diff --git a/lollms/server.py b/lollms/server.py
index 10edc4e..d3acb2d 100644
--- a/lollms/server.py
+++ b/lollms/server.py
@@ -458,15 +458,19 @@ class LoLLMsServer:
                     fd = model.detokenize(tk[-min(self.config.ctx_size,n_tokens):])
 
                     ASCIIColors.print("warm up", ASCIIColors.color_bright_cyan)
-                    generated_text = model.generate(fd, n_predict=n_predicts, callback=callback,
-                                                    temperature = parameters["temperature"],
-                                                    top_k = parameters["top_k"],
-                                                    top_p = parameters["top_p"],
-                                                    repeat_penalty = parameters["repeat_penalty"],
-                                                    repeat_last_n = parameters["repeat_last_n"],
-                                                    seed = parameters["seed"]                                                
-                                                    )
-                    ASCIIColors.success(f"\ndone")
+                    try:
+                        generated_text = model.generate(fd, n_predict=n_predicts, callback=callback,
+                                                        temperature = parameters["temperature"],
+                                                        top_k = parameters["top_k"],
+                                                        top_p = parameters["top_p"],
+                                                        repeat_penalty = parameters["repeat_penalty"],
+                                                        repeat_last_n = parameters["repeat_last_n"],
+                                                        seed = parameters["seed"]                                                
+                                                        )
+                        ASCIIColors.success(f"\ndone")
+                    except Exception as ex:
+                        self.socketio.emit('generation_error', {'error': str(ex)}, room=client_id)
+                        ASCIIColors.error(f"\ndone")
                     if client_id in self.clients:
                         if not self.clients[client_id]["requested_stop"]:
                             # Emit the generated text to the client
@@ -474,72 +478,76 @@ class LoLLMsServer:
                             self.socketio.sleep(0)
                     self.is_ready = True
                 else:
-                    personality: AIPersonality = self.personalities[personality_id]
-                    personality.model = model
-                    cond_tk = personality.model.tokenize(personality.personality_conditioning)
-                    n_cond_tk = len(cond_tk)
-                    # Placeholder code for text generation
-                    # Replace this with your actual text generation logic
-                    print(f"Text generation requested by client: {client_id}")
+                    try:
+                        personality: AIPersonality = self.personalities[personality_id]
+                        personality.model = model
+                        cond_tk = personality.model.tokenize(personality.personality_conditioning)
+                        n_cond_tk = len(cond_tk)
+                        # Placeholder code for text generation
+                        # Replace this with your actual text generation logic
+                        print(f"Text generation requested by client: {client_id}")
 
-                    self.answer["full_text"] = ''
-                    full_discussion_blocks = self.clients[client_id]["full_discussion_blocks"]
+                        self.answer["full_text"] = ''
+                        full_discussion_blocks = self.clients[client_id]["full_discussion_blocks"]
 
-                    if prompt != '':
-                        if personality.processor is not None and personality.processor_cfg["process_model_input"]:
-                            preprocessed_prompt = personality.processor.process_model_input(prompt)
-                        else:
-                            preprocessed_prompt = prompt
+                        if prompt != '':
+                            if personality.processor is not None and personality.processor_cfg["process_model_input"]:
+                                preprocessed_prompt = personality.processor.process_model_input(prompt)
+                            else:
+                                preprocessed_prompt = prompt
+                            
+                            if personality.processor is not None and personality.processor_cfg["custom_workflow"]:
+                                full_discussion_blocks.append(personality.user_message_prefix)
+                                full_discussion_blocks.append(preprocessed_prompt)
+                        
+                            else:
+
+                                full_discussion_blocks.append(personality.user_message_prefix)
+                                full_discussion_blocks.append(preprocessed_prompt)
+                                full_discussion_blocks.append(personality.link_text)
+                                full_discussion_blocks.append(personality.ai_message_prefix)
+
+                        full_discussion = personality.personality_conditioning + ''.join(full_discussion_blocks)
+
+                        def callback(text, message_type: MSG_TYPE):
+                            if message_type == MSG_TYPE.MSG_TYPE_CHUNK:
+                                self.answer["full_text"] = self.answer["full_text"] + text
+                                self.socketio.emit('text_chunk', {'chunk': text}, room=client_id)
+                                self.socketio.sleep(0)
+                            try:
+                                if self.clients[client_id]["requested_stop"]:
+                                    return False
+                                else:
+                                    return True
+                            except: # If the client is disconnected then we stop talking to it
+                                return False
+
+                        tk = personality.model.tokenize(full_discussion)
+                        n_tokens = len(tk)
+                        fd = personality.model.detokenize(tk[-min(self.config.ctx_size-n_cond_tk,n_tokens):])
                         
