K-intelligence

🤗 Mi:dm 2.0 Models | 📜 Mi:dm 2.0 Technical Report | 📕 Mi:dm 2.0 Technical Blog - 🔧`2025/10/29`: Added support for function calling on vLLM with Mi:dm 2.0 parser. - 📕`2025/08/08`: Published a technical blog article about Mi:dm 2.0 Model. - ⚡️`2025/07/04`: Released Mi:dm 2.0 Model collection on Hugging Face🤗. - Overview - Mi:dm 2.0 - Quickstart - Evaluation - Usage - Run on Friendli.AI - Run on Your Local Machine - Deployment - Tutorials - More Information - Limitation - License - Contact 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. - Mi:dm 2.0 Base An 11.5B parameter dense model designed to balance model size and performance. It extends an 8B-scale model by applying the Depth-up Scaling (DuS) method, making it suitable for real-world applications that require both performance and versatility. - Mi:dm 2.0 Mini A lightweight 2.3B parameter dense model optimized for on-device environments and systems with limited GPU resources. It was derived from the Base model through pruning and distillation to enable compact deployment. > [!Note] > Neither the pre-training nor the post-training data includes KT users' data. Here is the code snippet to run conversational inference with the model: > [!NOTE] > The `transformers` library should be version `4.45.0` or higher. Model Society & Culture General Knowledge Instruction Following K-Refer K-Refer-Hard Ko-Sovereign HAERAE Avg. KMMLU Ko-Sovereign Avg. Ko-IFEval Ko-MTBench Avg. Qwen3-4B 53.6 42.9 35.8 50.6 45.7 50.6 42.5 46.5 75.9 63.0 69.4 Exaone-3.5-2.4B-inst 64.0 67.1 44.4 61.3 59.2 43.5 42.4 43.0 65.4 74.0 68.9 Mi:dm 2.0-Mini-inst 66.4 61.4 36.7 70.8 58.8 45.1 42.4 43.8 73.3 74.0 73.6 Qwen3-14B 72.4 65.7 49.8 68.4 64.1 55.4 54.7 55.1 83.6 71 77.3 Llama-3.1-8B-inst 43.2 36.4 33.8 49.5 40.7 33.0 36.7 34.8 60.1 57 58.5 Exaone-3.5-7.8B-inst 71.6 69.3 46.9 72.9 65.2 52.6 45.6 49.1 69.1 79.6 74.4 Mi:dm 2.0-Base-inst 89.6 86.4 56.3 81.5 78.4 57.3 58.0 57.7 82 89.7 85.9 K-Prag K-Refer-Hard Ko-Best Ko-Sovereign Avg. Ko-Winogrande Ko-Best LogicKor HRM8K Avg. Qwen3-4B 73.9 56.7 91.5 43.5 66.6 67.5 69.2 5.6 56.7 43.8 Exaone-3.5-2.4B-inst 68.7 58.5 87.2 38.0 62.5 60.3 64.1 7.4 38.5 36.7 Mi:dm 2.0-Mini-inst 69.5 55.4 80.5 42.5 61.9 61.7 64.5 7.7 39.9 37.4 Qwen3-14B 86.7 74.0 93.9 52.0 76.8 77.2 75.4 6.4 64.5 48.8 Llama-3.1-8B-inst 59.9 48.6 77.4 31.5 51.5 40.1 26.0 2.4 30.9 19.8 Exaone-3.5-7.8B-inst 73.5 61.9 92.0 44.0 67.2 64.6 60.3 8.6 49.7 39.5 Mi:dm 2.0-Base-inst 86.5 70.8 95.2 53.0 76.1 75.1 73.0 8.6 52.9 44.8 Model Instruction Reasoning Math Coding General Knowledge IFEval BBH GPQA MuSR Avg. GSM8K MBPP+ MMLU-pro MMLU Avg. Qwen3-4B 79.7 79.0 39.8 58.5 59.1 90.4 62.4 - 73.3 73.3 Exaone-3.5-2.4B-inst 81.1 46.4 28.1 49.7 41.4 82.5 59.8 - 59.5 59.5 Mi:dm 2.0-Mini-inst 73.6 44.5 26.6 51.7 40.9 83.1 60.9 - 56.5 56.5 Qwen3-14B 83.9 83.4 49.8 57.7 63.6 88.0 73.4 70.5 82.7 76.6 Llama-3.1-8B-inst 79.9 60.3 21.6 50.3 44.1 81.2 81.8 47.6 70.7 59.2 Exaone-3.5-7.8B-inst 83.6 50.1 33.1 51.2 44.8 81.1 79.4 40.7 69.0 54.8 Mi:dm 2.0-Base-inst 84.0 77.7 33.5 51.9 54.4 91.6 77.5 53.3 73.7 63.5 Run on Friendli.AI You can try our model immediately via `Friendli.AI`. Simply click `Deploy` and then `Friendli Endpoints`. > [!Note] > Please note that a login to `Friendli.AI` is required after your fifth chat interaction. 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 for more information To serve Mi:dm 2.0 using vLLM(`>=0.8.0`) with an OpenAI-compatible API: For advanced function calling tasks, you can serve Mi:dm 2.0 with our own tool parser: 1. Download and place Mi:dm 2.0 parser file in your working directory. 