Commit
·
f2ed886
1
Parent(s):
048f2d2
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,14 +4,14 @@ license: apache-2.0
|
|
| 4 |
|
| 5 |
<center>
|
| 6 |
<h3>Welcome to llawa</h3>
|
| 7 |
-
|
| 8 |
-
|
| 9 |
</center>
|
| 10 |
|
| 11 |
|
| 12 |
The models in this repo are Llama2 7b chat models further fine-tuned with Wasm-related Q&As.
|
| 13 |
Instead of struggling with Python and PyTorch, the simplest way to run them on your own laptops, servers, or edge devices is to use the [WasmEdge Runtime](https://github.com/WasmEdge/WasmEdge).
|
| 14 |
-
|
| 15 |
|
| 16 |
1. Install WasmEdge
|
| 17 |
|
|
|
|
| 4 |
|
| 5 |
<center>
|
| 6 |
<h3>Welcome to llawa</h3>
|
| 7 |
+
<img src="https://huggingface.co/juntaoyuan/llawa/resolve/main/llawa-logo.png"/>
|
| 8 |
+
<br/><i>a.k.a Llama2 + Wasm QA</i>
|
| 9 |
</center>
|
| 10 |
|
| 11 |
|
| 12 |
The models in this repo are Llama2 7b chat models further fine-tuned with Wasm-related Q&As.
|
| 13 |
Instead of struggling with Python and PyTorch, the simplest way to run them on your own laptops, servers, or edge devices is to use the [WasmEdge Runtime](https://github.com/WasmEdge/WasmEdge).
|
| 14 |
+
Learn more about this [fast, lightweight, portable, and ZERO Python dependency approach](https://medium.com/stackademic/fast-and-portable-llama2-inference-on-the-heterogeneous-edge-a62508e82359) for running AI applications!
|
| 15 |
|
| 16 |
1. Install WasmEdge
|
| 17 |
|