                         if personality.processor is not None and personality.processor_cfg["custom_workflow"]:
-                            full_discussion_blocks.append(personality.user_message_prefix)
-                            full_discussion_blocks.append(preprocessed_prompt)
-                    
+                            print("processing...", end="", flush=True)
+                            generated_text = personality.processor.run_workflow(prompt, previous_discussion_text=personality.personality_conditioning+fd, callback=callback)
                         else:
+                            ASCIIColors.info("generating...", end="", flush=True)
+                            generated_text = personality.model.generate(
+                                                                        personality.personality_conditioning+fd, 
+                                                                        n_predict=personality.model_n_predicts, 
+                                                                        callback=callback)
 
-                            full_discussion_blocks.append(personality.user_message_prefix)
-                            full_discussion_blocks.append(preprocessed_prompt)
-                            full_discussion_blocks.append(personality.link_text)
-                            full_discussion_blocks.append(personality.ai_message_prefix)
+                        if personality.processor is not None and personality.processor_cfg["process_model_output"]: 
+                            generated_text = personality.processor.process_model_output(generated_text)
 
-                    full_discussion = personality.personality_conditioning + ''.join(full_discussion_blocks)
+                        full_discussion_blocks.append(generated_text.strip())
+                        ASCIIColors.success("\ndone", end="", flush=True)
 
-                    def callback(text, message_type: MSG_TYPE):
-                        if message_type == MSG_TYPE.MSG_TYPE_CHUNK:
-                            self.answer["full_text"] = self.answer["full_text"] + text
-                            self.socketio.emit('text_chunk', {'chunk': text}, room=client_id)
-                            self.socketio.sleep(0)
-                        try:
-                            if self.clients[client_id]["requested_stop"]:
-                                return False
-                            else:
-                                return True
-                        except: # If the client is disconnected then we stop talking to it
-                            return False
-
-                    tk = personality.model.tokenize(full_discussion)
-                    n_tokens = len(tk)
-                    fd = personality.model.detokenize(tk[-min(self.config.ctx_size-n_cond_tk,n_tokens):])
-                    
-                    if personality.processor is not None and personality.processor_cfg["custom_workflow"]:
-                        print("processing...", end="", flush=True)
-                        generated_text = personality.processor.run_workflow(prompt, previous_discussion_text=personality.personality_conditioning+fd, callback=callback)
-                    else:
-                        ASCIIColors.info("generating...", end="", flush=True)
-                        generated_text = personality.model.generate(
-                                                                    personality.personality_conditioning+fd, 
-                                                                    n_predict=personality.model_n_predicts, 
-                                                                    callback=callback)
-
-                    if personality.processor is not None and personality.processor_cfg["process_model_output"]: 
-                        generated_text = personality.processor.process_model_output(generated_text)
-
-                    full_discussion_blocks.append(generated_text.strip())
-                    ASCIIColors.success("\ndone", end="", flush=True)
-
-                    # Emit the generated text to the client
-                    self.socketio.emit('text_generated', {'text': generated_text}, room=client_id)
-                    self.socketio.sleep(0)
+                        # Emit the generated text to the client
+                        self.socketio.emit('text_generated', {'text': generated_text}, room=client_id)
+                        self.socketio.sleep(0)
+                    except Exception as ex:
+                        self.socketio.emit('generation_error', {'error': str(ex)}, room=client_id)
+                        ASCIIColors.error(f"\ndone")
                     self.is_ready = True
             # Start the text generation task in a separate thread
             self.socketio.start_background_task(target=generate_text, once=True)
diff --git a/setup.py b/setup.py
index 8b073c7..6451ebb 100644
--- a/setup.py
+++ b/setup.py
@@ -26,7 +26,7 @@ def get_all_files(path):
 
 setuptools.setup(
     name="lollms",
-    version="1.2.10",
+    version="1.2.11",
     author="Saifeddine ALOUI",
     author_email="aloui.saifeddine@gmail.com",
     description="A python library for AI personality definition",