1st commit

app.py

@@ -0,0 +1,26 @@
+import gradio as gr
+import huggingface_hub
+import os
+import spaces
+import torch
+
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+@spaces.GPU
+def sentience_check():
+    huggingface_hub.login(token=os.environ["HUGGINGFACE_TOKEN"])
+    device = torch.device("cuda")
+    tokenizer = AutoTokenizer.from_pretrained("debisoft/gemma-2-2B-it-thinking-function_calling-V0")
+    model = AutoModelForCausalLM.from_pretrained("debisoft/gemma-2-2B-it-thinking-function_calling-V0").to(device)
+
+    inputs = tokenizer("Are you sentient?", return_tensors="pt").to(device)
+
+    with torch.no_grad():
+        outputs = model.generate(
+            **inputs, max_new_tokens=128, pad_token_id = tokenizer.eos_token_id
+        )
+
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+demo = gr.Interface(fn=sentience_check, inputs=None, outputs=gr.Text())
+demo.launch()

requirements.txt

@@ -0,0 +1,2 @@
+huggingface_hub==0.24.5
+transformers==4.43.4