Upload 2 files
Browse files- app.py +39 -0
- requirements.txt +3 -0
app.py
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
|
3 |
+
import torch
|
4 |
+
|
5 |
+
# Load your model and tokenizer using the adapter weights
|
6 |
+
model_name = "mherrador/CE-5.0" # Replace with your actual model name
|
7 |
+
bnb_config = BitsAndBytesConfig(
|
8 |
+
load_in_4bit=True,
|
9 |
+
bnb_4bit_use_double_quant=True,
|
10 |
+
bnb_4bit_quant_type="nf4",
|
11 |
+
bnb_4bit_compute_dtype=torch.bfloat16,
|
12 |
+
)
|
13 |
+
|
14 |
+
model = AutoModelForCausalLM.from_pretrained(
|
15 |
+
model_name,
|
16 |
+
quantization_config=bnb_config,
|
17 |
+
device_map="auto",
|
18 |
+
trust_remote_code=True,
|
19 |
+
)
|
20 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
21 |
+
|
22 |
+
# Function to generate recommendations
|
23 |
+
def generate_recommendations(input_text):
|
24 |
+
inputs = tokenizer(input_text, return_tensors="pt").to("cuda")
|
25 |
+
outputs = model.generate(**inputs, max_new_tokens=128)
|
26 |
+
recommendations = tokenizer.batch_decode(outputs)[0]
|
27 |
+
return recommendations
|
28 |
+
|
29 |
+
# Create the Gradio interface
|
30 |
+
iface = gr.Interface(
|
31 |
+
fn=generate_recommendations,
|
32 |
+
inputs=gr.Textbox(lines=5, placeholder="Enter your questions here..."),
|
33 |
+
outputs=gr.Textbox(lines=10),
|
34 |
+
title="Circular Economy Recommender",
|
35 |
+
description="Enter your questions about circular economy practices to get recommendations.",
|
36 |
+
)
|
37 |
+
|
38 |
+
# Launch the interface
|
39 |
+
iface.launch()
|
requirements.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
gradio
|
2 |
+
unsloth
|
3 |
+
torch
|