Add timing on readme, remove useless line in dockerfile.
This commit is contained in:
parent
191d92c940
commit
a93cf1264a
|
|
@ -63,7 +63,6 @@ RUN cd text-generation-webui-tmp && python download-model.py samwit/alpaca7b-lor
|
|||
|
||||
COPY *.py .
|
||||
COPY text-generation-webui text-generation-webui
|
||||
RUN ls -l
|
||||
COPY monkeypatch .
|
||||
|
||||
RUN mv -f text-generation-webui-tmp/* text-generation-webui/
|
||||
|
|
|
|||
|
|
@ -5,7 +5,7 @@ Made some adjust for the code in peft and gptq for llama, and make it possible f
|
|||
|
||||
```
|
||||
git clone https://github.com/andybarry/alpaca_lora_4bit_docker.git
|
||||
DOCCKER_BUILDKIT=1 docker build -t alpaca_lora_4bit .
|
||||
DOCCKER_BUILDKIT=1 docker build -t alpaca_lora_4bit . # build step can take 12 min
|
||||
docker run --gpus=all -p 7860:7860 alpaca_lora_4bit
|
||||
```
|
||||
Point your browser to http://localhost:7860
|
||||
|
|
|
|||
Loading…
Reference in New Issue