phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-02 08:44:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Approach #2

Browse source
This commit is contained in:
Aidan Do 2024-12-16 11:47:45 +11:00
parent 20383bfea5
commit 86820d13cd
2 changed files with 26 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

22
COMMANDS.md Normal file
View file

@ -0,0 +1,22 @@
```bash
source ~/miniconda3/bin/activate
conda create --prefix ./envs python=3.10
source ~/miniconda3/bin/activate
conda activate ./envs
pip install -e . \
&& llama stack build --config ./build.yaml --image-type conda \
&& llama stack run ./run.yaml \
--port 5001
pytest llama_stack/providers/tests/inference/test_text_inference.py -v -k groq --lf -s
trash .git/hooks/pre-commit
llama stack build --template ollama --image-type conda \
&& llama stack run ./distributions/ollama/run.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env OLLAMA_URL=http://localhost:11434
```

8
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -48,10 +48,10 @@ model_aliases = [
"llama3.1:8b-instruct-fp16",
CoreModelId.llama3_1_8b_instruct.value,
),
build_model_alias_with_just_provider_model_id(
"llama3.1:8b",
CoreModelId.llama3_1_8b_instruct.value,
),
# build_model_alias_with_just_provider_model_id(
# "llama3.1:8b",
# CoreModelId.llama3_1_8b_instruct.value,
# ),
build_model_alias(
"llama3.1:70b-instruct-fp16",
CoreModelId.llama3_1_70b_instruct.value,