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

Libraries

How to use opencsg/Agentic-27B with Transformers:

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

pipe = pipeline("image-text-to-text", model="opencsg/Agentic-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("opencsg/Agentic-27B")
model = AutoModelForMultimodalLM.from_pretrained("opencsg/Agentic-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 opencsg/Agentic-27B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "opencsg/Agentic-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": "opencsg/Agentic-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/opencsg/Agentic-27B

SGLang

How to use opencsg/Agentic-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 "opencsg/Agentic-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": "opencsg/Agentic-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 "opencsg/Agentic-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": "opencsg/Agentic-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 opencsg/Agentic-27B with Docker Model Runner:
```
docker model run hf.co/opencsg/Agentic-27B
```

ZionWong commited on Sep 12

Commit

8c73132

verified ·

1 Parent(s): d480d70

Delete .ms_upload_cache

Browse files

Files changed (1) hide show

.ms_upload_cache +0 -1

.ms_upload_cache DELETED Viewed

@@ -1 +0,0 @@

- {"version": 3, "repo_id": "opencsg/Agentic-27B", "files": {"args.json|1788937435.0246255|24760": {"hash": "462347e43549c44ff31e9faec25784d1402e51def3da49d973c2f27294241ca1", "size": 24760, "status": "c"}, "config.json|1788937396.5624104|3713": {"hash": "0e9804c6f1769cf862cbf29cf2f492dc1718c561ea84fa7905f1ec604d02e04a", "size": 3713, "status": "c"}, "generation_config.json|1788937396.5634103|214": {"hash": "a4cef85934ea1fdcb207944dbc6eee70dbbf16806874428556ae33023336c0a4", "size": 214, "status": "c"}, "chat_template.jinja|1788937435.0236256|8952": {"hash": "c3cf9e34abf4f9e36c2d72165aa9c132d3e2a725b6c2586aaa3a8af9d7a81041", "size": 8952, "status": "c"}, "model-00001-of-00012.safetensors|1788937398.0084183|2542796928": {"hash": "54d83c1d36631de231876217a8e0c2483eccee8746369a482b79442bdfc5d958", "size": 2542796928, "status": "c"}, "model-00002-of-00012.safetensors|1788937401.5124378|4842451920": {"hash": "7ea119bb17e595803a09b6d09ecd1924158e2363cbba025cb090ab9a3bc6d01c", "size": 4842451920, "status": "c"}, "model-00006-of-00012.safetensors|1788937416.1245193|4912819320": {"hash": "14a4aaa7be9a852e7065d0ab87d03c67778f738f4c70707fc6559af2dcbd3500", "size": 4912819320, "status": "c"}, "model-00005-of-00012.safetensors|1788937412.3824985|4986198544": {"hash": "428e6daf3c641c064d50a70346c50c4200cceb4bdc1fc45f6446171412489326", "size": 4986198544, "status": "c"}, "model-00008-of-00012.safetensors|1788937422.886557|4966314576": {"hash": "14cb658181841362d51f3d0dae8db5387a05088216dd3243f4888d00485e3e49", "size": 4966314576, "status": "c"}, "model-00007-of-00012.safetensors|1788937419.5475385|4932703272": {"hash": "ce544f7f2e9dbec4ea954c90810058b42b7620ca05110b8fb7a399572074f252", "size": 4932703272, "status": "c"}, "model-00004-of-00012.safetensors|1788937408.892479|4912819264": {"hash": "28306c05bfadf5414a255176eeab06da570b3164e7871eacd4509cca20d2598d", "size": 4912819264, "status": "c"}, "model-00003-of-00012.safetensors|1788937405.0984578|4965227944": {"hash": "97a9b2fd6a1e37adec94c0a7979c26797b1e57b1223a6deb2a60803a01e2215a", "size": 4965227944, "status": "c"}, "model-00009-of-00012.safetensors|1788937425.500572|4964162248": {"hash": "5ee62616c41a5c1230a343b02c458e065b575c79a2e21cb8cd7d323b251bf202", "size": 4964162248, "status": "c"}, "model-00010-of-00012.safetensors|1788937429.266593|4933789824": {"hash": "da4828125c9669e8b69a2bed421981ee25efd5fa3ccd5af2d9a51e91728e0a55", "size": 4933789824, "status": "c"}, "model-00011-of-00012.safetensors|1788937433.0356143|4965228032": {"hash": "c706dd67abc9bef48cd5ffae7163e7ccb49c8d617e87174ef590131f93780fe7", "size": 4965228032, "status": "c"}, "model-00012-of-00012.safetensors|1788937434.8496246|2789094896": {"hash": "dd61bc73a36007d4213435ac85f124d251a45d261555984bd5482e52bbb7c828", "size": 2789094896, "status": "c"}, "model.safetensors.index.json|1788937434.8536246|111110": {"hash": "a600c6626eb1eb653a3f078ab3dd1c7a8fab2e71185c7ef3aa923a39aaa637be", "size": 111110, "status": "c"}, "preprocessor_config.json|1788937435.0246255|390": {"hash": "27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516", "size": 390, "status": "c"}, "processor_config.json|1788937435.0246255|1191": {"hash": "d89ef49ce9cd37fbf510158e13c1ef063d9286411c1ec9049932dbe0487143b1", "size": 1191, "status": "c"}, "tokenizer.json|1788937435.0106254|19989325": {"hash": "06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523", "size": 19989325, "status": "c"}, "tokenizer_config.json|1788937434.8546245|1165": {"hash": "792fa3f0cb88b111e54ef3134c873531008c4df471d108da17903426e308aa7b", "size": 1165, "status": "c"}}}