fix app

app.py

@@ -9,20 +9,20 @@ from typing import Optional
 
 app = FastAPI()
 
-# Predefined list of available models (verified working paths)
+# Predefined list of available models (TheBloke only - verified, fits 18GB Space)
 AVAILABLE_MODELS = {
-    # === Financial & Summarization Models (Recommended) ===
-    "qwen-2.5-7b": "Qwen/Qwen2.5-7B-Instruct-GGUF:qwen2.5-7b-instruct-q4_k_m.gguf",  # Best for financial + multilingual
-    "yi-1.5-9b": "TheBloke/Yi-1.5-9B-Chat-GGUF:yi-1.5-9b-chat.Q4_K_M.gguf",  # Excellent for finance
-    "llama-3.1-8b": "lmstudio-community/Meta-Llama-3.1-8B-Instruct-GGUF:Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf",  # Great reasoning
-    "mistral-7b": "TheBloke/Mistral-7B-Instruct-v0.3-GGUF:mistral-7b-instruct-v0.3.Q4_K_M.gguf",  # Reliable summarization
-    "llama-3.2-3b": "lmstudio-community/Llama-3.2-3B-Instruct-GGUF:Llama-3.2-3B-Instruct-Q4_K_M.gguf",  # Fast & lightweight
+    # === General Purpose (Default) ===
+    "deepseek-chat": "TheBloke/deepseek-llm-7B-chat-GGUF:deepseek-llm-7b-chat.Q4_K_M.gguf",
+
+    # === Financial & Summarization Models ===
+    "mistral-7b": "TheBloke/Mistral-7B-Instruct-v0.2-GGUF:mistral-7b-instruct-v0.2.Q4_K_M.gguf",
+    "openhermes-7b": "TheBloke/OpenHermes-2.5-Mistral-7B-GGUF:openhermes-2.5-mistral-7b.Q4_K_M.gguf",
 
     # === Coding Models ===
     "deepseek-coder": "TheBloke/deepseek-coder-6.7B-instruct-GGUF:deepseek-coder-6.7b-instruct.Q4_K_M.gguf",
 
-    # === General Purpose ===
-    "deepseek-chat": "TheBloke/deepseek-llm-7B-chat-GGUF:deepseek-llm-7b-chat.Q4_K_M.gguf",
+    # === Lightweight/Fast ===
+    "llama-7b": "TheBloke/Llama-2-7B-Chat-GGUF:llama-2-7b-chat.Q4_K_M.gguf",
 }
 
 # Global state