Update app.py

app.py

@@ -2,15 +2,19 @@ import spaces
 import json
 import subprocess
 import gradio as gr
-from huggingface_hub import hf_hub_download
+from huggingface_hub import hf_hub_download, snapshot_download
+import os
 
 subprocess.run('pip install llama-cpp-python==0.2.75 --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu124', shell=True)
 subprocess.run('pip install llama-cpp-agent==0.2.10', shell=True)
 
-download_gguf_model = hf_hub_download(repo_id="bartowski/Einstein-v6.1-Llama3-8B-GGUF", filename="Einstein-v6.1-Llama3-8B-Q6_K.gguf",  local_dir = "./models")
-#hf_hub_download(repo_id="crusoeai/dolphin-2.9.1-llama-3-70b-GGUF", filename="dolphin-2.9.1-llama-3-70b.Q3_K_M.gguf",  local_dir = "./models")
-# hf_hub_download(repo_id="bartowski/dolphin-2.9.1-yi-1.5-9b-GGUF", filename="dolphin-2.9.1-yi-1.5-9b-f32.gguf",  local_dir = "./models")
-# hf_hub_download(repo_id="crusoeai/dolphin-2.9.1-llama-3-8b-GGUF", filename="dolphin-2.9.1-llama-3-8b.Q6_K.gguf",  local_dir = "./models")
+####
+space_link = "https://huggingface.co/spaces/Weyaxi/chat"
+gguf_model_id = "bartowski/Einstein-v6.1-Llama3-8B-GGUF"
+###
+
+
+download_gguf_model_dir = snapshot_download(repo_id=gguf_model_id, allow_patterns=["*Q6_K.gguf"],  local_dir = "./models")
 
 css = """
 .message-row {
@@ -30,10 +34,10 @@ css = """
 }
 """
 
-PLACEHOLDER = """
+PLACEHOLDER = f"""
 <div class="message-bubble-border" style="display:flex; max-width: 600px; border-radius: 8px; box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1); backdrop-filter: blur(10px);">
     <figure style="margin: 0;">
-        <img src="https://huggingface.co/spaces/Weyaxi/chat/resolve/main/dolphin.gif" alt="Logo" style="width: 100%; height: 100%; border-radius: 8px;">
+        <img src="{space_link}/resolve/main/dolphin.gif" alt="Logo" style="width: 100%; height: 100%; border-radius: 8px;">
     </figure>
     <div style="padding: .5rem 1.5rem;">
         <h2 style="text-align: left; font-size: 1.5rem; font-weight: 700; margin-bottom: 0.5rem;">Cognitive Computations</h2>
@@ -73,9 +77,7 @@ def respond(
     from llama_cpp_agent.providers import LlamaCppPythonProvider
     from llama_cpp_agent.chat_history import BasicChatHistory
     from llama_cpp_agent.chat_history.messages import Roles
-    print(message)
-    print(history)
-    
+
     llm = Llama(
         model_path=f"models/{model}",
         flash_attn=True,
@@ -88,7 +90,7 @@ def respond(
 
     agent = LlamaCppAgent(
         provider,
-        system_prompt="You are Dolphin an AI assistant that helps humanity.",
+        system_prompt="You are Einstein an AI assistant that helps humanity.",
         predefined_messages_formatter_type=MessagesFormatterType.CHATML,
         debug_output=True
     )
@@ -148,8 +150,9 @@ demo = gr.ChatInterface(
             step=0.1,
             label="Repetition penalty",
         ),
-        #models = ['dolphin-2.9.1-yi-1.5-34b-Q6_K.gguf', 'dolphin-2.9.1-llama-3-70b.Q3_K_M.gguf']
-        gr.Dropdown(["Einstein-v6.1-Llama3-8B-Q6_K.gguf"], value="Einstein-v6.1-Llama3-8B-Q6_K.gguf", label="Model"),
+
+        files = [f for f in os.listdir(download_gguf_model_dir) if os.path.isfile(os.path.join(download_gguf_model_dir, f))]
+        gr.Dropdown(files, value=files[0], label="Model"),
     ],
     theme=gr.themes.Soft(primary_hue="indigo", secondary_hue="blue", neutral_hue="gray",font=[gr.themes.GoogleFont("Exo"), "ui-sans-serif", "system-ui", "sans-serif"]).set(
         body_background_fill_dark="#0f172a",