Instructions to use K-intelligence/Midm-2.0-Mini-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use K-intelligence/Midm-2.0-Mini-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="K-intelligence/Midm-2.0-Mini-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("K-intelligence/Midm-2.0-Mini-Instruct")
model = AutoModelForCausalLM.from_pretrained("K-intelligence/Midm-2.0-Mini-Instruct")
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

vLLM

How to use K-intelligence/Midm-2.0-Mini-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "K-intelligence/Midm-2.0-Mini-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "K-intelligence/Midm-2.0-Mini-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/K-intelligence/Midm-2.0-Mini-Instruct

SGLang

How to use K-intelligence/Midm-2.0-Mini-Instruct 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 "K-intelligence/Midm-2.0-Mini-Instruct" \
    --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": "K-intelligence/Midm-2.0-Mini-Instruct",
		"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 "K-intelligence/Midm-2.0-Mini-Instruct" \
        --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": "K-intelligence/Midm-2.0-Mini-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use K-intelligence/Midm-2.0-Mini-Instruct with Docker Model Runner:
```
docker model run hf.co/K-intelligence/Midm-2.0-Mini-Instruct
```

Midm-LLM commited on Jul 30, 2025

Commit

2f77541

verified ·

1 Parent(s): e7eea98

Update README.md

Browse files

Files changed (1) hide show

README.md +13 -13

README.md CHANGED Viewed

@@ -26,7 +26,7 @@ library_name: transformers
 <br>
-## News 📢
 - 🔜 _(Coming Soon!) GGUF format model files will be available soon for easier local deployment._
 - ⚡️`2025/07/04`: Released Mi:dm 2.0 Model collection on Hugging Face🤗.
@@ -53,7 +53,7 @@ library_name: transformers
 # Overview
-### Mi:dm 2.0
 **Mi:dm 2.0** is a __"Korea-centric AI"__ model developed using KT's proprietary technology. The term __"Korea-centric AI"__ refers to a model that deeply internalizes the unique values, cognitive frameworks, and commonsense reasoning inherent to Korean society. It goes beyond simply processing or generating Korean text—it reflects a deeper understanding of the socio-cultural norms and values that define Korean society.
@@ -74,7 +74,7 @@ Mi:dm 2.0 is released in two versions:
 <br>
-### Quickstart
 Here is the code snippet to run conversational inference with the model:
@@ -125,10 +125,10 @@ print(tokenizer.decode(output[0]))
 <br>
 <br>
-# Evaluation
-#### Korean
 <!-- first half table-->
 <table>
@@ -382,7 +382,7 @@ print(tokenizer.decode(output[0]))
 <br>
-#### English
 <table>
@@ -509,7 +509,7 @@ print(tokenizer.decode(output[0]))
 # Usage
-### Run on Friendli.AI
 You can try our model immediately via `Friendli.AI`. Simply click `Deploy` and then `Friendli Endpoints`.
 > [!Note]
@@ -520,11 +520,11 @@ You can try our model immediately via `Friendli.AI`. Simply click `Deploy` and t
   <img src="./assets/image_2.png" alt="Right Image" width="36%" style="display:inline-block">
 </p>
-### Run on Your Local Machine
 We provide a detailed description about running Mi:dm 2.0 on your local machine using llama.cpp, LM Studio, and Ollama. Please check our [github](https://github.com/K-intelligence-Midm/Midm-2.0) for more information
-### Deployment
 To serve Mi:dm 2.0 using [vLLM](https://github.com/vllm-project/vllm)(`>=0.8.0`) with an OpenAI-compatible API:
 ```bash
@@ -532,7 +532,7 @@ vllm serve K-intelligence/Midm-2.0-Mini-Instruct
 ```
-### Tutorials
 To help our end-users easily use Mi:dm 2.0, we have provided comprehensive tutorials on [github](https://github.com/K-intelligence-Midm/Midm-2.0).
 <br>
@@ -541,7 +541,7 @@ To help our end-users easily use Mi:dm 2.0, we have provided comprehensive tutor
 # More Information
-### Limitation
 * The training data for both Mi:dm 2.0 models consists primarily of English and Korean. Understanding and generation in other languages are not guaranteed.
 * The model is not guaranteed to provide reliable advice in fields that require professional expertise, such as law, medicine, or finance.
@@ -549,7 +549,7 @@ To help our end-users easily use Mi:dm 2.0, we have provided comprehensive tutor
 * Researchers have made efforts to exclude unethical content from the training data — such as profanity, slurs, bias, and discriminatory language. However, despite these efforts, the model may still produce inappropriate expressions or factual inaccuracies.
-### License
 Mi:dm 2.0 is licensed under the [MIT License](./LICENSE).
@@ -566,7 +566,7 @@ Mi:dm 2.0 is licensed under the [MIT License](./LICENSE).
       url={},
 }
 ``` -->
-### Contact
 Mi:dm 2.0 Technical Inquiries: midm-llm@kt.com
 <br>

 <br>
+# News 📢
 - 🔜 _(Coming Soon!) GGUF format model files will be available soon for easier local deployment._
 - ⚡️`2025/07/04`: Released Mi:dm 2.0 Model collection on Hugging Face🤗.
 # Overview
+## Mi:dm 2.0
 **Mi:dm 2.0** is a __"Korea-centric AI"__ model developed using KT's proprietary technology. The term __"Korea-centric AI"__ refers to a model that deeply internalizes the unique values, cognitive frameworks, and commonsense reasoning inherent to Korean society. It goes beyond simply processing or generating Korean text—it reflects a deeper understanding of the socio-cultural norms and values that define Korean society.
 <br>
+## Quickstart
 Here is the code snippet to run conversational inference with the model:
 <br>
 <br>
+## Evaluation
+### Korean
 <!-- first half table-->
 <table>
 <br>
+### English
 <table>
 # Usage
+## Run on Friendli.AI
 You can try our model immediately via `Friendli.AI`. Simply click `Deploy` and then `Friendli Endpoints`.
 > [!Note]
   <img src="./assets/image_2.png" alt="Right Image" width="36%" style="display:inline-block">
 </p>
+## Run on Your Local Machine
 We provide a detailed description about running Mi:dm 2.0 on your local machine using llama.cpp, LM Studio, and Ollama. Please check our [github](https://github.com/K-intelligence-Midm/Midm-2.0) for more information
+## Deployment
 To serve Mi:dm 2.0 using [vLLM](https://github.com/vllm-project/vllm)(`>=0.8.0`) with an OpenAI-compatible API:
 ```bash
 ```
+## Tutorials
 To help our end-users easily use Mi:dm 2.0, we have provided comprehensive tutorials on [github](https://github.com/K-intelligence-Midm/Midm-2.0).
 <br>
 # More Information
+## Limitation
 * The training data for both Mi:dm 2.0 models consists primarily of English and Korean. Understanding and generation in other languages are not guaranteed.
 * The model is not guaranteed to provide reliable advice in fields that require professional expertise, such as law, medicine, or finance.
 * Researchers have made efforts to exclude unethical content from the training data — such as profanity, slurs, bias, and discriminatory language. However, despite these efforts, the model may still produce inappropriate expressions or factual inaccuracies.
+## License
 Mi:dm 2.0 is licensed under the [MIT License](./LICENSE).
       url={},
 }
 ``` -->
+## Contact
 Mi:dm 2.0 Technical Inquiries: midm-llm@kt.com
 <br>