Update app.py
Browse files
app.py
CHANGED
@@ -108,6 +108,17 @@ def generate_response(query, history, model, temperature, max_tokens, top_p, see
|
|
108 |
return response
|
109 |
|
110 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
111 |
|
112 |
additional_inputs = [
|
113 |
gr.Dropdown(choices=["llama-3.3-70b-versatile", "llama-3.1-8b-instant", "llama3-70b-8192", "llama3-8b-8192", "mixtral-8x7b-32768", "gemma2-9b-it"], value="gemma2-9b-it", label="Model"),
|
|
|
108 |
return response
|
109 |
|
110 |
|
111 |
+
# gr.Markdown("""
|
112 |
+
# ### 1. Attention Is All You Need (Vaswani et al., 2017)
|
113 |
+
# This groundbreaking paper introduced the **Transformer** architecture. It revolutionized natural language processing by enabling parallelization and significantly improving performance on tasks like translation, leading to models like *BERT* and *GPT*.
|
114 |
+
|
115 |
+
# ### 2. Generative Adversarial Nets (Goodfellow et al., 2014)
|
116 |
+
# This paper proposed **GANs**, a novel framework for generative modeling using two neural networks—a generator and a discriminator—that compete in a zero-sum game.
|
117 |
+
|
118 |
+
# ### 3. Parameter-Efficient Transfer Learning for NLP (Houlsby et al., 2019)
|
119 |
+
# This paper introduces **adapter modules**, a method for fine-tuning large pre-trained language models with significantly fewer parameters.
|
120 |
+
# """)
|
121 |
+
|
122 |
|
123 |
additional_inputs = [
|
124 |
gr.Dropdown(choices=["llama-3.3-70b-versatile", "llama-3.1-8b-instant", "llama3-70b-8192", "llama3-8b-8192", "mixtral-8x7b-32768", "gemma2-9b-it"], value="gemma2-9b-it", label="Model"),
|