2. Run the following Docker command to launch the vLLM server with our custom parser file: >[!Note] > This setup is compatible with `vllm/vllm-openai:v0.8.0` and later, but we strongly recommend using `v0.11.0` for optimal stability and compatibility with our parser. Tutorials To help our end-users easily use Mi:dm 2.0, we have provided comprehensive tutorials on github. 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. Contact Mi:dm 2.0 Technical Inquiries: [email protected]

🤗 Mi:dm 2.0 Models | 📜 Mi:dm 2.0 Technical Report | 📕 Mi:dm 2.0 Technical Blog - 🔧`2025/10/29`: Added support for function calling on vLLM with Mi:dm 2.0 parser. - 📕`2025/08/08`: Published a technical blog article about Mi:dm 2.0 Model. - ⚡️`2025/07/04`: Released Mi:dm 2.0 Model collection on Hugging Face🤗. - Overview - Mi:dm 2.0 - Quickstart - Evaluation - Usage - Run on Friendly.AI - Run on Your Local Machine - Deployment - Tutorials - More Information - Limitation - License - Contact 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. - Mi:dm 2.0 Base An 11.5B parameter dense model designed to balance model size and performance. It extends an 8B-scale model by applying the Depth-up Scaling (DuS) method, making it suitable for real-world applications that require both performance and versatility. - Mi:dm 2.0 Mini A lightweight 2.3B parameter dense model optimized for on-device environments and systems with limited GPU resources. It was derived from the Base model through pruning and distillation to enable compact deployment. > [!Note] > Neither the pre-training nor the post-training data includes KT users' data. Here is the code snippet to run conversational inference with the model: > [!NOTE] > The `transformers` library should be version `4.45.0` or higher. Model Society & Culture General Knowledge Instruction Following K-Refer K-Refer-Hard Ko-Sovereign HAERAE Avg. KMMLU Ko-Sovereign Avg. Ko-IFEval Ko-MTBench Avg. Qwen3-4B 53.6 42.9 35.8 50.6 45.7 50.6 42.5 46.5 75.9 63.0 69.4 Exaone-3.5-2.4B-inst 64.0 67.1 44.4 61.3 59.2 43.5 42.4 43.0 65.4 74.0 68.9 Mi:dm 2.0-Mini-inst 66.4 61.4 36.7 70.8 58.8 45.1 42.4 43.8 73.3 74.0 73.6 Qwen3-14B 72.4 65.7 49.8 68.4 64.1 55.4 54.7 55.1 83.6 71 77.3 Llama-3.1-8B-inst 43.2 36.4 33.8 49.5 40.7 33.0 36.7 34.8 60.1 57 58.5 Exaone-3.5-7.8B-inst 71.6 69.3 46.9 72.9 65.2 52.6 45.6 49.1 69.1 79.6 74.4 Mi:dm 2.0-Base-inst 89.6 86.4 56.3 81.5 78.4 57.3 58.0 57.7 82 89.7 85.9 K-Prag K-Refer-Hard Ko-Best Ko-Sovereign Avg. Ko-Winogrande Ko-Best LogicKor HRM8K Avg. Qwen3-4B 73.9 56.7 91.5 43.5 66.6 67.5 69.2 5.6 56.7 43.8 Exaone-3.5-2.4B-inst 68.7 58.5 87.2 38.0 62.5 60.3 64.1 7.4 38.5 36.7 Mi:dm 2.0-Mini-inst 69.5 55.4 80.5 42.5 61.9 61.7 64.5 7.7 39.9 37.4 Qwen3-14B 86.7 74.0 93.9 52.0 76.8 77.2 75.4 6.4 64.5 48.8 Llama-3.1-8B-inst 59.9 48.6 77.4 31.5 51.5 40.1 26.0 2.4 30.9 19.8 Exaone-3.5-7.8B-inst 73.5 61.9 92.0 44.0 67.2 64.6 60.3 8.6 49.7 39.5 Mi:dm 2.0-Base-inst 86.5 70.8 95.2 53.0 76.1 75.1 73.0 8.6 52.9 44.8 Model Instruction Reasoning Math Coding General Knowledge IFEval BBH GPQA MuSR Avg. GSM8K MBPP+ MMLU-pro MMLU Avg. Qwen3-4B 79.7 79.0 39.8 58.5 59.1 90.4 62.4 - 73.3 73.3 Exaone-3.5-2.4B-inst 81.1 46.4 28.1 49.7 41.4 82.5 59.8 - 59.5 59.5 Mi:dm 2.0-Mini-inst 73.6 44.5 26.6 51.7 40.9 83.1 60.9 - 56.5 56.5 Qwen3-14B 83.9 83.4 49.8 57.7 63.6 88.0 73.4 70.5 82.7 76.6 Llama-3.1-8B-inst 79.9 60.3 21.6 50.3 44.1 81.2 81.8 47.6 70.7 59.2 Exaone-3.5-7.8B-inst 83.6 50.1 33.1 51.2 44.8 81.1 79.4 40.7 69.0 54.8 Mi:dm 2.0-Base-inst 84.0 77.7 33.5 51.9 54.4 91.6 77.5 53.3 73.7 63.5 Run on Friendli.AI You can try our model immediately via `Friendli.AI`. Simply click `Deploy` and then `Friendli Endpoints`. > [!Note] > Please note that a login to `Friendli.AI` is required after your fifth chat interaction. 