runfuture

> Just found [this PR](https://github.com/ggerganov/llama.cpp/pull/5392) merged into llama.cpp master. However, using llama.cpp [b2100](https://github.com/ggerganov/llama.cpp/releases/tag/b2100). Got the same error. Platform: Windows 11 Log file: > > ``` > [1707396576] Log start >...

@Chaunice For convenience, I have prepared a [Colab notebook](https://colab.research.google.com/drive/1n3YbcbnB7QGPHNEL95cdZPXskxMh6xq7?usp=sharing) to convert the model to GGUF. Additionally, I have provided the converted GGUF models in the links below: 1. [MiniCPM-2B-dpo-q4km-gguf](https://huggingface.co/runfuture/MiniCPM-2B-dpo-q4km-gguf) 2....

> Thank you for interest in MiniCPM. I am one of the authors. In MiniCPM, we implement `tie_word_embedding`, which involves utilizing the same matrix for both input embedding and the...

> > > A good news is that we have converted the original checkpoints into Llama format. Specifically, > > > > > > 1. we absorb the $mu$P scaling...

> A good news is that we have converted the original checkpoints into Llama format. Specifically, > > 1. we absorb the $mu$P scaling factors into the model checkpoints. >...

> Still getting > > ``` > llama_model_load: error loading model: create_tensor: tensor 'output.weight' not found > ``` > > ``` > ./main --version > version: 2252 (525213d2) > ```...

> I am still getting this on Apple Silicon: > > ```shell > $ make clean ; git pull origin ; make -j $(nproc) > $ conda activate llama >...