Better format the prompt when generation attempts > 1

modules/chat.py

@@ -116,7 +116,7 @@ def chatbot_wrapper(text, max_new_tokens, do_sample, temperature, top_p, typical
     # Generate
     reply = ''
     for i in range(chat_generation_attempts):
-        for reply in generate_reply(prompt+reply, max_new_tokens, do_sample, temperature, top_p, typical_p, repetition_penalty, top_k, min_length, no_repeat_ngram_size, num_beams, penalty_alpha, length_penalty, early_stopping, eos_token=eos_token, stopping_string=f"\n{name1}:"):
+        for reply in generate_reply(f"{prompt}{' ' if len(reply) > 0 else ''}{reply}", max_new_tokens, do_sample, temperature, top_p, typical_p, repetition_penalty, top_k, min_length, no_repeat_ngram_size, num_beams, penalty_alpha, length_penalty, early_stopping, eos_token=eos_token, stopping_string=f"\n{name1}:"):
 
             # Extracting the reply
             reply, next_character_found, substring_found = extract_message_from_reply(prompt, reply, name2, name1, check, extensions=True)