adding support for the chatglm3-6b model

[mnlife]

Hello everyone, I'm currently adding support for the chatglm3-6b model on llama.cpp. I've done a quick check on the inference algorithm, but I didn't find any issues.
However, the inference results are all over the place.

How should I go about debugging this?
Are there any tricks for pinpointing the issue when inference goes wrong?

The following are my log link and code modifications:

main.log
0001-feature-add-chatglm-support.patch.txt

[ggerganov]

Debugging could be tedious - you can try to compare the results after each op with the reference implementation. Or open a PR and more people can have a look

From a quick look, the following code incorrectly passes split_point for the offset argument of ggml_view_2d which expects bytes instead of elements:

+                // 创建两个视图张量，分别表示切分后的两部分
+                int64_t split_point = cur->ne[0] / 2;
+                struct ggml_tensor * x0 = ggml_cont(ctx, ggml_view_2d(ctx, cur, split_point, cur->ne[1], cur->nb[1], 0));
+                struct ggml_tensor * x1 = ggml_cont(ctx, ggml_view_2d(ctx, cur, split_point, cur->ne[1], cur->nb[1], split_point));

[mnlife]

Thank you!!!
I've made modifications to this, along with some other changes. After testing, everything seems fine. I'll tidy it up and push this commit shortly.