Instructions to use Tourr56/Mai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tourr56/Mai with Transformers:

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

pipe = pipeline("text-generation", model="Tourr56/Mai")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Tourr56/Mai")
model = AutoModelForCausalLM.from_pretrained("Tourr56/Mai", device_map="auto")
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 Tourr56/Mai with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Tourr56/Mai"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tourr56/Mai",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Tourr56/Mai

SGLang

How to use Tourr56/Mai 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 "Tourr56/Mai" \
    --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": "Tourr56/Mai",
		"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 "Tourr56/Mai" \
        --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": "Tourr56/Mai",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Tourr56/Mai with Docker Model Runner:
```
docker model run hf.co/Tourr56/Mai
```

model_gabungan

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Passthrough merge method using armand0e/Qwen3.5-4B-Gemini-3-Flash-Distill as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: passthrough
dtype: bfloat16
base_model: armand0e/Qwen3.5-4B-Gemini-3-Flash-Distill
modules:
  model.language_model.layers:
    slices:
      - sources:
          - model: armand0e/Qwen3.5-4B-Gemini-3-Flash-Distill
            layer_range: [0, 8]
      - sources:
          - model: p-e-w/Qwen3.5-4B-heretic
            layer_range: [8, 16]
      - sources:
          - model: DavidAU/Qwen3.5-4B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING
            layer_range: [16, 24]
      - sources:
          - model: huihui-ai/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated
            layer_range: [24, 32]

Downloads last month: 11

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for Tourr56/Mai

DavidAU/Qwen3.5-4B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING

armand0e/Qwen3.5-4B-Gemini-3-Flash-Distill

huihui-ai/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated

p-e-w/Qwen3.5-4B-heretic

Merge model

this model