Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Using HF_HOME instead of CACHE to get token read in addition to models. (#2288)

This commit is contained in:
Nicolas Patry 2024-08-09 14:25:44 +02:00 committed by GitHub
parent c6d5039cd7
commit 952b450a3b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Dockerfile
View File

@ -191,7 +191,7 @@ ENV PATH=/opt/conda/bin:$PATH \
CONDA_PREFIX=/opt/conda
# Text Generation Inference base env
ENV HUGGINGFACE_HUB_CACHE=/data \
ENV HF_HOME=/data \
HF_HUB_ENABLE_HF_TRANSFER=1 \
PORT=80

2
Dockerfile_amd
View File

@ -167,7 +167,7 @@ RUN python setup.py build
FROM base AS base-copy
# Text Generation Inference base env
ENV HUGGINGFACE_HUB_CACHE=/data \
ENV HF_HOME=/data \
HF_HUB_ENABLE_HF_TRANSFER=1 \
PORT=80

2
Dockerfile_intel
View File

@ -57,7 +57,7 @@ RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRO
RUN apt-get update && apt install -y intel-basekit xpu-smi cmake python3-dev ninja-build pciutils
# Text Generation Inference base env
ENV HUGGINGFACE_HUB_CACHE=/data \
ENV HF_HOME=/data \
HF_HUB_ENABLE_HF_TRANSFER=1 \
PORT=80