Instructions to use IntelligenceLab/RSR-27B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IntelligenceLab/RSR-27B with Transformers:

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

pipe = pipeline("image-text-to-text", model="IntelligenceLab/RSR-27B")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("IntelligenceLab/RSR-27B")
model = AutoModelForMultimodalLM.from_pretrained("IntelligenceLab/RSR-27B", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use IntelligenceLab/RSR-27B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IntelligenceLab/RSR-27B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IntelligenceLab/RSR-27B",
		"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/IntelligenceLab/RSR-27B

SGLang

How to use IntelligenceLab/RSR-27B 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 "IntelligenceLab/RSR-27B" \
    --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": "IntelligenceLab/RSR-27B",
		"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 "IntelligenceLab/RSR-27B" \
        --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": "IntelligenceLab/RSR-27B",
		"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 IntelligenceLab/RSR-27B with Docker Model Runner:
```
docker model run hf.co/IntelligenceLab/RSR-27B
```

zli12321 commited on about 1 month ago

Commit

eb39843

verified ·

1 Parent(s): 9927098

Label runbook descriptions as shortened summaries

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -34,7 +34,7 @@ Terminus-2, runbook kept private). Browse them side by side in the **[interactiv
 Data, query & formal (tree-sitter). The expert never marked the task complete: it kept working until the 2-hour limit ended the run, and the work it left in place passed. Runbook: `runbook_01`, checked by the leak judge; 4 of 4 replays passed, in 13, 15, 15, 34 steps, and the one shown took 34.
-**Runbook, in brief.** A short plan for rebuilding the tree-sitter Markdown demo: learn what the reference outputs look like, write a script that reproduces them, and check that it generalizes beyond the public examples.
 **Expert** — Base Qwen3.8-27B · continue-until-timeout: 64 steps, 153 commands
@@ -75,7 +75,7 @@ Data, query & formal (tree-sitter). The expert never marked the task complete: i
 Systems & infrastructure (CMake). The expert never marked the task complete: it kept working until the 2-hour limit ended the run, and the work it left in place passed. Runbook: `runbook_02`, checked by the leak judge; 4 of 4 replays passed, in 24, 27, 27, 29 steps, and the one shown took 27.
-**Runbook, in brief.** A short plan for reproducing the CMake configuration demo: work out which outputs change with the scenario parameters, write a script that reproduces them, and check that it generalizes beyond the public examples.
 **Expert** — Base Qwen3.8-27B · continue-until-timeout: 59 steps, 94 commands
@@ -116,7 +116,7 @@ Systems & infrastructure (CMake). The expert never marked the task complete: it
 Physical science & simulation (OpenFOAM). The expert never marked the task complete: it kept working until the 2-hour limit ended the run, and the work it left in place passed. Runbook: `runbook_01`, checked by the leak judge; 4 of 4 replays passed, in 23, 23, 33, 51 steps, and the one shown took 23.
-**Runbook, in brief.** A short plan for reproducing the OpenFOAM boundary-probe demo: work out which results depend on the scenario parameters, write a script that reproduces them, and check that it generalizes beyond the public examples.
 **Expert** — Base Qwen3.8-27B · continue-until-timeout: 56 steps, 72 commands

 Data, query & formal (tree-sitter). The expert never marked the task complete: it kept working until the 2-hour limit ended the run, and the work it left in place passed. Runbook: `runbook_01`, checked by the leak judge; 4 of 4 replays passed, in 13, 15, 15, 34 steps, and the one shown took 34.
+**Shortened runbook** (a brief summary, not the actual runbook used): A short plan for rebuilding the tree-sitter Markdown demo: learn what the reference outputs look like, write a script that reproduces them, and check that it generalizes beyond the public examples.
 **Expert** — Base Qwen3.8-27B · continue-until-timeout: 64 steps, 153 commands
 Systems & infrastructure (CMake). The expert never marked the task complete: it kept working until the 2-hour limit ended the run, and the work it left in place passed. Runbook: `runbook_02`, checked by the leak judge; 4 of 4 replays passed, in 24, 27, 27, 29 steps, and the one shown took 27.
+**Shortened runbook** (a brief summary, not the actual runbook used): A short plan for reproducing the CMake configuration demo: work out which outputs change with the scenario parameters, write a script that reproduces them, and check that it generalizes beyond the public examples.
 **Expert** — Base Qwen3.8-27B · continue-until-timeout: 59 steps, 94 commands
 Physical science & simulation (OpenFOAM). The expert never marked the task complete: it kept working until the 2-hour limit ended the run, and the work it left in place passed. Runbook: `runbook_01`, checked by the leak judge; 4 of 4 replays passed, in 23, 23, 33, 51 steps, and the one shown took 23.
+**Shortened runbook** (a brief summary, not the actual runbook used): A short plan for reproducing the OpenFOAM boundary-probe demo: work out which results depend on the scenario parameters, write a script that reproduces them, and check that it generalizes beyond the public examples.
 **Expert** — Base Qwen3.8-27B · continue-until-timeout: 56 steps, 72 commands