Add files

app.py

@@ -0,0 +1,46 @@
+import transformers
+import streamlit as st
+
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("VietAI/gpt-neo-1.3B-vietnamese-news")
+@st.cache
+def load_model(model_name):
+    model = AutoModelForCausalLM.from_pretrained(model_name)
+    return model
+
+model = load_model("VietAI/gpt-neo-1.3B-vietnamese-news")
+def infer(input_ids, max_length):
+
+    output_sequences = model.generate(
+        input_ids=input_ids,
+        max_length=max_length,
+        do_sample=True,
+        temperature=0.9,
+        top_k=20,
+        #top_p=top_p,
+        #num_return_sequences=1
+    )
+
+    return output_sequences
+
+default_value = "Have fun!"
+
+st.title("Write with Transformers 🦄")
+st.write("Generate Vietnamese text from a given prompt")
+
+sent = st.text_area("Text", default_value, height = 275)
+max_length = st.sidebar.slider("Max Length", min_value = 10, max_value=30)
+#temperature = st.sidebar.slider("Temperature", value = 1.0, min_value = 0.0, max_value=1.0, step=0.05)
+#top_k = st.sidebar.slider("Top-k", min_value = 0, max_value=5, value = 0)
+#top_p = st.sidebar.slider("Top-p", min_value = 0.0, max_value=1.0, step = 0.05, value = 0.9)
+
+encoded_prompt = tokenizer.encode(sent, add_special_tokens=False, return_tensors="pt")
+if encoded_prompt.size()[-1] == 0:
+    input_ids = None
+else:
+    input_ids = encoded_prompt
+
+gen_tokens = infer(encoded_prompt, max_length)
+gen_text = tokenizer.batch_decode(gen_tokens)[0]
+st.write(gen_text)

requirements.txt

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