yusufs/sailor2-3b-chat at main

Ctrl+K

1 contributor

fix(float16): Bfloat16 is only supported on GPUs with compute capability of at least 8.0. Your Tesla T4 GPU has compute capability 7.5. You can use float16 instead by explicitly setting the`dtype` flag in CLI, for example: --dtype=half.

78963b9 9 days ago

.gitignore

19 Bytes

feat(download_model.py): remove download_model.py during build, it causing big image size 5 months ago
Dockerfile

1.38 kB

fix(using sail/Sailor2-3B-Chat): sail/Sailor2-3B-Chat 9 days ago
README.md

1.73 kB

feat(add-model): always download model during build, it will be cached in the consecutive builds 5 months ago
download_model.py

700 Bytes

feat(add-model): always download model during build, it will be cached in the consecutive builds 5 months ago
main.py

6.7 kB

feat(parse): parse output 5 months ago
openai_compatible_api_server.py

24.4 kB

feat(dep_sizes.txt): removes dep_sizes.txt during build, it not needed 5 months ago
poetry.lock

426 kB

feat(refactor): move the files to root 5 months ago
pyproject.toml

416 Bytes

feat(refactor): move the files to root 5 months ago
requirements.txt

9.99 kB

feat(first-commit): follow examples and tutorials 5 months ago
run-llama.sh

1.51 kB

fix(runner.sh): --enforce-eager not support values 3 months ago
run-sailor.sh

1.83 kB

fix(runner.sh): --enforce-eager not support values 3 months ago
runner.sh

2.46 kB

fix(float16): Bfloat16 is only supported on GPUs with compute capability of at least 8.0. Your Tesla T4 GPU has compute capability 7.5. You can use float16 instead by explicitly setting the`dtype` flag in CLI, for example: --dtype=half. 9 days ago