Update app.py

app.py

@@ -1,13 +1,20 @@
-import streamlit as st
-from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
+!pip install -qU transformers accelerate
 
-tokenizer = AutoTokenizer.from_pretrained("nakodanei/Blue-Orchid-2x7b")
-model = AutoModelForCausalLM.from_pretrained("nakodanei/Blue-Orchid-2x7b")
+from transformers import AutoTokenizer
+import transformers
+import torch
 
+model = "mlabonne/NeuralBeagle14-7B"
+messages = [{"role": "user", "content": "What is a large language model?"}]
 
-pipe = pipeline('sentiment-analysis')
-text = st.text_area('enter some text!')
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
 
-if text:
-    out = pipe(text)
-    st.json(out)
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])