Instructions to use rbryant19/opscribe-captioner-ortho-tool-v4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbryant19/opscribe-captioner-ortho-tool-v4 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-VL-72B-Instruct")
model = PeftModel.from_pretrained(base_model, "rbryant19/opscribe-captioner-ortho-tool-v4")

Transformers

How to use rbryant19/opscribe-captioner-ortho-tool-v4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="rbryant19/opscribe-captioner-ortho-tool-v4")
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("rbryant19/opscribe-captioner-ortho-tool-v4", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rbryant19/opscribe-captioner-ortho-tool-v4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rbryant19/opscribe-captioner-ortho-tool-v4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rbryant19/opscribe-captioner-ortho-tool-v4",
		"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/rbryant19/opscribe-captioner-ortho-tool-v4

SGLang

How to use rbryant19/opscribe-captioner-ortho-tool-v4 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 "rbryant19/opscribe-captioner-ortho-tool-v4" \
    --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": "rbryant19/opscribe-captioner-ortho-tool-v4",
		"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 "rbryant19/opscribe-captioner-ortho-tool-v4" \
        --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": "rbryant19/opscribe-captioner-ortho-tool-v4",
		"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 rbryant19/opscribe-captioner-ortho-tool-v4 with Docker Model Runner:
```
docker model run hf.co/rbryant19/opscribe-captioner-ortho-tool-v4
```

opscribe-captioner-ortho-tool-v4

SVD task arithmetic merge for Qwen2.5-VL-72B-Instruct surgical frame captioning.

Adapter	Weight	Rank	Data
captioner_voiceover_v1	0.60	16	Surgeon-narrated ortho voiceover — broad visual vocabulary
captioner_v3	0.40	32	targeted_captioner_v1 + v2 combined (1380 train / 187 val, val_loss 1.9630) — expanded TKA/THA/MTP missed-instrument coverage

Merged to rank 32 (alpha=32, scale=1.0) via efficient thin-SVD task arithmetic.

Training Details (captioner_v3 source)

Dataset: targeted_captioner_v1 (1001 train) + targeted_captioner_v2 (379 train) = 1380 total
New terms in v2: Gelpi, Aquamantys, Mueller, Alice/Allis, Kocher, precision saw, sponge, grafting (THA); McGlamery, Kocher, oscillating saw, suction, irrigation (MTP); keel punch, lap sponge, double-angle retractor, wide flat osteotome, Tumi, rich retractor, marking pen (TKA)
Epochs: 3 | batch_size: 1 | grad_accum: 8 | lr: 5e-5 | lora_rank: 32
Hardware: 4× NVIDIA H200, device_map=auto, bf16
Best val_loss: 1.9630 (epoch 3)

Downloads last month: 2

Model tree for rbryant19/opscribe-captioner-ortho-tool-v4

Base model

Qwen/Qwen2.5-VL-72B-Instruct

Adapter

(14)

this model