RichardErkhov/nota-ai_-_cpt_st-vicuna-v1.3-1.5b-ppl-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

cpt_st-vicuna-v1.3-1.5b-ppl - GGUF

• —Model creator: https://huggingface.co/nota-ai/
• —Original model: https://huggingface.co/nota-ai/cpt_st-vicuna-v1.3-1.5b-ppl/

Original model description:

Shortened LLM Model Card

Shortened LLM is a depth-pruned version of large language models for efficient text generation.

• —Developed by: Nota AI
• —License: Non-commercial license
• —Repository: https://github.com/Nota-NetsPresso/shortened-llm
• —Paper: https://arxiv.org/abs/2402.02834

Compression Method

• —After identifying unimportant Transformer blocks, we perform one-shot pruning.
• —In retraining pruned models for quality recovery, continued pretraining (CPT) on a large corpus markedly outperforms LoRA-based tuning, particularly at severe pruning ratios.

Models from Aggressive Pruning & CPT Retraining (arXiv-v2):

<details> <summary> Click to see the results: </summary>

• —EleutherAI/lm-evaluation-harness version 3326c54

<img alt="results" img src="https://netspresso-research-code-release.s3.us-east-2.amazonaws.com/compressed-llm/stllm-cptresults.png" width="100%">

</details>

Experimental Setup for CPT of Pruned Vicuna-7B

• —Dataset: SlimPajama-627B
• —Training using 8 NVIDIA H100 GPUs.
• —5.5B parameters: 37B training tokens (for 6 days)
• —3.7B parameters: 74B tokens (for 8 days)
• —2.7B parameters: 150B tokens (for 12 days)
• —1.5B parameters: 271B tokens (for 11 days)
• —AdamW optimizer with (β1, β2)=(0.9, 0.95); a learning rate of 0.0001; a weight decay of 0.1.
• —Global batch size: 512 (micro-batch size of 2 × 32 gradient accumulation steps × 8 GPUs).

<details> <summary> Click to see the learning curve: </summary>

Zero-shot performance over the course of training for models from Vicuna-7B-v1.3 at different pruning ratios. For each model size, the CPT duration was limited to a two-week period, but additional training could further improve the quality.

<img alt="results" img src="https://netspresso-research-code-release.s3.us-east-2.amazonaws.com/compressed-llm/stllm-cptlearning-curve.png" width="100%">

</details>

Models from Moderate Pruning & LoRA Retraining (arXiv-v1):

<details>

<summary> Click to see the results: </summary>

• —EleutherAI/lm-evaluation-harness version 3326c54

<img alt="results" img src="https://netspresso-research-code-release.s3.us-east-2.amazonaws.com/compressed-llm/st-llamazero-shotscores.png" width="100%">

</details>

License

• —All rights related to this repository and the compressed models are reserved by Nota Inc.
• —The intended use is strictly limited to research and non-commercial projects.

Acknowledgments

• —Microsoft for Startups Founders Hub and Gwangju AICA for generously providing GPU resources.
• —LLM-Pruner, which utilizes LM Evaluation Harness, PEFT, and Alpaca-LoRA. Thanks for the pioneering work on structured pruning of LLMs!
• —Meta AI's LLaMA and LMSYS Org's Vicuna. Thanks for the open-source LLMs!

Citation

@article{kim2024shortened,
  title={Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods},
  author={Kim, Bo-Kyeong and Kim, Geonmin and Kim, Tae-Ho and Castells, Thibault and Choi, Shinkook and Shin, Junho and Song, Hyoung-Kyu},
  journal={arXiv preprint arXiv:2402.02834},      
  year={2024},
  url={https://arxiv.org/abs/2402.02834}
}

@article{kim2024mefomo,
  title={Shortened LLaMA: A Simple Depth Pruning for Large Language Models},
  author={Kim, Bo-Kyeong and Kim, Geonmin and Kim, Tae-Ho and Castells, Thibault and Choi, Shinkook and Shin, Junho and Song, Hyoung-Kyu},
  journal={ICLR Workshop on Mathematical and Empirical Understanding of Foundation Models (ME-FoMo)},
  year={2024},
  url={https://openreview.net/forum?id=18VGxuOdpu}
}