update

app.py

@@ -0,0 +1,25 @@
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# Load model and tokenizer
+model_id = "prasenjeethowlader099/zetallm_4"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda" if torch.cuda.is_available() else "cpu")
+
+# Chat function
+def chat(prompt, history=[]):
+    input_ids = tokenizer.encode(prompt, return_tensors="pt").to(model.device)
+    output = model.generate(input_ids, max_new_tokens=200, do_sample=True, top_k=50, top_p=0.95, temperature=0.7)
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
+    return response
+
+# Gradio UI
+gr.Interface(
+    fn=chat,
+    inputs=gr.Textbox(lines=5, label="Ask Zeeta"),
+    outputs=gr.Textbox(label="Zeeta's Response"),
+    title="CodeAgent Zeeta LLM",
+    description="Chat with prasenjeethowlader099/zetallm_4"
+).launch()

requirements.txt

@@ -0,0 +1,3 @@
+transformers
+torch
+gradio