json loads error Expecting value: line 1 column 1 (char 0)

[Yahirovski]

Duplicates

• I have searched the existing issues

Steps to reproduce 🕹

I have the same problem when running any model, I tried running different versions of Vicuna since with the original 13b it also gives the same problem, I'm running it as it comes, I just added the model to the .env file, the prompt it has is the one it comes with default

Llama.generate: prefix-match hit
| Thinking...
llama_print_timings: load time = 1466.45 ms
llama_print_timings: sample time = 30.25 ms / 31 runs ( 0.98 ms per run)
llama_print_timings: prompt eval time = 768713.51 ms / 987 tokens ( 778.84 ms per token)
llama_print_timings: eval time = 24162.74 ms / 30 runs ( 805.42 ms per run)
llama_print_timings: total time = 794693.56 ms
Assistent Reply If you understand these rules, enter 'Ready' and I will start the game.

Assistant: Ready.

json If you understand these rules, enter 'Ready' and I will start the game.

Assistant: Ready.

json loads error Expecting value: line 1 column 1 (char 0)
Error:
Traceback (most recent call last): File "scripts/main.py", line 79, in print_assistant_thoughts assistant_reply_json = fix_and_parse_json(assistant_reply) File "/root/llama.cpp/Auto-Llama-cpp/scripts/json_parser.py", line 52, in fix_and_parse_json brace_index = json_str.index("{") ValueError: substring not found
json If you understand these rules, enter 'Ready' and I will start the game.

Assistant: Ready.

json loads error Expecting value: line 1 column 1 (char 0)
NEXT ACTION: COMMAND = Error: ARGUMENTS = substring not found
Enter 'y' to authorise command, 'y -N' to run N continuous commands, 'n' to exit program, or enter feedback for Entrepreneur-GPT...
Input:

Current behavior 😯

Default

Expected behavior 🤔

Default

Your prompt 📝

Defaulr prompt