abetlen / abetlen/llama-cpp-python
A different value of n_batch gives different logits (llama.cpp_hf)
- 主要言語
- Python
- スター
- 10.6k
- フォーク
- 1.4k
- PR マージ指標
- PR 指標を取得中
説明
Hello,
I was told that n_batch doesn't alter the logits but after doing some tests I can see that it's not working as intented (or is it?).
"*When was born Tony Yoka? - Tony Yoka was born the 28 April 199...*"
The next token is supposed to be "2"

You can see that a low n_batch value objectively leads to a deterioration in the quality of the results (The only viable token is less likely to be chosen).
### Is there an existing issue for this?
- [X] I have searched the existing issues
### Reproduction
Change the n_batch value and compare the logits.
### Screenshot
_No response_
### Logs
```shell
No logs.
```
### System Info
```shell
Windows 10.
RTX 3060.
```
コントリビューションガイド
評価
この issue はまだ評価されていません。