Sign inSign up

secondstate/qwen-2-0.5b-allminilm-2:cuda12

Multi-platform
Machine learning & AI
Developer tools
Index digest

sha256:b6fd3a9fd893a2a61c0dba90f2b7a1d059148a4149ffd75454c600a27d419b45

OS/ARCH

Compressed size

991.04 MB

Last pushed

over 2 years by juntaoyuan

Type

Image

Manifest digest

sha256:92ea59aaef724f5b1fa12617563eb7cf53b4c9a9a94aa21d3b50c8483d73364b

Image Layers

Image Layers

1ARG RELEASE0 B
2ARG LAUNCHPAD_BUILD_ARCH0 B
3LABEL org.opencontainers.image.ref.name=ubuntu0 B
4LABEL org.opencontainers.image.version=22.040 B
5ADD file ... in / 28.17 MB
6CMD ["/bin/bash"]0 B
7ENV NVARCH=x86_640 B
8ENV NVIDIA_REQUIRE_CUDA=cuda>=12.5 brand=unknown,driver>=470,driver<471 brand=grid,driver>=470,driver<471 brand=tesla,driver>=470,driver<4710 B
9ENV NV_CUDA_CUDART_VERSION=12.5.39-10 B
10ENV NV_CUDA_COMPAT_PACKAGE=cuda-compat-12-50 B
11ARG TARGETARCH0 B
12LABEL maintainer=NVIDIA CORPORATION <[email protected]>0 B
13RUN |1 TARGETARCH=amd64 /bin/sh -c4.41 MB
14ENV CUDA_VERSION=12.5.00 B
15RUN |1 TARGETARCH=amd64 /bin/sh -c53.33 MB
16RUN |1 TARGETARCH=amd64 /bin/sh -c183 B
17ENV PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin0 B
18ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib640 B
19COPY NGC-DL-CONTAINER-LICENSE / # buildkit6.72 KB
20ENV NVIDIA_VISIBLE_DEVICES=all0 B
21ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility0 B
22ARG CHAT_MODEL_FILE0 B
23ARG EMBEDDING_MODEL_FILE0 B
24ARG PROMPT_TEMPLATE0 B
25ENV CHAT_MODEL_FILE=Qwen2-0.5B-Instruct-Q5_K_M.gguf0 B
26ENV EMBEDDING_MODEL_FILE=all-MiniLM-L6-v2-ggml-model-f16.gguf0 B
27ENV PROMPT_TEMPLATE=chatml0 B
28RUN |3 CHAT_MODEL_FILE=Qwen2-0.5B-Instruct-Q5_K_M.gguf EMBEDDING_MODEL_FILE=all-MiniLM-L6-v2-ggml-model-f16.gguf PROMPT_TEMPLATE=chatml385.5 MB
29RUN |3 CHAT_MODEL_FILE=Qwen2-0.5B-Instruct-Q5_K_M.gguf EMBEDDING_MODEL_FILE=all-MiniLM-L6-v2-ggml-model-f16.gguf PROMPT_TEMPLATE=chatml96 B
30COPY Qwen2-0.5B-Instruct-Q5_K_M.gguf /models/Qwen2-0.5B-Instruct-Q5_K_M.gguf # buildkit388.25 MB
31COPY all-MiniLM-L6-v2-ggml-model-f16.gguf /models/all-MiniLM-L6-v2-ggml-model-f16.gguf # buildkit39.93 MB
32RUN |3 CHAT_MODEL_FILE=Qwen2-0.5B-Instruct-Q5_K_M.gguf EMBEDDING_MODEL_FILE=all-MiniLM-L6-v2-ggml-model-f16.gguf PROMPT_TEMPLATE=chatml87.05 MB
33RUN |3 CHAT_MODEL_FILE=Qwen2-0.5B-Instruct-Q5_K_M.gguf EMBEDDING_MODEL_FILE=all-MiniLM-L6-v2-ggml-model-f16.gguf PROMPT_TEMPLATE=chatml2.71 MB
34RUN |3 CHAT_MODEL_FILE=Qwen2-0.5B-Instruct-Q5_K_M.gguf EMBEDDING_MODEL_FILE=all-MiniLM-L6-v2-ggml-model-f16.gguf PROMPT_TEMPLATE=chatml1.68 MB
35COPY run.sh . # buildkit373 B
36RUN |3 CHAT_MODEL_FILE=Qwen2-0.5B-Instruct-Q5_K_M.gguf EMBEDDING_MODEL_FILE=all-MiniLM-L6-v2-ggml-model-f16.gguf PROMPT_TEMPLATE=chatml374 B
37ENTRYPOINT ["/bin/sh" "-c" "./run.sh $CHAT_MODEL_FILE0 B

Command

 ARG RELEASE