From 7c3e00f8417d73f46afcdf853153ee0792da080d Mon Sep 17 00:00:00 2001 From: Raymond Ng Date: Thu, 4 Apr 2024 14:26:01 +0800 Subject: [PATCH] add section on deployment framework --- README.md | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 6342997..303c79b 100644 --- a/README.md +++ b/README.md @@ -131,6 +131,16 @@ The configuration used for pre-training and an overview guide is provided [here] The SEA-LION models can be fine-tuned using the HuggingFace TRL library. An overview guide and sample configurations are provided [here](examples/fine-tuning/README.md). +## Deployment Framework + +### Text-Generation-Inference (TGI) + +SEA-LION is natively supported in TGI from [v1.4.0](https://github.com/huggingface/text-generation-inference/releases/tag/v1.4.0). + +### vLLM + +For SEA-LION vLLM intergration, please refer to this [guide for instructions](https://github.com/aisingapore/sealion/tree/vllm/vllm). + ## Contributing We welcome contributions to SEA-LION! Check out the [contributing guide](CONTRIBUTING.md) to get started. @@ -168,7 +178,7 @@ Any opinion, finding, conclusion or recommendation expressed in this material ar For questions, comments, or issues, please open a GitHub issue or contact us via this [SEA-LION Inquiry Form](https://forms.gle/sLCUVb95wmGf43hi6). -## Citations +## References ```bibtex @misc{lowphansirikul2021wangchanberta,