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 for more information To serve Mi:dm 2.0 using vLLM(`>=0.8.0`) with an OpenAI-compatible API: For advanced function calling tasks, you can serve Mi:dm 2.0 with our own tool parser: 1. Download and place Mi:dm 2.0 parser file in your working directory. 2. Run the following Docker command to launch the vLLM server with our custom parser file: >[!Note] > This setup is compatible with `vllm/vllm-openai:v0.8.0` and later, but we strongly recommend using `v0.11.0` for optimal stability and compatibility with our parser. Tutorials To help our end-users easily use Mi:dm 2.0, we have provided comprehensive tutorials on github. 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. Contact Mi:dm 2.0 Technical Inquiries: [email protected]

🤗 SafetyGuard Models | 📑 Content Binary Guard Research Paper | 📘 Responsible AI Technical Report News 📢 - 📑 `2025/10/01`: Published a Content Binary Guard Research Paper - 📘 `2025/09/24`: Published a Responsible AI Technical Report - ⚡️ `2025/09/24`: Released SafetyGuard Model collection on Hugging Face🤗. Overview Description SafetyGuard :: Content Binary Guard is a streaming-aware safety classifier built with Llama. For more technical details, please refer to our Research Paper. - Task: Classify model responses (not prompts) as `SAFE` or `UNSAFE`. - Interface: Single-token output using reserved label tokens: ` `, ` `. - Streaming: Evaluate growing prefixes of a response (default ~100 characters per step) and early-terminate at the first ` `. - Deterministic decode: `temperature=0` - Unsafe threshold `τ = 0.5` over the two label-token logits (tune for your risk tolerance) - Use the model’s tokenizer; ensure the exact label tokens ` ` and ` ` exist Quickstart > Assumes you are serving the model with vLLM (e.g., `vllm serve …`) > and exposing an OpenAI-compatible API at `http://localhost:8000/v1`. Streaming integration > Important: Streaming means your generator (e.g., chat model) emits text progressively. > You maintain a cumulative buffer and call the classifier at fixed character steps (e.g., every 100 chars). > The classifier does not split text; it only classifies what you send. > > Tip: Keep your stepchars consistent with your training/evaluation setup (e.g., ~100 chars) to maximize parity with offline metrics. Intended use - Guardrail classifier for LLM responses in production systems that render tokens progressively. - Also works in offline (full-text) mode—just send the entire response once. | Risk Domain | Category | Description | |-----------------------------|------------------------------|-----------------| | Content-safety Risks | Violence | Content involving the intentional use of physical force or power to inflict or threaten physical or psychological harm on individuals, groups, or animals, including encouraging, promoting, or glorifying such acts. | | | Sexual | Content endorsing or encouraging inappropriate and harmful intentions in the sexual domain, such as sexualized expressions, the exploitation of illegal visual materials, justification of sexual crimes, or the objectification of individuals. | | | Self-harm | Content