Instructions to use rp-yu/Dimple-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rp-yu/Dimple-7B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="rp-yu/Dimple-7B", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("rp-yu/Dimple-7B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rp-yu/Dimple-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rp-yu/Dimple-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rp-yu/Dimple-7B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/rp-yu/Dimple-7B

SGLang

How to use rp-yu/Dimple-7B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "rp-yu/Dimple-7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rp-yu/Dimple-7B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "rp-yu/Dimple-7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rp-yu/Dimple-7B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use rp-yu/Dimple-7B with Docker Model Runner:
```
docker model run hf.co/rp-yu/Dimple-7B
```

Update paper link in model card

by nielsr HF Staff - opened May 25, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+25

-24

Files changed (1) hide show

README.md +25 -24

README.md CHANGED Viewed

@@ -1,26 +1,27 @@
 ---
-library_name: transformers
-tags:
-- Diffusion_Multimodal_Large_Language_Model
-- MLLM
-- Discrete_Diffusion
-license: apache-2.0
 datasets:
 - liuhaotian/LLaVA-CC3M-Pretrain-595K
 - lmms-lab/LLaVA-NeXT-Data
 language:
 - en
 metrics:
 - accuracy
-base_model:
-- Dream-org/Dream-v0-Instruct-7B
 pipeline_tag: image-text-to-text
 ---
 <img src="https://cdn-uploads.huggingface.co/production/uploads/635364b3c41f548fe39db945/T6ffjtAkFkI76QjXmN6iR.png" alt="Dimple" style="width:100%;"/>
 <p align="center">
-🤗 <a href="https://huggingface.co/rp-yu/Dimple-7B">Model</a>&nbsp&nbsp | &nbsp&nbsp 💬 <a href="https://huggingface.co/spaces/rp-yu/Dimple-7B">Demo: Chat with Dimple</a>&nbsp&nbsp | &nbsp&nbsp📑 <a href="https://arxiv.org/abs/">Paper</a>&nbsp&nbsp | &nbsp&nbsp ✨ <a href="https://github.com/yu-rp/Dimple">Code</a>&nbsp&nbsp
 </p>
 # 💧 Dimple-7B
@@ -50,20 +51,20 @@ Trained on the same dataset as LLaVA-NEXT, **Dimple-7B surpasses LLaVA-NEXT-7B b
 | **Training Samples**  | 1.3M             | 1.2M         | 1.3M          | 2.4M     | 27.8M     | 1.5B       | -             |
 | **Training Tokens**   | 0.8B             | -            | -             | -        | -         | -          | 2.6T          |
 | **Base LLM**          | Dream (Qwen2.5)  | Vicuna       | Vicuna-1.5    | Vicuna   | Qwen2.5   | Qwen       | Qwen2.5       |
-| **GQA**               | 59.2             | 62.0         | 64.8          | 64.9 | -         | 59.3       | -             |
-| **MMBench (en test)** | 74.6         | 64.3         | 68.7          | 68.4     | -         | -          | 83.5      |
-| **MME (Perception)**  | 1514             | 1510         | 1519          | 1528 | -         | -          | -             |
-| **MME (Cognition)**   | 432          | -            | 332           | -        | -         | -          | -             |
-| **MME (Total)**       | 1946         | -            | 1851          | -        | -         | -          | 2347      |
-| **POPE**              | 86.2             | 85.8         | 86.7          | 88.8 | -         | -          | -             |
-| **MMMU (val)**        | 45.2         | -            | 35.8          | 36.3     | 56.1      | -          | 58.6      |
-| **SQA (img)**         | 77.1         | 66.8         | 72.8          | 70.0     | -         | -          | -             |
-| **AI2D**              | 74.4         | -            | 65.4          | -        | 83.9  | 62.3       | 83.9      |
-| **ChartQA**           | 63.4             | -            | 54.9          | 67.7 | 86.4  | 65.7       | 87.3      |
-| **TextVQA**           | 61.6             | -            | 64.8      | -        | 83.0  | -          | -             |
-| **OCRBench**          | 565          | -            | 490           | 529      | -         | -          | -             |
-| **MathVista (mini)**  | 42.3         | -            | 33.0          | -        | 63.8  | 37.0       | 68.2      |
-| **MMVet**             | 41.2             | 31.1         | 47.3      | -        | 62.2  | -          | 67.1      |
 ---
@@ -153,4 +154,4 @@ for j in range(len(messages)):
 ## 📚 Citation
 > Citation information will be provided soon.
-> Please stay tuned if you are interested in citing **Dimple** in your work.

