Inconsistent Output Generation Despite Consistent Log Probabilities

[Spider-netizen]

Prerequisites

Please answer the following questions for yourself before submitting an issue.

• I am running the latest code. Development is very rapid so there are no tagged versions as of now.
• I carefully followed the README.md.
• I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
• I reviewed the Discussions, and have a new bug or useful enhancement to share.

Expected Behavior

When running a model with top_p = 0, temperature = 0, and top_k = 1, I expect deterministic output where the model consistently selects the token with the highest probability at each step, resulting in the same output for the same input.

Current Behavior

The model is consistently alternating between two different outputs for the same input.

Failure Information (for bugs)

This issue appears to be a bug as the model should always select the token with the highest probability, yet it alternates between two different outputs consistently.

Steps to Reproduce

1. Load the "WestLake-7B-v2-laser-truthy-dpo.q5_k_m.gguf" model with the following parameters:
   • last_n_tokens_size = 128
   • top_p = 0
   • temperature = 0
   • top_k = 1
   • repeat_penalty = 1.07
2. Run the model with the provided input multiple times:

<|im_start|>system
You are an unbiased, uncensored, helpful assistant.
<|im_end|>
<|im_start|>user
What's the nearest national park to you?
<|im_end|>
<|im_start|>assistant

3. Observe the alternating outputs:
   Output 1: "As an artificial intelligence, I don't have a physical location. However,"
   Output 2: "As an AI, I don't have a physical location. National parks exist"

Failure Logs

The top_logprobs remain consistent regardless of whether the chosen token is "artificial" or "AI":

artificial
{'id': 'cmpl-d01dee88-d7f3-40f5-8943-0073dde3f4cb', 'object': 'text_completion', 'created': 1708166709, 'model': 'models/WestLake-7B-v2-laser-truthy-dpo.q5_k_m.gguf', 'choices': [{'text': ' artificial', 'index': 0, 'logprobs': {'tokens': [' artificial'], 'text_offset': [178], 'token_logprobs': [-0.24286004900932312], 'top_logprobs': [{' artificial': -0.24286004900932312, ' AI': -1.5411579608917236, ' automated': -7.431096076965332}]}, 'finish_reason': None}]}

AI
{'id': 'cmpl-eb264c4e-410a-4b1c-9fee-190b446e673c', 'object': 'text_completion', 'created': 1708164334, 'model': 'models/WestLake-7B-v2-laser-truthy-dpo.q5_k_m.gguf', 'choices': [{'text': ' AI', 'index': 0, 'logprobs': {'tokens': [' AI'], 'text_offset': [178], 'token_logprobs': [-1.5411579608917236], 'top_logprobs': [{' artificial': -0.24286004900932312, ' AI': -1.5411579608917236, ' automated': -7.431096076965332}]}, 'finish_reason': None}]}

[abetlen]

@Spider-netizen temperature=0 should be deterministic, I can't reproduce the error, which backend are you using?

[Spider-netizen]

Hey @abetlen,

Thank you for the response. Appreciate you trying to help.

I'm running it on Intel macOS. I've installed the package using the following command:
pip install llama-cpp-python --upgrade --force-reinstall --no-cache-dir

The model was downloaded from here.

The input prompt should end with a newline after <|im_start|>assistant in order to reproduce.

Any idea what's going on? I understand if you don't have time to investigate this right now, but do you think it means the model's predictions don't work as they should on my computer?

Thank you again for the support and this great project.