Instructions to use MariChatmen/MariChatmen-2B-Experimental with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MariChatmen/MariChatmen-2B-Experimental with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-2B-Base")
model = PeftModel.from_pretrained(base_model, "MariChatmen/MariChatmen-2B-Experimental")

Transformers

How to use MariChatmen/MariChatmen-2B-Experimental with Transformers:

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

pipe = pipeline("text-generation", model="MariChatmen/MariChatmen-2B-Experimental")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("MariChatmen/MariChatmen-2B-Experimental", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MariChatmen/MariChatmen-2B-Experimental with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MariChatmen/MariChatmen-2B-Experimental"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MariChatmen/MariChatmen-2B-Experimental",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MariChatmen/MariChatmen-2B-Experimental

SGLang

How to use MariChatmen/MariChatmen-2B-Experimental 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 "MariChatmen/MariChatmen-2B-Experimental" \
    --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": "MariChatmen/MariChatmen-2B-Experimental",
		"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 "MariChatmen/MariChatmen-2B-Experimental" \
        --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": "MariChatmen/MariChatmen-2B-Experimental",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MariChatmen/MariChatmen-2B-Experimental with Docker Model Runner:
```
docker model run hf.co/MariChatmen/MariChatmen-2B-Experimental
```

MariChatmen-2B-Experimental / chat_template.jinja

alobos

Publish local 2B experimental recovery adapter

e89aa7b verified about 2 months ago

Raw

History Blame Contribute Delete

494 Bytes

	{%- for message in messages %}
	{%- set content = message['content'] if message['content'] is string else '' %}
	{%- if message['role'] == 'assistant' %}
	{{- '<\|im_start\|>assistant
	' -}}{% generation %}{{- content + '<\|im_end\|>
	' }}{% endgeneration %}
	{%- elif message['role'] == 'system' or message['role'] == 'user' %}
	{{- '<\|im_start\|>' + message['role'] + '
	' + content + '<\|im_end\|>
	' }}
	{%- endif %}
	{%- endfor %}
	{%- if add_generation_prompt %}
	{{- '<\|im_start\|>assistant
	' }}
	{%- endif %}