Spaces:
Runtime error
Runtime error
Upload 3 files
Browse files- Dockerfile +0 -30
- main.py +7 -3
Dockerfile
CHANGED
@@ -11,33 +11,3 @@ RUN pip install --no-cache-dir --upgrade -r requirements.txt
|
|
11 |
|
12 |
COPY --chown=user . /app
|
13 |
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]
|
14 |
-
|
15 |
-
|
16 |
-
# FROM python:3.9
|
17 |
-
|
18 |
-
# # Set environment variables
|
19 |
-
# ENV MODEL_NAME="meta-llama/Meta-Llama-3-8B-Instruct"
|
20 |
-
# ENV TRANSFORMERS_CACHE="/app/transformers_cache"
|
21 |
-
# ENV LC_ALL=C.UTF-8
|
22 |
-
# ENV LANG=C.UTF-8
|
23 |
-
|
24 |
-
# # Install additional dependencies if needed
|
25 |
-
# RUN pip install --no-cache-dir fastapi uvicorn
|
26 |
-
|
27 |
-
# # Create the app directory and set permissions
|
28 |
-
# RUN mkdir /app && chmod -R 777 /app
|
29 |
-
|
30 |
-
# # Set the working directory
|
31 |
-
# WORKDIR /app
|
32 |
-
|
33 |
-
# # Copy your model and code to the container
|
34 |
-
# COPY ./app.py /app
|
35 |
-
# COPY ./Dockerfile /app
|
36 |
-
# COPY ./requirements.txt /app
|
37 |
-
|
38 |
-
|
39 |
-
# # Expose the port FastAPI will run on
|
40 |
-
# EXPOSE 8000
|
41 |
-
|
42 |
-
# # Run FastAPI server
|
43 |
-
# CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8000"]
|
|
|
11 |
|
12 |
COPY --chown=user . /app
|
13 |
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
main.py
CHANGED
@@ -1,12 +1,16 @@
|
|
1 |
from fastapi import FastAPI, HTTPException
|
2 |
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
|
|
|
3 |
|
4 |
app = FastAPI()
|
5 |
|
6 |
-
#
|
|
|
|
|
|
|
7 |
model_name = "meta-llama/Meta-Llama-3-8B-Instruct"
|
8 |
-
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
9 |
-
model = AutoModelForCausalLM.from_pretrained(model_name)
|
10 |
generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
|
11 |
|
12 |
@app.get("/")
|
|
|
1 |
from fastapi import FastAPI, HTTPException
|
2 |
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
|
3 |
+
import os
|
4 |
|
5 |
app = FastAPI()
|
6 |
|
7 |
+
# Hugging Face authentication token
|
8 |
+
hf_token = os.getenv("HF_TOKEN")
|
9 |
+
|
10 |
+
# Load model and tokenizer with the authentication token
|
11 |
model_name = "meta-llama/Meta-Llama-3-8B-Instruct"
|
12 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=hf_token)
|
13 |
+
model = AutoModelForCausalLM.from_pretrained(model_name, use_auth_token=hf_token)
|
14 |
generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
|
15 |
|
16 |
@app.get("/")
|