Instructions to use rbryant19/opscribe-captioner-merged-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbryant19/opscribe-captioner-merged-v1 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("/staging/rhbryant/hf_cache/models--Qwen--Qwen2.5-VL-72B-Instruct/snapshots/89c86200743eec961a297729e7990e8f2ddbc4c5")
model = PeftModel.from_pretrained(base_model, "rbryant19/opscribe-captioner-merged-v1")

Transformers

How to use rbryant19/opscribe-captioner-merged-v1 with Transformers:

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

pipe = pipeline("text-generation", model="rbryant19/opscribe-captioner-merged-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("rbryant19/opscribe-captioner-merged-v1", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rbryant19/opscribe-captioner-merged-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rbryant19/opscribe-captioner-merged-v1"
# 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-merged-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rbryant19/opscribe-captioner-merged-v1

SGLang

How to use rbryant19/opscribe-captioner-merged-v1 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-merged-v1" \
    --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-merged-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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-merged-v1" \
        --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-merged-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rbryant19/opscribe-captioner-merged-v1 with Docker Model Runner:
```
docker model run hf.co/rbryant19/opscribe-captioner-merged-v1
```

OpScribe Captioner Combined v1

LoRA adapter for Qwen2.5-VL-72B-Instruct — surgical frame captioning for the OpScribe pipeline.

Training

Base model: Qwen/Qwen2.5-VL-72B-Instruct
Dataset: EgoSurgery (9,618 frames) + surgeon-narrated voiceover dataset (3,402 frames, 3x weighted)
Total training examples: 13,020 train / 1,893 val
Framework: Custom PyTorch training loop, LoRA rank=16, alpha=32, lr=2e-4
Epochs: 3 (24h on 4x NVIDIA H200 140GB)
Best val_loss: 0.1046
Hardware: CHTC bhaskargpu4000

Usage

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from peft import PeftModel

base = Qwen2VLForConditionalGeneration.from_pretrained(
    "Qwen/Qwen2.5-VL-72B-Instruct", device_map="auto"
)
model = PeftModel.from_pretrained(base, "rbryant19/opscribe-captioner-merged-v1")
processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-72B-Instruct")

Framework versions

PEFT 0.18.1

Downloads last month: -

Model tree for rbryant19/opscribe-captioner-merged-v1

Base model

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

Adapter

(14)

this model