Fixes for LLM release (#227)

* Fix various bugs from the initial release

* Add models folder marker

* fix for leap

setup.py

@@ -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]",
         ],
     },

src/turnkeyml/llm/README.md

@@ -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"`
 

src/turnkeyml/llm/leap.py

@@ -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)
 

src/turnkeyml/llm/tools/ort_genai/models/README.md

@@ -0,0 +1 @@
+This directory is where your OGA model folders go.

src/turnkeyml/version.py

@@ -1 +1 @@
-__version__ = "4.0.1"
+__version__ = "4.0.2"