license, license_name, license_link, pipeline_tag, library_name

license	license_name	license_link	pipeline_tag	library_name
other	hyperclovax-seed	LICENSE	text-generation	transformers

HyperCLOVAX-SEED-Text-Instruct-0.5B GGUF Models

Model Generation Details

This model was generated using llama.cpp at commit 5e7d95e2.

Choosing the Right Model Format

Selecting the correct model format depends on your hardware capabilities and memory constraints.

BF16 (Brain Float 16) – Use if BF16 acceleration is available

• A 16-bit floating-point format designed for faster computation while retaining good precision.
• Provides similar dynamic range as FP32 but with lower memory usage.
• Recommended if your hardware supports BF16 acceleration (check your device's specs).
• Ideal for high-performance inference with reduced memory footprint compared to FP32.

📌 Use BF16 if:
✔ Your hardware has native BF16 support (e.g., newer GPUs, TPUs).
✔ You want higher precision while saving memory.
✔ You plan to requantize the model into another format.

📌 Avoid BF16 if:
❌ Your hardware does not support BF16 (it may fall back to FP32 and run slower).
❌ You need compatibility with older devices that lack BF16 optimization.

---

F16 (Float 16) – More widely supported than BF16

• A 16-bit floating-point high precision but with less of range of values than BF16.
• Works on most devices with FP16 acceleration support (including many GPUs and some CPUs).
• Slightly lower numerical precision than BF16 but generally sufficient for inference.

📌 Use F16 if:
✔ Your hardware supports FP16 but not BF16.
✔ You need a balance between speed, memory usage, and accuracy.
✔ You are running on a GPU or another device optimized for FP16 computations.

📌 Avoid F16 if:
❌ Your device lacks native FP16 support (it may run slower than expected).
❌ You have memory limitations.

---

Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference

Quantization reduces model size and memory usage while maintaining as much accuracy as possible.

• Lower-bit models (Q4_K) → Best for minimal memory usage, may have lower precision.
• Higher-bit models (Q6_K, Q8_0) → Better accuracy, requires more memory.

📌 Use Quantized Models if:
✔ You are running inference on a CPU and need an optimized model.
✔ Your device has low VRAM and cannot load full-precision models.
✔ You want to reduce memory footprint while keeping reasonable accuracy.

📌 Avoid Quantized Models if:
❌ You need maximum accuracy (full-precision models are better for this).
❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16).

---

Very Low-Bit Quantization (IQ3_XS, IQ3_S, IQ3_M, Q4_K, Q4_0)

These models are optimized for extreme memory efficiency, making them ideal for low-power devices or large-scale deployments where memory is a critical constraint.

• IQ3_XS: Ultra-low-bit quantization (3-bit) with extreme memory efficiency.

  • Use case: Best for ultra-low-memory devices where even Q4_K is too large.
  • Trade-off: Lower accuracy compared to higher-bit quantizations.

• IQ3_S: Small block size for maximum memory efficiency.

  • Use case: Best for low-memory devices where IQ3_XS is too aggressive.

• IQ3_M: Medium block size for better accuracy than IQ3_S.

  • Use case: Suitable for low-memory devices where IQ3_S is too limiting.

• Q4_K: 4-bit quantization with block-wise optimization for better accuracy.

  • Use case: Best for low-memory devices where Q6_K is too large.

• Q4_0: Pure 4-bit quantization, optimized for ARM devices.

  • Use case: Best for ARM-based devices or low-memory environments.

---

Summary Table: Model Format Selection

Model Format	Precision	Memory Usage	Device Requirements	Best Use Case
BF16	Highest	High	BF16-supported GPU/CPUs	High-speed inference with reduced memory
F16	High	High	FP16-supported devices	GPU inference when BF16 isn't available
Q4_K	Medium Low	Low	CPU or Low-VRAM devices	Best for memory-constrained environments
Q6_K	Medium	Moderate	CPU with more memory	Better accuracy while still being quantized
Q8_0	High	Moderate	CPU or GPU with enough VRAM	Best accuracy among quantized models
IQ3_XS	Very Low	Very Low	Ultra-low-memory devices	Extreme memory efficiency and low accuracy
Q4_0	Low	Low	ARM or low-memory devices	llama.cpp can optimize for ARM devices

---

Included Files & Details

HyperCLOVAX-SEED-Text-Instruct-0.5B-bf16.gguf

• Model weights preserved in BF16.
• Use this if you want to requantize the model into a different format.
• Best if your device supports BF16 acceleration.

HyperCLOVAX-SEED-Text-Instruct-0.5B-f16.gguf

• Model weights stored in F16.
• Use if your device supports FP16, especially if BF16 is not available.

HyperCLOVAX-SEED-Text-Instruct-0.5B-bf16-q8_0.gguf

• Output & embeddings remain in BF16.
• All other layers quantized to Q8_0.
• Use if your device supports BF16 and you want a quantized version.

HyperCLOVAX-SEED-Text-Instruct-0.5B-f16-q8_0.gguf

• Output & embeddings remain in F16.
• All other layers quantized to Q8_0.

