Instructions to use Mindscend/mindtype-rewrite-360m-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Mindscend/mindtype-rewrite-360m-v2 with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Mindscend/mindtype-rewrite-360m-v2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Mindscend/mindtype-rewrite-360m-v2:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Mindscend/mindtype-rewrite-360m-v2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Mindscend/mindtype-rewrite-360m-v2:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Mindscend/mindtype-rewrite-360m-v2:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Mindscend/mindtype-rewrite-360m-v2:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Mindscend/mindtype-rewrite-360m-v2:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Mindscend/mindtype-rewrite-360m-v2:Q4_K_M

Use Docker

docker model run hf.co/Mindscend/mindtype-rewrite-360m-v2:Q4_K_M

LM Studio
Jan

vLLM

How to use Mindscend/mindtype-rewrite-360m-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mindscend/mindtype-rewrite-360m-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mindscend/mindtype-rewrite-360m-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Mindscend/mindtype-rewrite-360m-v2:Q4_K_M

Ollama
How to use Mindscend/mindtype-rewrite-360m-v2 with Ollama:
```
ollama run hf.co/Mindscend/mindtype-rewrite-360m-v2:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use Mindscend/mindtype-rewrite-360m-v2 with Docker Model Runner:
```
docker model run hf.co/Mindscend/mindtype-rewrite-360m-v2:Q4_K_M
```

Lemonade

How to use Mindscend/mindtype-rewrite-360m-v2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Mindscend/mindtype-rewrite-360m-v2:Q4_K_M

Run and chat with the model

lemonade run user.mindtype-rewrite-360m-v2-Q4_K_M

List all available models

lemonade list

Atomic Chat

mindtype-rewrite-360m-v2 (experimental)

The rewrite model behind MindType by Mindscend: it rewrites a sentence to be more formal, friendlier, shorter, clearer, simpler, neutral, or simply rephrased. It is a LoRA fine-tune of SmolLM2-360M-Instruct, merged and quantized to GGUF (Q4_K_M, 271 MB), small enough to run on a phone or a small CPU server with llama.cpp.

Experimental: formal rewrites are usually good; "friendly" often changes little, and "shorter" sometimes drops details (for example a name). Check the result before you use it.

Prompt format (important)

The model was trained on SmolLM2's chat format including its default system prompt. Without that system prompt it produces garbage. One user turn per sentence:

<|im_start|>system
You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
<|im_start|>user
Rewrite (formal):
Hey, can we go over to Uncle's place after school?<|im_end|>
<|im_start|>assistant

Modes: formal, friendly, shorter, clearer, simpler, neutral, rephrase. Use greedy decoding. llama-server applies this template (with the system prompt) on its own for /v1/chat/completions.

Examples (held-out messages, greedy)

Input	Mode	Output
Hey, can we go over to Uncle's place after school?	formal	Hello, could we arrange to go to Uncle's residence after school?
Hey, can we go over to Uncle's place after school?	shorter	Can we go to Uncle's after school?
Heading to the mall, want to join?	formal	I am planning to visit the mall. Would you like to join?
I will bring a few boxes to donate to the food drive. Is there a specific type?	friendly	I'll bring a few boxes to the food drive. Is there a specific type you'd like?

Training

57,829 examples: 20.8k rewrites (formal, friendly, shorter) of casual messages written by a local open-weight teacher (Qwen2.5-14B-Instruct, Apache-2.0), plus CoEdIT (Apache-2.0) for clearer, simpler, neutral and rephrase.
LoRA (all layers), 1 epoch, 3,615 steps at batch 16, on an Apple M4 Pro with mlx-lm; final validation loss 1.086.

Files

File	What it is
`model-q4_k_m.gguf`	merged model, GGUF Q4_K_M (llama.cpp)
`training.json`	training settings and dataset counts
`SHA256SUMS`	checksums

License

Apache-2.0, like the base model. Training data: teacher rewrites (Qwen2.5, Apache-2.0) and CoEdIT (Apache-2.0).

Downloads last month: 14

GGUF

Model size

0.4B params

Architecture

llama

Hardware compatibility

4-bit

Model tree for Mindscend/mindtype-rewrite-360m-v2

Base model

HuggingFaceTB/SmolLM2-360M

Quantized

HuggingFaceTB/SmolLM2-360M-Instruct

Quantized

(125)

this model