|
|
@ -70,13 +70,13 @@ RUN mkdir -p /workspace |
|
|
|
WORKDIR /workspace |
|
|
|
|
|
|
|
#RUN mkdir /workspace && |
|
|
|
RUN --mount=type=cache,target=/root/.cache,sharing=locked pip3 \ |
|
|
|
RUN --mount=type=cache,target=/root/.cache,sharing=locked \ |
|
|
|
cd /workspace && git clone --depth 1 https://github.com/oobabooga/text-generation-webui.git && \ |
|
|
|
cd /workspace/text-generation-webui && pip3 install -r requirements.txt && \ |
|
|
|
cd extensions/api && pip3 install -r requirements.txt |
|
|
|
# pip3 cache purge |
|
|
|
|
|
|
|
RUN --mount=type=cache,target=/root/.cache,sharing=locked pip3 \ |
|
|
|
RUN --mount=type=cache,target=/root/.cache,sharing=locked \ |
|
|
|
cd /workspace/text-generation-webui/ && mkdir repositories && cd repositories && \ |
|
|
|
# https://github.com/oobabooga/GPTQ-for-LLaMa |
|
|
|
# git clone --branch cuda --single-branch https://github.com/qwopqwop200/GPTQ-for-LLaMa.git && \ |
|
|
@ -91,12 +91,15 @@ FROM builder AS modeldownloader |
|
|
|
ARG MODEL_NAME="PygmalionAI/pygmalion-350m" |
|
|
|
ENV MODEL_NAME=${MODEL_NAME} |
|
|
|
|
|
|
|
#RUN cd /workspace/text-generation-webui && python3 download-model.py ${MODEL_NAME} |
|
|
|
RUN cd /workspace/text-generation-webui && python3 download-model.py ${MODEL_NAME} |
|
|
|
#RUN git lfs install && \ |
|
|
|
# git clone --depth 1 https://huggingface.co/${MODEL_NAME} |
|
|
|
RUN wget -P /workspace/text-generation-webui/models/ https://raw.githubusercontent.com/BlinkDL/ChatRWKV/main/v2/20B_tokenizer.json && \ |
|
|
|
wget -P /workspace/text-generation-webui/models/ https://huggingface.co/BlinkDL/rwkv-4-raven/resolve/main/RWKV-4-Raven-7B-v9-Eng99%25-Other1%25-20230412-ctx8192.pth |
|
|
|
|
|
|
|
#RUN wget -P /workspace/text-generation-webui/models/ https://raw.githubusercontent.com/BlinkDL/ChatRWKV/main/v2/20B_tokenizer.json && \ |
|
|
|
# wget -P /workspace/text-generation-webui/models/ https://huggingface.co/BlinkDL/rwkv-4-raven/resolve/main/RWKV-4-Raven-7B-v9-Eng99%25-Other1%25-20230412-ctx8192.pth |
|
|
|
|
|
|
|
#https://huggingface.co/BlinkDL/rwkv-4-pile-7b/resolve/main/RWKV-4-Pile-7B-20230406-ctx8192-test949.pth |
|
|
|
|
|
|
|
#RUN cd /workspace/text-generation-webui && python3 download-model.py MetaIX/GPT4-X-Alpaca-30B-Int4 --text-only && \ |
|
|
|
# wget -P /workspace/text-generation-webui/models/GPT4-X-Alpaca-30B-Int4/ https://huggingface.co/MetaIX/GPT4-X-Alpaca-30B-Int4/resolve/main/gpt4-x-alpaca-30b-4bit.safetensors |
|
|
|
|
|
|
@ -134,8 +137,8 @@ COPY --from=modeldownloader /workspace/text-generation-webui/models /workspace/t |
|
|
|
RUN --mount=type=cache,target=/root/.cache,sharing=locked \ |
|
|
|
cd /workspace/text-generation-webui && pip3 install -r requirements.txt && \ |
|
|
|
(cd extensions/api && pip3 install -r requirements.txt) && \ |
|
|
|
(cd repositories/GPTQ-for-LLaMa && pip3 install -r requirements.txt) && \ |
|
|
|
pip3 install /workspace/text-generation-webui/repositories/GPTQ-for-LLaMa/*.whl |
|
|
|
(cd repositories/GPTQ-for-LLaMa && pip3 install -r requirements.txt) |
|
|
|
# pip3 install /workspace/text-generation-webui/repositories/GPTQ-for-LLaMa/*.whl |
|
|
|
# pip3 cache purge |
|
|
|
|
|
|
|
COPY runpod_infer.py /workspace/ |
|
|
|