 ---
+base_model:
+- Dream-org/Dream-v0-Instruct-7B
 datasets:
 - liuhaotian/LLaVA-CC3M-Pretrain-595K
 - lmms-lab/LLaVA-NeXT-Data
 language:
 - en
+library_name: transformers
+license: apache-2.0
 metrics:
 - accuracy
 pipeline_tag: image-text-to-text
+tags:
+- Diffusion_Multimodal_Large_Language_Model
+- MLLM
+- Discrete_Diffusion
 ---
 <img src="https://cdn-uploads.huggingface.co/production/uploads/635364b3c41f548fe39db945/T6ffjtAkFkI76QjXmN6iR.png" alt="Dimple" style="width:100%;"/>
 <p align="center">
+🤗 <a href="https://huggingface.co/rp-yu/Dimple-7B">Model</a>&nbsp&nbsp | &nbsp&nbsp 💬 <a href="https://huggingface.co/spaces/rp-yu/Dimple-7B">Demo: Chat with Dimple</a>&nbsp&nbsp | &nbsp&nbsp📑 <a href="https://huggingface.co/papers/2505.16990">Paper</a>&nbsp&nbsp | &nbsp&nbsp ✨ <a href="https://github.com/yu-rp/Dimple">Code</a>&nbsp&nbsp
 </p>
 # 💧 Dimple-7B
 | **Training Samples**  | 1.3M             | 1.2M         | 1.3M          | 2.4M     | 27.8M     | 1.5B       | -             |
 | **Training Tokens**   | 0.8B             | -            | -             | -        | -         | -          | 2.6T          |
 | **Base LLM**          | Dream (Qwen2.5)  | Vicuna       | Vicuna-1.5    | Vicuna   | Qwen2.5   | Qwen       | Qwen2.5       |
+| **GQA**               | 59.2             | 62.0         | 64.8          | 64.9     | -         | 59.3       | -             |
+| **MMBench (en test)** | 74.6             | 64.3         | 68.7          | 68.4     | -         | -          | 83.5           |
+| **MME (Perception)**  | 1514             | 1510         | 1519          | 1528     | -         | -          | -             |
+| **MME (Cognition)**   | 432              | -            | 332           | -        | -         | -          | -             |
+| **MME (Total)**       | 1946             | -            | 1851          | -        | -         | -          | 2347           |
+| **POPE**              | 86.2             | 85.8         | 86.7          | 88.8     | -         | -          | -             |
+| **MMMU (val)**        | 45.2             | -            | 35.8          | 36.3     | 56.1      | -          | 58.6           |
+| **SQA (img)**         | 77.1             | 66.8         | 72.8          | 70.0     | -         | -          | -             |
+| **AI2D**              | 74.4             | -            | 65.4          | -        | 83.9      | 62.3       | 83.9           |
+| **ChartQA**           | 63.4             | -            | 54.9          | 67.7     | 86.4      | 65.7       | 87.3           |
+| **TextVQA**           | 61.6             | -            | 64.8          | -        | 83.0      | -          | -             |
+| **OCRBench**          | 565              | -            | 490           | 529      | -         | -          | -             |
+| **MathVista (mini)**  | 42.3             | -            | 33.0          | -        | 63.8      | 37.0       | 68.2           |
+| **MMVet**             | 41.2             | 31.1         | 47.3          | -        | 62.2      | -          | 67.1           |
 ---
 ## 📚 Citation
 > Citation information will be provided soon.
+> Please stay tuned if you are interested in citing **Dimple** in your work.