add minitron 8B base

app.py

@@ -1,7 +1,43 @@
-import gradio as gr
+import gradio as gr  
+import torch  
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
-def greet(name):
-    return "Hello " + name + "!!"
+title = """# 🙋🏻‍♂️ Welcome to Tonic's Minitron-8B-Base"""
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
-demo.launch()
+# Load the tokenizer and model
+model_path = "nvidia/Minitron-8B-Base"
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+
+device='cuda'
+dtype=torch.bfloat16
+model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype=dtype, device_map=device)
+
+# Define the prompt format  
+def create_prompt(instruction):  
+    PROMPT = '''You are TronTonic an AI created by Tonic-AI. Below is an instruction that describes a task.\n\nWrite a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response:'''  
+    return PROMPT.format(instruction=instruction)  
+  
+def respond(message, history, system_message, max_tokens, temperature, top_p):  
+    prompt = create_prompt(message)  
+      
+    input_ids = tokenizer.encode(prompt, return_tensors="pt").to(model.device)
+
+    output_ids = model.generate(input_ids, max_length=50, num_return_sequences=1)
+
+    output_text = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+      
+    return output_text  
+  
+demo = gr.ChatInterface(
+    gr.markdown(title),
+    # gr.markdown(description),
+    respond,  
+    additional_inputs=[  
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),  
+        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),  
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)")  
+    ],  
+)  
+  
+if __name__ == "__main__":  
+    demo.launch()  

transformers

@@ -0,0 +1 @@
+Subproject commit 63d9cb0afd2bf5d4cb5431ba1b2c4e353752a937