---
inference: false
pipeline_tag: image-text-to-text
datasets:
- yifanzhang114/SMR
---

<br>
<br>

<img src="https://cdn-uploads.huggingface.co/production/uploads/623d8ca4c29adf5ef6175615/F2d0zMtwUqPKtOrbMu0Gr.jpeg" alt="image/jpeg" style="width:10%;">

# SliME Model Card

## Model details

**Model type:**
SliME is an open-source chatbot trained by fine-tuning LLM on multimodal instruction-following data.
It is an auto-regressive language model, based on the transformer architecture.
Base LLM: [lmsys/vicuna-7b-v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5)

![image/png](https://cdn-uploads.huggingface.co/production/uploads/623d8ca4c29adf5ef6175615/_dsyhwdanIgUPtejamXmX.png)

**Paper or resources for more information:**

Paper: https://huggingface.co/papers/2406.08487

Arxiv: https://arxiv.org/abs/2406.08487

Code: https://github.com/yfzhang114/SliME

## License
Llama 2 is licensed under the LLAMA 2 Community License, 
Copyright (c) Meta Platforms, Inc. All Rights Reserved.

**Where to send questions or comments about the model:**
https://github.com/yfzhang114/SliME/issues

## Intended use
**Primary intended uses:**
The primary use of SliME is research on large multimodal models and chatbots.

**Primary intended users:**
The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.

## Training dataset
- SharedGPT4v sft data
- SMR data

## Evaluation dataset
A collection of 15 benchmarks, including 5 academic VQA benchmarks and 10 recent benchmarks specifically proposed for instruction-following LMMs.


![image/png](https://cdn-uploads.huggingface.co/production/uploads/623d8ca4c29adf5ef6175615/dLXygEd23t-xImhSBLlta.png)