Create app.py

app.py

@@ -0,0 +1,27 @@
+import gradio as gr
+import os
+os.system("pip install torch sentencepiece transformers Xformers")
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("cyberagent/open-calm-1b", device_map="auto", torch_dtype=torch.float16)
+tokenizer = AutoTokenizer.from_pretrained("cyberagent/open-calm-1b")
+
+def generate_text(prompt, max_new_tokens, do_sample, temperature, top_p, repetition_penalty, pad_token_id):
+  inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+  with torch.no_grad():
+    tokens = model.generate(
+        **inputs,
+        max_new_tokens=max_new_tokens,
+        do_sample=do_sample,
+        temperature=temperature,
+        top_p=top_p,
+        repetition_penalty=repetition_penalty,
+        pad_token_id=pad_token_id,
+    )
+    
+  output = tokenizer.decode(tokens[0], skip_special_tokens=True)
+  return output
+
+app = gr.Interface(generate_text, inputs=[gr.Input(label="Prompt", type="text"), gr.IntSlider(label="Max new tokens", min=1, max=1024, step=1), gr.Checkbox(label="Do sample"), gr.FloatSlider(label="Temperature", min=0.1, max=1.0, step=0.1), gr.FloatSlider(label="Top P", min=0.0, max=1.0, step=0.01), gr.FloatSlider(label="Repetition penalty", min=0.0, max=2.0, step=0.1), gr.IntSlider(label="Pad token ID", min=0, max=1023, step=1)], outputs=[gr.Output(label="Output", type="text")])
+app.launch()