license: other license_name: yi-license license_link: LICENSE

Yi

Introduction

The Yi series models are large language models trained from scratch by developers at 01.AI. The first public release contains two base models with the parameter size of 6B and 34B. Besides, a specialized version with 200K context window size is also provided.

News

🎯 2023/11/05: The base model of Yi-6B and Yi-34B (with 200K context window)

Model Performance

(FIXME)

Usage

1. Download the model (optional)

By default the model weights and tokenizer will be downloaded from HuggingFace automatically in the next step. You can also download them manually from the following places:

ModelScope (FIXME)
Mirror site (remember to extra the content with tar)
- Yi-6B.tar
- Yi-34B.tar

2. Run with docker

The recommended approach to try out our models is through docker. We provide the following docker images.

ghcr.io/01-ai/yi:latest
ml-a100-cn-beijing.cr.volces.com/ci/01-ai/yi:latest

Note that the latest tag always point to the latest code in the main branch. To test a stable version, please replace it with a specific tag.

2.1 Try out the base model:

docker run -it ghcr.io/01-ai/yi:latest python demo/text_generation.py

To reuse the downloaded models in the previous step, you can mount them into the container:

docker run -it                   \
  -v /path/to/model:/model       \
  ghcr.io/01-ai/yi:latest        \
  python demo/text_generation.py \
  --model /model

For more advanced usage, please refer the doc.

2.2 Finetuning from the base model:

docker run -it                                      \
  -v /path/to/base/model:/base_model                \
  -v /path/to/save/finetuned/model:/finetuned_model \
  ghcr.io/01-ai/yi:latest                           \
  bash finetune/scripts/run_sft_Yi_6b.sh

Once finished, you can compare the finetuned model and the base model with the following command:

docker run -it                                       \
  -v /path/to/save/finetuned/model/:/finetuned_model \
  -v /path/to/base/model/:/base_model                \
  ghcr.io/01-ai/yi:latest                            \
  bash finetune/scripts/run_eval.sh

For more advanced usage like fine-tuning based on your custom data, please refer the doc.

2.3 Quantization

docker run -it                                         \
  -v /path/to/base/model:/base_model                   \
  -v /path/to/save/quantization/model:/quantized_model \
  ghcr.io/01-ai/yi:latest                              \
  python quantization/gptq/quant_autogptq.py           \
  --model /base_model                                  \
  --output_dir /quantized_model                        \
  --trust_remote_code

Once finished, you can then evaluate the resulted model as follows:

docker run -it                                         \
  -v /path/to/save/quantization/model:/quantized_model \
  ghcr.io/01-ai/yi:latest                              \
  python quantization/gptq/eval_quantized_model.py     \
  --model /quantized_model                             \
  --trust_remote_code

For more detailed explanation, please read the doc

Disclaimer

Although we use data compliance checking algorithms during the training process to ensure the compliance of the trained model to the best of our ability, due to the complexity of the data and the diversity of language model usage scenarios, we cannot guarantee that the model will generate correct and reasonable output in all scenarios. Please be aware that there is still a risk of the model producing problematic outputs. We will not be responsible for any risks and issues resulting from misuse, misguidance, illegal usage, and related misinformation, as well as any associated data security concerns.

License

The source code in this repo is licensed under the Apache 2.0 license. The Yi series model must be adhere to the Model License Agreement.