Spaces:
Sleeping
Sleeping
abhaysastha
commited on
c1
Browse files- .gitattributes +35 -35
- Dockerfile +24 -0
- README.md +12 -12
- main.py +48 -0
- requirements.txt +6 -0
.gitattributes
CHANGED
@@ -1,35 +1,35 @@
|
|
1 |
-
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
-
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
-
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
-
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
-
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
-
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
-
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
-
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
-
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
-
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
-
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
-
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
-
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
-
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
-
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
-
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
-
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
-
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
-
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
-
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
-
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
-
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
-
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
-
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
-
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
-
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
-
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
-
*.tar filter=lfs diff=lfs merge=lfs -text
|
29 |
-
*.tflite filter=lfs diff=lfs merge=lfs -text
|
30 |
-
*.tgz filter=lfs diff=lfs merge=lfs -text
|
31 |
-
*.wasm filter=lfs diff=lfs merge=lfs -text
|
32 |
-
*.xz filter=lfs diff=lfs merge=lfs -text
|
33 |
-
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
-
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
-
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
Dockerfile
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Use Python 3.9 as the base image
|
2 |
+
FROM python:3.9
|
3 |
+
|
4 |
+
# Set the working directory inside the container
|
5 |
+
WORKDIR /code
|
6 |
+
|
7 |
+
# Copy requirements file into the container
|
8 |
+
COPY ./requirements.txt /code/requirements.txt
|
9 |
+
|
10 |
+
# Install dependencies
|
11 |
+
RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
|
12 |
+
|
13 |
+
# Add the model download logic here
|
14 |
+
RUN apt-get update && apt-get install -y wget && \
|
15 |
+
wget -O /code/zephyr-7b-beta.Q4_K_S.gguf "https://huggingface.co/TheBloke/zephyr-7B-beta-GGUF/resolve/main/zephyr-7b-beta.Q5_K_S.gguf"
|
16 |
+
|
17 |
+
# Copy the main Python application
|
18 |
+
COPY ./main.py /code/main.py
|
19 |
+
|
20 |
+
# Expose the port for the FastAPI app
|
21 |
+
EXPOSE 7860
|
22 |
+
|
23 |
+
# Command to run the application
|
24 |
+
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]
|
README.md
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
-
---
|
2 |
-
title: Llm
|
3 |
-
emoji: 😻
|
4 |
-
colorFrom: green
|
5 |
-
colorTo: green
|
6 |
-
sdk: docker
|
7 |
-
pinned: false
|
8 |
-
license: mit
|
9 |
-
short_description: llm deployment
|
10 |
-
---
|
11 |
-
|
12 |
-
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
1 |
+
---
|
2 |
+
title: Llm
|
3 |
+
emoji: 😻
|
4 |
+
colorFrom: green
|
5 |
+
colorTo: green
|
6 |
+
sdk: docker
|
7 |
+
pinned: false
|
8 |
+
license: mit
|
9 |
+
short_description: llm deployment
|
10 |
+
---
|
11 |
+
|
12 |
+
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
main.py
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
import requests
|
3 |
+
from ctransformers import AutoModelForCausalLM
|
4 |
+
from fastapi import FastAPI
|
5 |
+
from pydantic import BaseModel
|
6 |
+
|
7 |
+
# Define the public URL for the model file
|
8 |
+
MODEL_URL = "https://huggingface.co/TheBloke/zephyr-7B-beta-GGUF/resolve/main/zephyr-7b-beta.Q5_K_S.gguf"
|
9 |
+
MODEL_PATH = "zephyr-7b-beta.Q4_K_S.gguf"
|
10 |
+
|
11 |
+
# Download the model file if not already present
|
12 |
+
def download_model(model_url, model_path):
|
13 |
+
if not os.path.exists(model_path):
|
14 |
+
print(f"Downloading model from {model_url}...")
|
15 |
+
response = requests.get(model_url, stream=True)
|
16 |
+
with open(model_path, "wb") as f:
|
17 |
+
for chunk in response.iter_content(chunk_size=8192):
|
18 |
+
f.write(chunk)
|
19 |
+
print("Model download complete.")
|
20 |
+
else:
|
21 |
+
print("Model already exists locally.")
|
22 |
+
|
23 |
+
# Ensure the model file is downloaded
|
24 |
+
download_model(MODEL_URL, MODEL_PATH)
|
25 |
+
|
26 |
+
# Load the model
|
27 |
+
llm = AutoModelForCausalLM.from_pretrained(
|
28 |
+
MODEL_PATH,
|
29 |
+
model_type="mistral",
|
30 |
+
max_new_tokens=1096,
|
31 |
+
threads=3,
|
32 |
+
)
|
33 |
+
|
34 |
+
# Pydantic object for request validation
|
35 |
+
class Validation(BaseModel):
|
36 |
+
prompt: str
|
37 |
+
|
38 |
+
# Initialize FastAPI app
|
39 |
+
app = FastAPI()
|
40 |
+
|
41 |
+
# Zephyr completion endpoint
|
42 |
+
@app.post("/llm_on_cpu")
|
43 |
+
async def stream(item: Validation):
|
44 |
+
system_prompt = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.'
|
45 |
+
E_INST = "</s>"
|
46 |
+
user, assistant = "<|user|>", "<|assistant|>"
|
47 |
+
prompt = f"{system_prompt}{E_INST}\n{user}\n{item.prompt.strip()}{E_INST}\n{assistant}\n"
|
48 |
+
return llm(prompt)
|
requirements.txt
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
python-multipart
|
2 |
+
fastapi
|
3 |
+
pydantic
|
4 |
+
uvicorn
|
5 |
+
requests
|
6 |
+
ctransformers
|