4.38.1
# pip install git+https://github.com/huggingface/transformers.git
# pip install accelerate

import torch
from transformers import pipeline

pipe = pipeline(
    "text-generation",
    model="HuggingFaceH4/zephyr-7b-gemma",
    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.
```

## Bias, Risks, and Limitations

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

Zephyr 7B Gemma has not been aligned to human preferences for safety within the RLHF phase or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so). It is also unknown what the size and composition of the corpus was used to train the base model (`google/gemma-7b`), however it is likely to have included a mix of Web data and technical sources like books and code. See the [StarCoder2 model card](https://huggingface.co/bigcode/starcoder2-15b) for an example of this.


## Training and evaluation data


This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-gemma-sft](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-sft) on the argilla/dpo-mix-7k dataset.

It achieves the following results on the evaluation set:
- Loss: 0.4695
- Rewards/chosen: -3.3746
- Rewards/rejected: -4.9715
- Rewards/accuracies: 0.7188
- Rewards/margins: 1.5970
- Logps/rejected: -459.4853
- Logps/chosen: -429.9115
- Logits/rejected: 86.4684
- Logits/chosen: 92.8200

### Training hyperparameters

The following hyperparameters were used during training:
- 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

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.1923        | 1.9   | 100  | 0.4736          | -3.4575        | -4.9556          | 0.75               | 1.4980          | -459.1662      | -431.5707    | 86.3863         | 92.7360       |


### Framework versions

- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.1