Instructions to use yali30/findingdory-qwen2.5-VL-3B-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yali30/findingdory-qwen2.5-VL-3B-finetuned with Transformers:

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

pipe = pipeline("image-text-to-text", model="yali30/findingdory-qwen2.5-VL-3B-finetuned")
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 AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("yali30/findingdory-qwen2.5-VL-3B-finetuned")
model = AutoModelForMultimodalLM.from_pretrained("yali30/findingdory-qwen2.5-VL-3B-finetuned", device_map="auto")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yali30/findingdory-qwen2.5-VL-3B-finetuned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yali30/findingdory-qwen2.5-VL-3B-finetuned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yali30/findingdory-qwen2.5-VL-3B-finetuned",
		"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/yali30/findingdory-qwen2.5-VL-3B-finetuned

SGLang

How to use yali30/findingdory-qwen2.5-VL-3B-finetuned 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 "yali30/findingdory-qwen2.5-VL-3B-finetuned" \
    --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": "yali30/findingdory-qwen2.5-VL-3B-finetuned",
		"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 "yali30/findingdory-qwen2.5-VL-3B-finetuned" \
        --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": "yali30/findingdory-qwen2.5-VL-3B-finetuned",
		"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 yali30/findingdory-qwen2.5-VL-3B-finetuned with Docker Model Runner:
```
docker model run hf.co/yali30/findingdory-qwen2.5-VL-3B-finetuned
```

Update README.md

by ykarmesh - opened Jul 6, 2025

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+12

-6

Files changed (1) hide show

README.md +12 -6

README.md CHANGED Viewed

@@ -12,15 +12,20 @@ tags:
 - embodied-ai
 - memory
 ---
 <a href="https://arxiv.org/abs/2506.15635" target="_blank">
     <img alt="arXiv" src="https://img.shields.io/badge/arXiv-FindingDory-red?logo=arxiv" height="20" />
 </a>
 <a href="https://findingdory-benchmark.github.io/" target="_blank">
     <img alt="Website" src="https://img.shields.io/badge/🌎_Website-FindingDory-blue.svg" height="20" />
 </a>
-<a href="https://github.com/findingdory-benchmark/findingdory-trl" target="_blank" style="display: inline-block; margin-right: 10px;">
     <img alt="GitHub Code" src="https://img.shields.io/badge/Code-FindingDory--TRL-white?&logo=github&logoColor=white" />
 </a>
 <center><h1>FindingDory: A Benchmark to Evaluate Memory in Embodied Agents</h1>
   <a href="https://www.karmeshyadav.com/">Karmesh Yadav*</a>,
@@ -38,14 +43,14 @@ At deployment the image corresponding to the index is fed into a low-level navig
 🏋️ Training details
 | Property | Value |
 | -------- | ----- |
-| Epochs   | 5 |
 | Effective batch | 32 |
 | LR schedule | Cosine (LR=5e-6, Warmup ratio=0.1)  |
-| Image resol. | TODO |
-| Compute  | “8 × A40 48 GB for ~18 hours” |
-| Input frames | 96 Images |
 | Optimiser | AdamW(β₁ = 0.9, β₂ = 0.95) |
-| Best checkpoint | TODO |
 📊 Evaluation
@@ -57,6 +62,7 @@ We compare the performance of our finetuned `FindingDory-Qwen2.5-VL-3B-SFT` chec
 | Gemma3-12B-it | 13.2% | zero-shot |
 | GPT-4o | 27.3% | zero-shot |
 | Gemini-2.0-Flash | 25.4% | zero-shot |
 Checkout Fig 2 in the paper for more details.
 📄 Citation

 - embodied-ai
 - memory
 ---
+<center>
 <a href="https://arxiv.org/abs/2506.15635" target="_blank">
     <img alt="arXiv" src="https://img.shields.io/badge/arXiv-FindingDory-red?logo=arxiv" height="20" />
 </a>
 <a href="https://findingdory-benchmark.github.io/" target="_blank">
     <img alt="Website" src="https://img.shields.io/badge/🌎_Website-FindingDory-blue.svg" height="20" />
 </a>
+<a href="https://github.com/findingdory-benchmark/findingdory-trl" target="_blank">
     <img alt="GitHub Code" src="https://img.shields.io/badge/Code-FindingDory--TRL-white?&logo=github&logoColor=white" />
 </a>
+<a href="https://huggingface.co/datasets/yali30/findingdory/" target="_blank"">
+    <img alt="Huggingface" src="https://img.shields.io/badge/Dataset-FindingDory-yellow?logo=huggingface" />
+</a>
+</center>
 <center><h1>FindingDory: A Benchmark to Evaluate Memory in Embodied Agents</h1>
   <a href="https://www.karmeshyadav.com/">Karmesh Yadav*</a>,
 🏋️ Training details
 | Property | Value |
 | -------- | ----- |
+| Epochs   | 5 (Total training steps 12840) |
 | Effective batch | 32 |
 | LR schedule | Cosine (LR=5e-6, Warmup ratio=0.1)  |
+| Max Pixels. | 360 x 420 |
+| Compute  | “8 × A40 48 GB for ~84 hours” |
+| Input frames | 96 Images (~10k tokens) |
 | Optimiser | AdamW(β₁ = 0.9, β₂ = 0.95) |
+| Best checkpoint | 8800 Steps |
 📊 Evaluation
 | Gemma3-12B-it | 13.2% | zero-shot |
 | GPT-4o | 27.3% | zero-shot |
 | Gemini-2.0-Flash | 25.4% | zero-shot |
 Checkout Fig 2 in the paper for more details.
 📄 Citation