Instructions to use MagistrTheOne/murzik-15b-init with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MagistrTheOne/murzik-15b-init with Transformers:

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

pipe = pipeline("text-generation", model="MagistrTheOne/murzik-15b-init", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("MagistrTheOne/murzik-15b-init", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MagistrTheOne/murzik-15b-init with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MagistrTheOne/murzik-15b-init"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MagistrTheOne/murzik-15b-init",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MagistrTheOne/murzik-15b-init

SGLang

How to use MagistrTheOne/murzik-15b-init 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 "MagistrTheOne/murzik-15b-init" \
    --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": "MagistrTheOne/murzik-15b-init",
		"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 "MagistrTheOne/murzik-15b-init" \
        --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": "MagistrTheOne/murzik-15b-init",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MagistrTheOne/murzik-15b-init with Docker Model Runner:
```
docker model run hf.co/MagistrTheOne/murzik-15b-init
```

murzik-15b-init / chat_template.jinja

MagistrTheOne

Murzik-15B: PT checkpoint (1500 steps, wiki+identity) → murzik-15b-init

83d9edb verified 2 months ago

Raw

History Blame Contribute Delete

532 Bytes

	{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ 'System: ' + system_message + '<\|end\|>' + '
	' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '<\|end\|>' + '
	Assistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<\|end\|>' + '
	' }}{% endif %}{% endfor %}

	{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ 'System: ' + system_message + '<\|end\|>' + '
	' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '<\|end\|>' + '
	Assistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<\|end\|>' + '
	' }}{% endif %}{% endfor %}