Qwen2.5 14B Instruct GGUF

🚀 Qwen2.5-14B-Instruct GGUF Models

Qwen2.5-14B-Instruct GGUF models offer various formats to suit different hardware and memory requirements. These models are designed for text generation and are based on the Qwen/Qwen2.5-14B base model.

✨ Features

• Multiple Model Formats: BF16, F16, and various quantized models (Q4_K, Q6_K, Q8, etc.) are available to meet different hardware and memory needs.
• Enhanced Capabilities: Qwen2.5 brings significant improvements in knowledge, coding, mathematics, instruction following, long text generation, and more compared to Qwen2.
• Long-context Support: Supports up to 128K tokens and can generate up to 8K tokens.
• Multilingual Support: Supports over 29 languages.

📦 Installation

The installation process depends on the specific usage scenario and hardware. Please refer to the official documentation for detailed installation instructions.

💻 Usage Examples

Basic Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Qwen/Qwen2.5-14B-Instruct"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "Give me a short introduction to large language model."
messages = [
    {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

Processing Long Texts

{
  ...,
  "rope_scaling": {
    "factor": 4.0,
    "original_max_position_embeddings": 32768,
    "type": "yarn"
  }
}

📚 Documentation

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).

Summary Table: Model Format Selection

Included Files & Details

• Qwen2.5-14B-Instruct-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.
• Qwen2.5-14B-Instruct-f16.gguf: Model weights stored in F16. Use if your device supports FP16, especially if BF16 is not available.
• Qwen2.5-14B-Instruct-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.
• Qwen2.5-14B-Instruct-f16-q8_0.gguf: Output & embeddings remain in F16. All other layers quantized to Q8_0.
• Qwen2.5-14B-Instruct-q4_k.gguf: Output & embeddings quantized to Q8_0. All other layers quantized to Q4_K. Good for CPU inference with limited memory.
• Qwen2.5-14B-Instruct-q4_k_s.gguf: Smallest Q4_K variant, using less memory at the cost of accuracy. Best for very low-memory setups.
• Qwen2.5-14B-Instruct-q6_k.gguf: Output & embeddings quantized to Q8_0. All other layers quantized to Q6_K .
• Qwen2.5-14B-Instruct-q8_0.gguf: Fully Q8 quantized model for better accuracy. Requires more memory but offers higher precision.

Testing and Available AI Assistants

• TestLLM: Runs the current testing model using llama.cpp on 6 threads of a Cpu VM. Inference speed is slow and it only processes one user prompt at a time.
• TurboLLM: Uses gpt-4o-mini. Fast but tokens are limited. You can Login or Download the Free Network Monitor agent to get more tokens.
• HugLLM: Runs open-source Hugging Face models. Fast but runs small models (≈8B) hence lower quality. Get 2x more tokens (subject to Hugging Face API availability).

🔧 Technical Details

Qwen2.5 Improvements

Qwen2.5 brings the following improvements upon Qwen2:

• Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains.
• Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots.
• Long-context Support up to 128K tokens and can generate up to 8K tokens.
• Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.

Processing Long Texts

The current config.json is set for context length up to 32,768 tokens. To handle extensive inputs exceeding 32,768 tokens, we utilize YaRN, a technique for enhancing model length extrapolation, ensuring optimal performance on lengthy texts.

📄 License

This project is licensed under the Apache-2.0 License.

Citation

If you find our work helpful, feel free to give us a cite.

@misc{qwen2.5,
    title = {Qwen2.5: A Party of Foundation Models},
    url = {https://qwenlm.github.io/blog/qwen2.5/},
    author = {Qwen Team},
    month = {September},
    year = {2024}
}

@article{qwen2,
      title={Qwen2 Technical Report}, 
      author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan},
      journal={arXiv preprint arXiv:2407.10671},
      year={2024}
}