HyperCLOVAX-SEED-Text-Instruct-0.5B-q4_k.gguf

• Output & embeddings quantized to Q8_0.
• All other layers quantized to Q4_K.
• Good for CPU inference with limited memory.

HyperCLOVAX-SEED-Text-Instruct-0.5B-q4_k_s.gguf

• Smallest Q4_K variant, using less memory at the cost of accuracy.
• Best for very low-memory setups.

HyperCLOVAX-SEED-Text-Instruct-0.5B-q6_k.gguf

• Output & embeddings quantized to Q8_0.
• All other layers quantized to Q6_K .

HyperCLOVAX-SEED-Text-Instruct-0.5B-q8_0.gguf

• Fully Q8 quantized model for better accuracy.
• Requires more memory but offers higher precision.

HyperCLOVAX-SEED-Text-Instruct-0.5B-iq3_xs.gguf

• IQ3_XS quantization, optimized for extreme memory efficiency.
• Best for ultra-low-memory devices.

HyperCLOVAX-SEED-Text-Instruct-0.5B-iq3_m.gguf

• IQ3_M quantization, offering a medium block size for better accuracy.
• Suitable for low-memory devices.

HyperCLOVAX-SEED-Text-Instruct-0.5B-q4_0.gguf

• Pure Q4_0 quantization, optimized for ARM devices.
• Best for low-memory environments.
• Prefer IQ4_NL for better accuracy.

🚀 If you find these models useful

❤ Please click "Like" if you find this useful!
Help me test my AI-Powered Network Monitor Assistant with quantum-ready security checks:
👉 Quantum Network Monitor

💬 How to test:
Choose an AI assistant type:

• TurboLLM (GPT-4o-mini)
• HugLLM (Hugginface Open-source)
• TestLLM (Experimental CPU-only)

What I’m Testing

I’m pushing the limits of small open-source models for AI network monitoring, specifically:

• Function calling against live network services
• How small can a model go while still handling:
  • Automated Nmap scans
  • Quantum-readiness checks
  • Network Monitoring tasks

🟡 TestLLM – Current experimental model (llama.cpp on 2 CPU threads):

• ✅ Zero-configuration setup
• ⏳ 30s load time (slow inference but no API costs)
• 🔧 Help wanted! If you’re into edge-device AI, let’s collaborate!

Other Assistants

🟢 TurboLLM – Uses gpt-4o-mini for:

• Create custom cmd processors to run .net code on Quantum Network Monitor Agents
• Real-time network diagnostics and monitoring
• Security Audits
• Penetration testing (Nmap/Metasploit)

🔵 HugLLM – Latest Open-source models:

• 🌐 Runs on Hugging Face Inference API

💡 Example commands to you could test:

1. "Give me info on my websites SSL certificate"
2. "Check if my server is using quantum safe encyption for communication"
3. "Run a comprehensive security audit on my server"
4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a Quantum Network Monitor Agent to run the .net code from. This is a very flexible and powerful feature. Use with caution!

Final Word

I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is open source. Feel free to use whatever you find helpful.

If you appreciate the work, please consider buying me a coffee ☕. Your support helps cover service costs and allows me to raise token limits for everyone.

I'm also open to job opportunities or sponsorship.

Thank you! 😊

Overview

HyperCLOVAX-SEED-Text-Instruct-0.5B is a Text-to-Text model with instruction-following capabilities that excels in understanding Korean language and culture. Compared to external competitors of similar scale, it demonstrates improved mathematical performance and a substantial enhancement in Korean language capability. The HyperCLOVAX-SEED-Text-Instruct-0.5B is currently the smallest model released by the HyperCLOVAX, representing a lightweight solution suitable for deployment in resource‑constrained environments such as edge devices. It supports a maximum context length of 4K and functions as a versatile small model applicable to a wide range of tasks. The total cost of a single training run for HyperCLOVAX-SEED-Text-Instruct-0.5B was 4.358K A100 GPU hours (approximately USD 6.537K), which is 39 times lower than the cost of training the QWEN2.5‑0.5B‑instruct model.

Basic Information

• Architecture: Transformer‑based (Dense Model)
• Parameters: 0.57 B (total); 0.45 B (excluding token embeddings, tied embeddings)
• Input/Output Format: Text / Text
• Maximum Context Length: 4 K tokens
• Knowledge Cutoff Date: Trained on data up to January 2025

Training and Data

The training dataset for HyperCLOVAX-SEED-Text-Instruct-0.5B consists of diverse sources, including the high‑quality data accumulated during the development of HyperCLOVAX-SEED-Text-Instruct-0.5B. Training was conducted in three main stages:

1. Pretraining: Knowledge acquisition using high‑quality data and a high‑performance pretrained model.
2. Rejection Sampling Fine‑Tuning (RFT): Enhancement of multi‑domain knowledge and complex reasoning capabilities.
3. Supervised Fine‑Tuning (SFT): Improvement of instruction‑following proficiency.