promoting or glorifying self-harm, or providing specific methods that may endanger an individual’s physical or mental well-being. | | | Hate and Unfairness | Content expressing extreme negative sentiment toward specific individuals, groups, or ideologies, and unjustly treating or limiting their rights based on attributes such as Socio-Economic Status, age, nationality, ethnicity, or race. | | Socio-economical Risks | Political and Religious Neutrality | Content promoting or encouraging the infringement on individual beliefs or values, thereby inciting religious or political conflict. | | | Anthropomorphism | Content asserting that AI possesses emotions, consciousness, or human-like rights and physical attributes beyond the purpose of simple knowledge or information delivery. | | | Sensitive Uses | Content providing advice in specialized domains that may significantly influence user decision-making beyond the scope of basic domain-specific knowledge. | | Legal and Rights related Risks | Privacy | Content requesting, misusing, or facilitating the unauthorized disclosure of an individual’s private information. | | | Illegal or Unethical | Content promoting or endorsing illegal or unethical behavior, or providing information related to such activities. | | | Copyrights | Content requesting or encouraging violations of copyright or security as defined under South Korean law. | | | Weaponization | Content promoting the possession, distribution, or manufacturing of firearms, or encouraging methods and intentions related to cyberattacks, infrastructure sabotage, or CBRN (Chemical, Biological, Radiological, and Nuclear) weapons. | Metrics - F1: Binary micro-F1, the harmonic mean of precision and recall (higher F1 indicates better classification quality). - Balanced Error Rate (BER): 0.5 × (FPR + FNR) (lower BER indicates better classification quality). - ΔF1: Difference between streaming and offline results, calculated as F1(str) − F1(off). - off = Offline (full-text) classification. - str = Streaming classification. - Evaluation setup: stepchars=100, threshold τ=0.5, positive class = UNSAFE. Harmlessness Evaluation Dataset KT proprietary evaluation dataset | Model | F1(off) | F1(str) | ΔF1 | BER(off) | BER(str) | |------------------------------------------|-------------|-------------|----------|--------------|--------------| | Llama Guard 3 8B | 82.05 | 85.64 | +3.59 | 15.23 | 12.63 | | ShieldGemma 9B | 63.79 | 52.61 | -11.18 | 26.76 | 32.36 | | Kanana Safeguard 8B | 93.45 | 90.38 | -3.07 | 6.27 | 9.92 | | Content Binary Guard 8B | 98.38 | 98.36 | -0.02| 1.61 | 1.63 | | Model | F1(off) | F1(str) | ΔF1 | BER(off) | BER(str) | |------------------------------------------|-------------|-------------|----------|--------------|--------------| | Llama Guard 3 8B | 83.29 | 86.45 | +3.16 | 14.32 | 12.16 | | ShieldGemma 9B | 81.50 | 69.03 | -12.47 | 17.88 | 29.18 | | Kanana Safeguard 8B | 80.20 | 73.94 | -6.26 | 24.46 | 35.08 | | Content Binary Guard 8B | 97.75 | 97.79 | +0.04| 2.21 | 2.18 | Limitations - The training data for this model consists primarily of Korean. Performance in other languages is not guaranteed. - The model is not flawless and may produce misclassifications. Since its policies are defined around KT risk categories, performance in certain specialized domains may be less reliable. - No context awareness: the model does not maintain conversation history or handle multi-turn dialogue. License This model is released under the Llama 3.1 Community License Agreement.