Commit
·
7652cb7
1
Parent(s):
28ee0f2
feat: converted readme.md to index.html
Browse files- Dockerfile +1 -1
- README.md +1 -9
- index.html +30 -3
- main.py +5 -5
Dockerfile
CHANGED
|
@@ -19,7 +19,7 @@ RUN mkdir model && \
|
|
| 19 |
|
| 20 |
COPY ./start_server.sh ./
|
| 21 |
COPY ./main.py ./
|
| 22 |
-
COPY ./
|
| 23 |
|
| 24 |
# Make the server start script executable
|
| 25 |
RUN chmod +x ./start_server.sh
|
|
|
|
| 19 |
|
| 20 |
COPY ./start_server.sh ./
|
| 21 |
COPY ./main.py ./
|
| 22 |
+
COPY ./index.html ./
|
| 23 |
|
| 24 |
# Make the server start script executable
|
| 25 |
RUN chmod +x ./start_server.sh
|
README.md
CHANGED
|
@@ -3,7 +3,6 @@ title: orca_mini_v3_13B-GGML (q5_K_S)
|
|
| 3 |
colorFrom: purple
|
| 4 |
colorTo: blue
|
| 5 |
sdk: docker
|
| 6 |
-
app_file: index.html
|
| 7 |
models:
|
| 8 |
- TheBloke/orca_mini_v3_13B-GGML
|
| 9 |
tags:
|
|
@@ -17,11 +16,4 @@ pinned: false
|
|
| 17 |
|
| 18 |
# orca_mini_v3_13B-GGML (q5_K_S)
|
| 19 |
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
- The API endpoint:
|
| 23 |
-
https://limcheekin-orca-mini-v3-13b-ggml.hf.space/v1
|
| 24 |
-
- The API doc:
|
| 25 |
-
https://limcheekin-orca-mini-v3-13b-ggml.hf.space/docs
|
| 26 |
-
|
| 27 |
-
If you find this resource valuable, your support in the form of starring the space would be greatly appreciated. Your engagement plays a vital role in furthering the application for a community GPU grant, ultimately enhancing the capabilities and accessibility of this space.
|
|
|
|
| 3 |
colorFrom: purple
|
| 4 |
colorTo: blue
|
| 5 |
sdk: docker
|
|
|
|
| 6 |
models:
|
| 7 |
- TheBloke/orca_mini_v3_13B-GGML
|
| 8 |
tags:
|
|
|
|
| 16 |
|
| 17 |
# orca_mini_v3_13B-GGML (q5_K_S)
|
| 18 |
|
| 19 |
+
Please refer to the [index.html](index.html) for more information.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
index.html
CHANGED
|
@@ -1,10 +1,37 @@
|
|
| 1 |
<!DOCTYPE html>
|
| 2 |
<html>
|
| 3 |
<head>
|
| 4 |
-
<title>
|
| 5 |
</head>
|
| 6 |
<body>
|
| 7 |
-
<h1>
|
| 8 |
-
<p>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
</body>
|
| 10 |
</html>
|
|
|
|
| 1 |
<!DOCTYPE html>
|
| 2 |
<html>
|
| 3 |
<head>
|
| 4 |
+
<title>orca_mini_v3_13B-GGML (q5_K_S)</title>
|
| 5 |
</head>
|
| 6 |
<body>
|
| 7 |
+
<h1>orca_mini_v3_13B-GGML (q5_K_S)</h1>
|
| 8 |
+
<p>
|
| 9 |
+
With the utilization of the
|
| 10 |
+
<a href="https://github.com/abetlen/llama-cpp-python">llama-cpp-python</a>
|
| 11 |
+
package, we are excited to introduce the GGML model hosted in the Hugging
|
| 12 |
+
Face Docker Spaces, made accessible through an OpenAI-compatible API. This
|
| 13 |
+
space includes comprehensive API documentation to facilitate seamless
|
| 14 |
+
integration.
|
| 15 |
+
</p>
|
| 16 |
+
<ul>
|
| 17 |
+
<li>
|
| 18 |
+
The API endpoint:
|
| 19 |
+
<a href="https://limcheekin-orca-mini-v3-13b-ggml.hf.space/v1"
|
| 20 |
+
>https://limcheekin-orca-mini-v3-13b-ggml.hf.space/v1</a
|
| 21 |
+
>
|
| 22 |
+
</li>
|
| 23 |
+
<li>
|
| 24 |
+
The API doc:
|
| 25 |
+
<a href="https://limcheekin-orca-mini-v3-13b-ggml.hf.space/docs"
|
| 26 |
+
>https://limcheekin-orca-mini-v3-13b-ggml.hf.space/docs</a
|
| 27 |
+
>
|
| 28 |
+
</li>
|
| 29 |
+
</ul>
|
| 30 |
+
<p>
|
| 31 |
+
If you find this resource valuable, your support in the form of starring
|
| 32 |
+
the space would be greatly appreciated. Your engagement plays a vital role
|
| 33 |
+
in furthering the application for a community GPU grant, ultimately
|
| 34 |
+
enhancing the capabilities and accessibility of this space.
|
| 35 |
+
</p>
|
| 36 |
</body>
|
| 37 |
</html>
|
main.py
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
from llama_cpp.server.app import create_app, Settings
|
| 2 |
-
# from fastapi.staticfiles import StaticFiles
|
| 3 |
from fastapi.responses import HTMLResponse
|
| 4 |
import os
|
| 5 |
|
|
@@ -12,15 +11,16 @@ app = create_app(
|
|
| 12 |
)
|
| 13 |
)
|
| 14 |
|
| 15 |
-
# app.mount("/static", StaticFiles(directory="static"), name="static")
|
| 16 |
-
|
| 17 |
|
| 18 |
@app.get("/", response_class=HTMLResponse)
|
| 19 |
async def read_items():
|
| 20 |
-
with open("
|
| 21 |
content = f.read()
|
| 22 |
return content
|
| 23 |
|
| 24 |
if __name__ == "__main__":
|
| 25 |
import uvicorn
|
| 26 |
-
uvicorn.run(app,
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
from llama_cpp.server.app import create_app, Settings
|
|
|
|
| 2 |
from fastapi.responses import HTMLResponse
|
| 3 |
import os
|
| 4 |
|
|
|
|
| 11 |
)
|
| 12 |
)
|
| 13 |
|
|
|
|
|
|
|
| 14 |
|
| 15 |
@app.get("/", response_class=HTMLResponse)
|
| 16 |
async def read_items():
|
| 17 |
+
with open("index.html", "r") as f:
|
| 18 |
content = f.read()
|
| 19 |
return content
|
| 20 |
|
| 21 |
if __name__ == "__main__":
|
| 22 |
import uvicorn
|
| 23 |
+
uvicorn.run(app,
|
| 24 |
+
host=os.environ["HOST"],
|
| 25 |
+
port=int(os.environ["PORT"])
|
| 26 |
+
)
|