|
|
@@ -1,6 +1,17 @@
|
|
|
# Llama 2 Fine-tuning / Inference Recipes and Examples
|
|
|
|
|
|
-**[Update Oct. 20, 2023] We just released a series of Llama 2 demo apps [here](./demo_apps), showing how to run Llama 2 both locally or in the cloud, to chat about data (PDF, DB, or live) and get video summary.**
|
|
|
+**[Update Oct. 20, 2023]**
|
|
|
+
|
|
|
+**We have just released a series of Llama 2 demo apps [here](./demo_apps).**
|
|
|
+
|
|
|
+**These examples show how to:**
|
|
|
+- **Run Llama 2 locally and in the cloud**
|
|
|
+- **Augment the Llama 2 models knowledge using information from:**
|
|
|
+ - **PDF documents**
|
|
|
+ - **a database**
|
|
|
+ - **live data**
|
|
|
+ - **video transcript**
|
|
|
+
|
|
|
|
|
|
The 'llama-recipes' repository is a companion to the [Llama 2 model](https://github.com/facebookresearch/llama). The goal of this repository is to provide examples to quickly get started with fine-tuning for domain adaptation and how to run inference for the fine-tuned models. For ease of use, the examples use Hugging Face converted versions of the models. See steps for conversion of the model [here](#model-conversion-to-hugging-face).
|
|
|
|
sekyonda