From 5c5e7daa573294857d7e4097acab0b23298b1ecb Mon Sep 17 00:00:00 2001 From: "Wang, Yi A" Date: Sat, 17 Feb 2024 22:32:03 -0800 Subject: [PATCH] update README, add PPO support Signed-off-by: Wang, Yi A --- README.md | 7 ++++--- docs/source/index.mdx | 13 +++++++++++-- 2 files changed, 15 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index 1dd050ee9c..09a80082d6 100644 --- a/README.md +++ b/README.md @@ -197,7 +197,7 @@ The following model architectures, tasks and device distributions have been vali
| Architecture | Training | Inference | Tasks | -|------------------|:--------:|:--------------------:|:-----:| +|------------------|:--------:|:--------------------:|:------| | Stable Diffusion | |
  • Single card
    • |
  • [text-to-image generation](https://github.com/huggingface/optimum-habana/tree/main/examples/stable-diffusion)
    • | | LDM3D | |
  • Single card
    • |
  • [text-to-image generation](https://github.com/huggingface/optimum-habana/tree/main/examples/stable-diffusion)
    • | @@ -208,8 +208,9 @@ The following model architectures, tasks and device distributions have been vali
    | Architecture | Training | Inference | Tasks | -|------------------|:--------:|:--------------------:|:-----:| -| Llama 2 |
  • Multi card
    • | |
  • [DPO Pipeline](https://github.com/huggingface/optimum-habana/tree/main/examples/trl)
    • | +|------------------|:--------:|:--------------------:|:------| +| Llama 2 | :heavy_check_mark: | |
  • [DPO Pipeline](https://github.com/huggingface/optimum-habana/tree/main/examples/trl)
    • | +| Llama 2 | :heavy_check_mark: | |
  • [PPO Pipeline](https://github.com/huggingface/optimum-habana/tree/main/examples/trl)
    • |
    diff --git a/docs/source/index.mdx b/docs/source/index.mdx index fd394af6ff..ff85c83048 100644 --- a/docs/source/index.mdx +++ b/docs/source/index.mdx @@ -64,11 +64,20 @@ In the tables below, ✅ means single-card, multi-card and DeepSpeed have all be - Diffusers -| Architecture | Training | Inference |
    Tasks
    | -|------------------|:--------:|:---------:|------------------------| +| Architecture | Training | Inference | Tasks | +|------------------|:--------:|:---------:|:------| | Stable Diffusion | |
  • Single card
    • |
  • [text-to-image generation](https://github.com/huggingface/optimum-habana/tree/main/examples/stable-diffusion)
    • | | LDM3D | |
  • Single card
    • |
  • [text-to-image generation](https://github.com/huggingface/optimum-habana/tree/main/examples/stable-diffusion)
    • | + +- TRL: + +| Architecture | Training | Inference | Tasks | +|------------------|:--------:|:--------------------:|:------| +| Llama 2 | ✅ | |
  • [DPO Pipeline](https://github.com/huggingface/optimum-habana/tree/main/examples/trl)
    • | +| Llama 2 | ✅ | |
  • [PPO Pipeline](https://github.com/huggingface/optimum-habana/tree/main/examples/trl)
    • | + + Other models and tasks supported by the 🤗 Transformers and 🤗 Diffusers library may also work. You can refer to this [section](https://github.com/huggingface/optimum-habana#how-to-use-it) for using them with 🤗 Optimum Habana. Besides, [this page](https://github.com/huggingface/optimum-habana/tree/main/examples) explains how to modify any [example](https://github.com/huggingface/transformers/tree/main/examples/pytorch) from the 🤗 Transformers library to make it work with 🤗 Optimum Habana.