Instructions to use Merlin-Research/Merlin-Agent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Merlin-Research/Merlin-Agent with Transformers:

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

pipe = pipeline("text-generation", model="Merlin-Research/Merlin-Agent")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Merlin-Research/Merlin-Agent")
model = AutoModelForCausalLM.from_pretrained("Merlin-Research/Merlin-Agent")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Merlin-Research/Merlin-Agent with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Merlin-Research/Merlin-Agent"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Merlin-Research/Merlin-Agent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Merlin-Research/Merlin-Agent

SGLang

How to use Merlin-Research/Merlin-Agent 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 "Merlin-Research/Merlin-Agent" \
    --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": "Merlin-Research/Merlin-Agent",
		"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 "Merlin-Research/Merlin-Agent" \
        --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": "Merlin-Research/Merlin-Agent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Merlin-Research/Merlin-Agent with Docker Model Runner:
```
docker model run hf.co/Merlin-Research/Merlin-Agent
```

Merlin-Agent / signature_records.json

squ11z1

Upload folder using huggingface_hub

3b4e58d verified 6 days ago

Raw

History Blame Contribute Delete

3.66 kB

	{
	"collected_at": "2026-07-02T06:07:00.294531+00:00",
	"backend": "ibm_marrakesh",
	"tiles": 25,
	"records": [
	{
	"slot": 0,
	"seed": 42,
	"backend": "ibm_marrakesh",
	"n_qubits": 100,
	"tiles": 25,
	"shots": 2048,
	"syk_depths": [
	1,
	2,
	3,
	4,
	5,
	6
	],
	"ibm_job_id": "d92ve0t958jc73bsbong",
	"otoc_6d": [
	0.08673828125,
	0.06501953125,
	0.06294921875,
	0.0621484375,
	0.06146484375,
	0.063828125
	]
	},
	{
	"slot": 1,
	"seed": 43,
	"backend": "ibm_marrakesh",
	"n_qubits": 100,
	"tiles": 25,
	"shots": 2048,
	"syk_depths": [
	1,
	2,
	3,
	4,
	5,
	6
	],
	"ibm_job_id": "d92ve0t958jc73bsbong",
	"otoc_6d": [
	0.19728515625,
	0.065625,
	0.06103515625,
	0.0636328125,
	0.06310546875,
	0.06396484375
	]
	},
	{
	"slot": 2,
	"seed": 44,
	"backend": "ibm_marrakesh",
	"n_qubits": 100,
	"tiles": 25,
	"shots": 2048,
	"syk_depths": [
	1,
	2,
	3,
	4,
	5,
	6
	],
	"ibm_job_id": "d92ve0t958jc73bsbong",
	"otoc_6d": [
	0.12580078125,
	0.06103515625,
	0.06216796875,
	0.0609375,
	0.06306640625,
	0.06375
	]
	},
	{
	"slot": 3,
	"seed": 45,
	"backend": "ibm_marrakesh",
	"n_qubits": 100,
	"tiles": 25,
	"shots": 2048,
	"syk_depths": [
	1,
	2,
	3,
	4,
	5,
	6
	],
	"ibm_job_id": "d92ve0t958jc73bsbong",
	"otoc_6d": [
	0.24994140625,
	0.10943359375,
	0.05970703125,
	0.06130859375,
	0.063203125,
	0.06275390625
	]
	},
	{
	"slot": 4,
	"seed": 46,
	"backend": "ibm_marrakesh",
	"n_qubits": 100,
	"tiles": 25,
	"shots": 2048,
	"syk_depths": [
	1,
	2,
	3,
	4,
	5,
	6
	],
	"ibm_job_id": "d92ve0t958jc73bsbong",
	"otoc_6d": [
	0.06734375,
	0.06650390625,
	0.0615625,
	0.06162109375,
	0.0646875,
	0.06271484375
	]
	},
	{
	"slot": 5,
	"seed": 47,
	"backend": "ibm_marrakesh",
	"n_qubits": 100,
	"tiles": 25,
	"shots": 2048,
	"syk_depths": [
	1,
	2,
	3,
	4,
	5,
	6
	],
	"ibm_job_id": "d92ve0t958jc73bsbong",
	"otoc_6d": [
	0.07216796875,
	0.07421875,
	0.0793359375,
	0.063125,
	0.06453125,
	0.06048828125
	]
	},
	{
	"slot": 6,
	"seed": 48,
	"backend": "ibm_marrakesh",
	"n_qubits": 100,
	"tiles": 25,
	"shots": 2048,
	"syk_depths": [
	1,
	2,
	3,
	4,
	5,
	6
	],
	"ibm_job_id": "d92ve0t958jc73bsbong",
	"otoc_6d": [
	0.2820703125,
	0.09130859375,
	0.06955078125,
	0.06390625,
	0.0606640625,
	0.06275390625
	]
	},
	{
	"slot": 7,
	"seed": 49,
	"backend": "ibm_marrakesh",
	"n_qubits": 100,
	"tiles": 25,
	"shots": 2048,
	"syk_depths": [
	1,
	2,
	3,
	4,
	5,
	6
	],
	"ibm_job_id": "d92ve0t958jc73bsbong",
	"otoc_6d": [
	0.14970703125,
	0.067109375,
	0.07498046875,
	0.06775390625,
	0.06279296875,
	0.06373046875
	]
	}
	]
	}