Instructions to use Freddie1946/PathVLM-R1-Stage2-Continued-RuleRL1000-seed42 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Freddie1946/PathVLM-R1-Stage2-Continued-RuleRL1000-seed42 with Transformers:

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

pipe = pipeline("image-text-to-text", model="Freddie1946/PathVLM-R1-Stage2-Continued-RuleRL1000-seed42")
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("Freddie1946/PathVLM-R1-Stage2-Continued-RuleRL1000-seed42")
model = AutoModelForMultimodalLM.from_pretrained("Freddie1946/PathVLM-R1-Stage2-Continued-RuleRL1000-seed42", 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 Freddie1946/PathVLM-R1-Stage2-Continued-RuleRL1000-seed42 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Freddie1946/PathVLM-R1-Stage2-Continued-RuleRL1000-seed42"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Freddie1946/PathVLM-R1-Stage2-Continued-RuleRL1000-seed42",
		"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/Freddie1946/PathVLM-R1-Stage2-Continued-RuleRL1000-seed42

SGLang

How to use Freddie1946/PathVLM-R1-Stage2-Continued-RuleRL1000-seed42 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 "Freddie1946/PathVLM-R1-Stage2-Continued-RuleRL1000-seed42" \
    --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": "Freddie1946/PathVLM-R1-Stage2-Continued-RuleRL1000-seed42",
		"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 "Freddie1946/PathVLM-R1-Stage2-Continued-RuleRL1000-seed42" \
        --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": "Freddie1946/PathVLM-R1-Stage2-Continued-RuleRL1000-seed42",
		"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 Freddie1946/PathVLM-R1-Stage2-Continued-RuleRL1000-seed42 with Docker Model Runner:
```
docker model run hf.co/Freddie1946/PathVLM-R1-Stage2-Continued-RuleRL1000-seed42
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

PathVLM-R1-Stage2-Continued-RuleRL1000-seed42

Stage2 outcome-RL checkpoint continued with rule-only RL.

This is a research checkpoint derived from Qwen2.5-VL-7B-Instruct. It is archived to support the controlled experiments and reviewer-response analysis for PathVLM-R1. It is not intended for clinical deployment or diagnosis.

Access

The repository is public for discovery, but weight downloads require manual approval by the repository owner.

Training record

Expected terminal optimizer step: 1500
Seed: 42
Backup type: model-only; optimizer and RNG state are not included
Exact file hashes are provided in snapshot_manifest.json

The complete experimental protocol, evaluation scope and limitations are maintained in the associated PathVLM-R1 revision repository.

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for Freddie1946/PathVLM-R1-Stage2-Continued-RuleRL1000-seed42

Base model

Qwen/Qwen2.5-VL-7B-Instruct

Finetuned

(1177)

this model