Create app.py

app.py

@@ -0,0 +1,21 @@
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model_name = "Guavacoderepo/gclm-3b-pidgin"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    device_map="auto",
+    load_in_4bit=True,
+    bnb_4bit_compute_dtype=torch.float16
+)
+
+def chat_fn(user_input):
+    prompt = f"User: {user_input}\nAssistant:"
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    outputs = model.generate(**inputs, max_new_tokens=150)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+iface = gr.Interface(fn=chat_fn, inputs="text", outputs="text", title="GCLM-3B-Pidgin Chat")
+iface.launch()