Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -1,9 +1,14 @@
|
|
1 |
import gradio as gr
|
2 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
3 |
|
|
|
4 |
model_name = "QuantFactory/Meta-Llama-3-8B-Instruct-GGUF"
|
5 |
-
|
6 |
-
|
|
|
|
|
|
|
|
|
7 |
|
8 |
def generate_response(prompt):
|
9 |
inputs = tokenizer(prompt, return_tensors="pt")
|
@@ -13,3 +18,4 @@ def generate_response(prompt):
|
|
13 |
|
14 |
interface = gr.Interface(fn=generate_response, inputs="text", outputs="text")
|
15 |
interface.launch()
|
|
|
|
1 |
import gradio as gr
|
2 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
3 |
|
4 |
+
# Ensure the correct model path
|
5 |
model_name = "QuantFactory/Meta-Llama-3-8B-Instruct-GGUF"
|
6 |
+
|
7 |
+
try:
|
8 |
+
model = AutoModelForCausalLM.from_pretrained(model_name)
|
9 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
10 |
+
except OSError as e:
|
11 |
+
print(f"Error loading the model: {e}")
|
12 |
|
13 |
def generate_response(prompt):
|
14 |
inputs = tokenizer(prompt, return_tensors="pt")
|
|
|
18 |
|
19 |
interface = gr.Interface(fn=generate_response, inputs="text", outputs="text")
|
20 |
interface.launch()
|
21 |
+
|