Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fixes for LLM release #227

Merged
merged 3 commits into from
Aug 29, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions setup.py
Original file line number Diff line number Diff line change
Expand Up @@ -79,6 +79,12 @@
"onnx==1.16.0",
"onnxruntime==1.18.0",
"numpy==1.26.4",
"tqdm",
"accelerate",
"py-cpuinfo",
"sentencepiece",
"datasets",
"fastapi",
"uvicorn[standard]",
],
},
Expand Down
4 changes: 2 additions & 2 deletions src/turnkeyml/llm/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -102,9 +102,9 @@ You can also try Phi-3-Mini-128k-Instruct with the following commands:

> Note: no other models or devices are officially supported by `lemonade` on OGA at this time. Contributions appreciated!

## Install Ryzen AI NPU
## Install RyzenAI NPU

To run your LLMs on Ryzen AI NPU, first install and set up the `ryzenai-transformers` conda environment (see instructions [here](https://github.com/amd/RyzenAI-SW/tree/main/example/transformers)). Then, install `lemonade` into `ryzenai-transformers`. The `ryzenai-npu-load` Tool will become available in that environment.
To run your LLMs on RyzenAI NPU, first install and set up the `ryzenai-transformers` conda environment (see instructions [here](https://github.com/amd/RyzenAI-SW/blob/main/example/transformers/models/llm/docs/README.md)). Then, install `lemonade` into `ryzenai-transformers`. The `ryzenai-npu-load` Tool will become available in that environment.

You can try it out with: `lemonade -i meta-llama/Llama-2-7b-chat-hf ryzenai-npu-load --device DEVICE llm-prompt -p "Hello, my thoughts are"`

Expand Down
2 changes: 2 additions & 0 deletions src/turnkeyml/llm/leap.py
Original file line number Diff line number Diff line change
Expand Up @@ -128,6 +128,8 @@ def from_pretrained(
checkpoint != "TheBloke/Llama-2-7b-Chat-fp16"
and checkpoint != "meta-llama/Llama-2-7b-chat-hf"
and checkpoint != "microsoft/Phi-3-mini-4k-instruct"
and checkpoint != "meta-llama/Meta-Llama-3-8B-Instruct"
and checkpoint != "meta-llama/Meta-Llama-3-8B"
):
_raise_not_supported(recipe, checkpoint)

Expand Down
1 change: 1 addition & 0 deletions src/turnkeyml/llm/tools/ort_genai/models/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
This directory is where your OGA model folders go.
2 changes: 1 addition & 1 deletion src/turnkeyml/version.py
Original file line number Diff line number Diff line change
@@ -1 +1 @@
__version__ = "4.0.1"
__version__ = "4.0.2"
Loading