-
Notifications
You must be signed in to change notification settings - Fork 115
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #255 from rhatdan/bootc
Improve model_server Makefile.
- Loading branch information
Showing
2 changed files
with
12 additions
and
6 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,9 +1,15 @@ | ||
#https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/resolve/main/llama-2-7b-chat.Q5_K_S.gguf | ||
#https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q4_K_M.gguf | ||
#https://huggingface.co/TheBloke/CodeLlama-7B-Instruct-GGUF/resolve/main/codellama-7b-instruct.Q4_K_M.gguf | ||
#https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-small.bin | ||
# Suggested alternative open AI Models | ||
# https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/resolve/main/llama-2-7b-chat.Q5_K_S.gguf | ||
# https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q4_K_M.gguf (Default) | ||
# https://huggingface.co/TheBloke/CodeLlama-7B-Instruct-GGUF/resolve/main/codellama-7b-instruct.Q4_K_M.gguf | ||
# https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-small.bin | ||
# podman build --build-arg MODEL_URL=https://... -t quay.io/yourimage . | ||
# | ||
FROM registry.access.redhat.com/ubi9/ubi-micro:9.3-13 | ||
|
||
# Can be substituted using the --build-arg defined above | ||
ARG MODEL_URL=https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q4_K_M.gguf | ||
|
||
# By default the Model Server container image uses the AI Model stored in the model/model.file file. | ||
WORKDIR /model | ||
ADD $MODEL_URL /model/model.file |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,6 +1,6 @@ | ||
MODEL ?= MODEL=https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q4_K_M.gguf | ||
MODEL ?= https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q4_K_M.gguf | ||
IMAGE ?= quay.io/ai-lab/llama:latest | ||
|
||
.PHONY: build | ||
build: | ||
podman build --build-arg ${MODEL} -f Containerfile -t ${IMAGE} . | ||
podman build $${MODEL:+--build-arg MODEL=$${MODEL}} -f Containerfile -t ${IMAGE} . |