---
license: cc-by-nc-4.0
base_model: Qwen/Qwen2-7B-Instruct
model-index:
- name: Dolphin 
  results: []
tags:
- RAG
- on-device language model
- Retrieval Augmented Generation
inference: false
space: false
spaces: false
language:
- en
---
# Dolphin: Long Context as a New Modality for on-device RAG

<p align="center">
- <a href="https://www.nexaai.com/models" target="_blank">Nexa Model Hub</a>
- <a href="https://arxiv.org/abs/2404.01744" target="_blank">ArXiv</a>
</p>

<p align="center" width="100%">
  <a><img src="logo.png" alt="nexa-octopus" style="width: 30%; min-width: 300px; display: block; margin: auto;"></a>
</p>

## Overview
Dolphin is a novel approach to accelerate language model inference by treating long context as a new modality, similar to image, audio, and video modalities in vision-language models. This innovative method incorporates a language encoder model to encode context information into embeddings, applying multimodal model concepts to enhance the efficiency of language model inference。 Below are model highlights:
- 🧠 Context as a distinct modality
- 🗜️ Language encoder for context compression
- 🔗 Multimodal techniques applied to language processing
- ⚡ Optimized for energy efficiency and on-device use
- 📜 Specialized for long context understanding

## Model Architecture
Dolphin employs a decoder-decoder framework with two main components:
1. A smaller decoder (0.5B parameters) for transforming information from extensive contexts
2. A larger decoder (7B parameters) for comprehending and generating responses to current queries
3. The architecture also includes a projector to align embeddings between the text encoder and the main decoder.

![Model Architecture](modelstructure.jpg)

## Running the Model

```python
from transformers import AutoTokenizer
from configuration_dolphin import DolphinForCausalLM
import time

tokenizer = AutoTokenizer.from_pretrained('nexa-collaboration/dolphin_instruct_1M_0805', trust_remote_code=True)
model = DolphinForCausalLM.from_pretrained('nexa-collaboration/dolphin_instruct_1M_0805', trust_remote_code=True)

def inference(input_text):
    inputs = tokenizer(input_text, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=100)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

input_text = "Take a selfie for me with front camera"
nexa_query = f"Below is the query from the users, please call the correct function and generate the parameters to call the function.\n\nQuery: {input_text} \n\nResponse:"

start_time = time.time()
result = inference(nexa_query)
print("Dolphin model result:\n", result)
print("Latency:", time.time() - start_time, "s")
```

## Training Process
Dolphin's training involves three stages:
1. Restoration Training: Reconstructing original context from compressed embeddings
2. Continual Training: Generating context continuations from partial compressed contexts
3. Instruction Fine-tuning: Generating responses to queries given compressed contexts

This multi-stage approach progressively enhances the model's ability to handle long contexts and generate appropriate responses.

## Citation
If you use Dolphin in your research, please cite our paper:

```bibtex
@article{dolphin2024,
  title={Dolphin: Long Context as a New Modality for Energy-Efficient On-Device Language Models},
  author={[Author Names]},
  journal={arXiv preprint arXiv:[paper_id]},
  year={2024}
}
```

## Contact
For questions or feedback, please [contact us](octopus@nexa4ai.com)