Quantization made by Richard Erkhov.

TAID-LLM-1.5B - GGUF

Model creator: https://huggingface.co/SakanaAI/
Original model: https://huggingface.co/SakanaAI/TAID-LLM-1.5B/

Name	Quant method	Size
TAID-LLM-1.5B.Q2_K.gguf	Q2_K	0.63GB
TAID-LLM-1.5B.IQ3_XS.gguf	IQ3_XS	0.68GB
TAID-LLM-1.5B.IQ3_S.gguf	IQ3_S	0.71GB
TAID-LLM-1.5B.Q3_K_S.gguf	Q3_K_S	0.71GB
TAID-LLM-1.5B.IQ3_M.gguf	IQ3_M	0.72GB
TAID-LLM-1.5B.Q3_K.gguf	Q3_K	0.77GB
TAID-LLM-1.5B.Q3_K_M.gguf	Q3_K_M	0.77GB
TAID-LLM-1.5B.Q3_K_L.gguf	Q3_K_L	0.82GB
TAID-LLM-1.5B.IQ4_XS.gguf	IQ4_XS	0.84GB
TAID-LLM-1.5B.Q4_0.gguf	Q4_0	0.87GB
TAID-LLM-1.5B.IQ4_NL.gguf	IQ4_NL	0.88GB
TAID-LLM-1.5B.Q4_K_S.gguf	Q4_K_S	0.88GB
TAID-LLM-1.5B.Q4_K.gguf	Q4_K	0.92GB
TAID-LLM-1.5B.Q4_K_M.gguf	Q4_K_M	0.92GB
TAID-LLM-1.5B.Q4_1.gguf	Q4_1	0.95GB
TAID-LLM-1.5B.Q5_0.gguf	Q5_0	1.02GB
TAID-LLM-1.5B.Q5_K_S.gguf	Q5_K_S	1.02GB
TAID-LLM-1.5B.Q5_K.gguf	Q5_K	1.05GB
TAID-LLM-1.5B.Q5_K_M.gguf	Q5_K_M	1.05GB
TAID-LLM-1.5B.Q5_1.gguf	Q5_1	1.1GB
TAID-LLM-1.5B.Q6_K.gguf	Q6_K	1.18GB
TAID-LLM-1.5B.Q8_0.gguf	Q8_0	1.53GB

Original model description:

license: apache-2.0 language: - en pipeline_tag: text-generation library_name: transformers base_model: - Qwen/Qwen2-1.5B-Instruct datasets: - HuggingFaceTB/smollm-corpus

🐟 TAID-LLM-1.5B

🤗 Models | 📚 Paper | 📝 Blog | 🐦 Twitter

TAID-LLM-1.5B is an English language model created through TAID (Temporally Adaptive Interpolated Distillation), our new knowledge distillation method. We used Qwen2-72B-Instruct as the teacher model and Qwen2-1.5B-Instruct as the student model.

Model Details

Developed by: Sakana AI
Model type: Autoregressive Language Model
Language(s): English
License: Apache License, Version 2.0
Paper: https://arxiv.org/abs/2501.16937
Blog: https://sakana.ai/taid/

Uses

This model is provided for research and development purposes only and should be considered as an experimental prototype. It is not intended for commercial use or deployment in mission-critical environments. Use of this model is at the user's own risk, and its performance and outcomes are not guaranteed. Sakana AI shall not be liable for any direct, indirect, special, incidental, or consequential damages, or any loss arising from the use of this model, regardless of the results obtained. Users must fully understand the risks associated with the use of this model and use it at their own discretion.

Acknowledgement

We would like to thank the developers of the source models for their contributions and for making their work available.

This model is based on results obtained from a project, JPNP20017, subsidized by the New Energy and Industrial Technology Development Organization (NEDO).

Citation

@misc{sakana2025taid,
      title         = {TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models}, 
      author.       = {Makoto Shing and Kou Misaki and Han Bao and Sho Yokoi and Takuya Akiba},
      year          = {2025},
      eprint        = {2501.16937},
      archivePrefix = {arXiv},
      primaryClass  = {cs.LG},
      url           = {https://arxiv.org/abs/2501.16937}
}