Training Cost

HyperCLOVAX-SEED-Text-Instruct-0.5B leveraged HyperCLOVA X’s lightweight training process and high‑quality data to achieve significantly lower training costs compared to industry‑leading competitors of similar scale. Excluding the SFT stage, a single pretraining run incurred:

Pretraining Cost Category	HyperCLOVAX-SEED-Text-Instruct-0.5B	QWEN2.5‑0.5B‑instruct
A100 GPU Hours	4.358 K	169.257 K
Cost (USD)	6.537 K	253.886 K

This represents approximately a 39× reduction in pretraining cost relative to QWEN2.5‑0.5B-instruct.

Benchmarks

Model	KMMLU (5-shot, acc)	HAE-RAE (5-shot, acc)	CLiCK (5-shot, acc)	KoBEST (5-shot, acc)
HyperCLOVAX-SEED-Text-Base-0.5B	0.4181	0.6370	0.5373	0.6963
HyperCLOVAX-SEED-Text-Instruct-0.5B	0.3815	0.5619	0.4446	0.6299
QWEN2.5-0.5B-instruct	0.2968	0.3428	0.3805	0.5025

HuggingFace Usage Example

Python Code

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B").to(device="cuda")
tokenizer = AutoTokenizer.from_pretrained("naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B")

chat = [
  {"role": "tool_list", "content": ""},
  {"role": "system", "content": "- AI 언어모델의 이름은 \"CLOVA X\" 이며 네이버에서 만들었다.\n- 오늘은 2025년 04월 24일(목)이다."},
  {"role": "user", "content": "슈뢰딩거 방정식과 양자역학의 관계를 최대한 자세히 알려줘."},
]

inputs = tokenizer.apply_chat_template(chat, add_generation_prompt=True, return_dict=True, return_tensors="pt")
inputs = inputs.to(device="cuda")
output_ids = model.generate(**inputs, max_length=1024, stop_strings=["<|endofturn|>", "<|stop|>"], repetition_penalty=1.2, tokenizer=tokenizer)
print(tokenizer.batch_decode(output_ids))

Result

['<|im_start|>tool_list\n<|im_end|>\n<|im_start|>system\n- AI 언어모델의 이름은 "CLOVA X" 이며 네이버에서 만들었다.\n- 오늘은 2025년 04월 24일(목)이다.<|im_end|>\n<|im_start|>user\n슈뢰딩거 방정식과 양자역학의 관계를 최대한 자세히 알려줘.<|im_end|>\n<|im_start|>assistant\n양자역학은 슈뢰딩거 방정식을 통해 물질과 에너지, 공간 등의 현상을 설명합니다.\n\n**1. 슈뢰딩거 방정식**\n\n슈뢰딩거는 파동함수를 이용하여 입자의 위치와 운동량을 계산할 수 있다고 주장했습니다. 이를 위해 다음과 같은 식으로 표현됩니다:\n\n$$\\frac{\\partial \\psi}{\\partial t} = iH \\nabla^2 \\psi + V(x)\\psi $$\n\n여기서 $\\psi$는 파동함수이고 $i$는 허수 단위입니다. 여기서 $t$는 시간, $x$는 공간 좌표이며, $H$는 해밀턴 상수로 시스템의 에너지를 나타냅니다. 또한 $V(x)$는 외부 힘이나 장벽에 의해 영향을 받는 부분을 나타내는 함수로, 일반적으로 전위장을 사용합니다.\n\n**2. 양자역학과 슈뢰딩거 방정식의 관계**\n\n양자역학에서는 슈뢰딩거 방정식이 매우 중요한 역할을 합니다. 이는 모든 물리적 시스템이 불확정성 원리에 따라 행동을 하며, 이러한 시스템들은 확률적으로 상태를 가질 수밖에 없기 때문입니다. 따라서 슈뢰딩거 방정식은 양자역학을 수학적으로 모델링하는 핵심적인 도구 중 하나입니다.\n\n예를 들어, 원자핵 내의 전자들의 상태는 슈뢰딩거 방정식에 의해 결정되며, 이는 물리학적 법칙을 따르는 것으로 보입니다. 또한, 광전 효과에서도 슈뢰딩거 방정식은 빛이 물질 내에서 어떻게 흡수되고 반사되는지를 예측하는데 사용됩니다.\n\n**3. 응용 분야**\n\n슈뢰딩거 방정식은 다양한 분야에서 활용되고 있습니다. 예를 들면, 반도체 기술에서의 트랜지스터 설계, 핵물리학에서의 방사성 붕괴 연구 등이 있으며, 이는 모두 슈뢰딩거 방정식을 기반으로 한 이론적 기반 위에서 이루어집니다.\n\n또한, 현대 과학 기술의 발전에도 큰 기여를 하고 있는데, 특히 인공지능(AI), 컴퓨터 시뮬레이션 등에서 복잡한 문제를 해결하고 새로운 지식을 창출하기 위한 기초가 되고 있습니다.\n\n결론적으로, 슈뢰딩거 방정식은 양자역학의 기본 개념들을 이해하고 해석하며, 그 결과로서 많은 혁신적이고 실용적인 기술을 가능하게 했습니다. 이는 양자역학의 중요성을 보여주는 대표적인 예시라고 할 수 있습니다.<|im_end|><|endofturn|>']