Instructions to use modrill/merged_model_olmo3_7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use modrill/merged_model_olmo3_7b with Transformers:

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

pipe = pipeline("text-generation", model="modrill/merged_model_olmo3_7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("modrill/merged_model_olmo3_7b")
model = AutoModelForCausalLM.from_pretrained("modrill/merged_model_olmo3_7b")
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 modrill/merged_model_olmo3_7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "modrill/merged_model_olmo3_7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "modrill/merged_model_olmo3_7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/modrill/merged_model_olmo3_7b

SGLang

How to use modrill/merged_model_olmo3_7b 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 "modrill/merged_model_olmo3_7b" \
    --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": "modrill/merged_model_olmo3_7b",
		"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 "modrill/merged_model_olmo3_7b" \
        --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": "modrill/merged_model_olmo3_7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use modrill/merged_model_olmo3_7b with Docker Model Runner:
```
docker model run hf.co/modrill/merged_model_olmo3_7b
```

merged_model_olmo3_7b / chat_template.jinja

modrill

Add files using upload-large-folder tool

d55b042 verified 14 days ago

raw

history blame contribute delete

1.62 kB

{% set has_system = messages|selectattr('role', 'equalto', 'system')|list|length > 0 %}{% if not has_system %}{{ '<|im_start|>system\nYou are a helpful AI assistant. You do not currently have access to any functions. <functions></functions><|im_end|>\n' }}{% endif %}{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|im_start|>system\n' + message['content'] }}{% if message.get('functions', none) is not none %}{{ ' <functions>' + message['functions'] + '</functions><|im_end|>\n' }}{% else %}{{ ' You do not currently have access to any functions. <functions></functions><|im_end|>\n' }}{% endif %}{% elif message['role'] == 'user' %}{% if message.get('functions', none) is not none %}{{ '<|im_start|>user\n' + message['content'] + '\n<functions>' + message['functions'] + '</functions><|im_end|>\n' }}{% else %}{{ '<|im_start|>user\n' + message['content'] + '<|im_end|>\n' }}{% endif %}{% elif message['role'] == 'assistant' %}{{ '<|im_start|>assistant\n' }}{% if message.get('content', none) is not none %}{{ message['content'] }}{% endif %}{% if message.get('function_calls', none) is not none %}{{ '<function_calls>' + message['function_calls'] + '</function_calls>' }}{% endif %}{% if not loop.last %}{{ '<|im_end|>\n' }}{% else %}{{ '<|endoftext|>' }}{% endif %}{% elif message['role'] == 'observation' %}{{ '<|im_start|>environment\n' + message['content'] + '<|im_end|>\n' }}{% elif message['role'] == 'function' %}{{ '<|im_start|>environment\n' + message['content'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n<think>' }}{% endif %}