add GPT2 and 3.1

app.py

@@ -20,12 +20,18 @@ hf_hub_download(
     local_dir="./models"
 )
 
-#hf_hub_download(
-#    repo_id="TobDeBer/Meta-Llama-3.1-8B-Instruct-Q4_K_M-GGUF",
-#    filename="meta-llama-3.1-8b-instruct-q4_k_m.gguf",
-#    local_dir="./models",
-#    token=huggingface_token
-#)
+hf_hub_download(
+    repo_id="TobDeBer/gpt2-Q4_K_M-GGUF",
+    filename="gpt2-q4_k_m.gguf",
+    local_dir="./models"
+)
+
+hf_hub_download(
+    repo_id="TobDeBer/Meta-Llama-3.1-8B-Instruct-Q4_K_M-GGUF",
+    filename="meta-llama-3.1-8b-instruct-q4_k_m.gguf",
+    local_dir="./models",
+    token=huggingface_token
+)
 
 # TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF
 # granite-8b-code-instruct-128k-q4_k_m.gguf
@@ -103,15 +109,17 @@ def respond(
         outputs += output
         yield outputs
 
-description = """<p align="center">Defaults Qwen 500M</p>
+description = """<p align="center">Defaults to Qwen 500M</p>
+More models in Advanced Section <br>
 """
 
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
         gr.Dropdown([
+                'qwen2-0_5b-instruct-q4_k_m.gguf',
+				'gpt2-q4_k_m.gguf',
                 'meta-llama-3.1-8b-instruct-q4_k_m.gguf',
-                'qwen2-0_5b-instruct-q4_k_m.gguf'
             ],
             value="qwen2-0_5b-instruct-q4_k_m.gguf",
             label="Model"