From 21c13ff3a635237ca6f48b0ef30e72971df6fbb4 Mon Sep 17 00:00:00 2001 From: Thanaji Rao Thakkalapelli Date: Thu, 17 Oct 2024 14:07:51 -0700 Subject: [PATCH] Remove References to torch compile mode in readme (#236) --- README.md | 14 +------------- 1 file changed, 1 insertion(+), 13 deletions(-) diff --git a/README.md b/README.md index 23c0e7879..38b3aa5ae 100644 --- a/README.md +++ b/README.md @@ -58,19 +58,7 @@ To use [🤗 text-generation-inference](https://github.com/huggingface/text-gene --max-total-tokens 2048 ``` - ii. On 1 Gaudi card using PyTorch eager mode with torch compile: - ```bash - model=meta-llama/Llama-2-7b-hf - hf_token=YOUR_ACCESS_TOKEN - volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run - - docker run -p 8080:80 -v $volume:/data --runtime=habana -e HABANA_VISIBLE_DEVICES=all \ - -e PT_HPU_LAZY_MODE=0 -e OMPI_MCA_btl_vader_single_copy_mechanism=none \ - -e HF_TOKEN=$hf_token --cap-add=sys_nice --ipc=host \ - ghcr.io/huggingface/tgi-gaudi:2.0.5 --model-id $model --max-input-tokens 1024 --max-total-tokens 2048 - ``` - - iii. On 8 Gaudi cards: + ii. On 8 Gaudi cards: ```bash model=meta-llama/Llama-2-70b-hf hf_token=YOUR_ACCESS_TOKEN