vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

docs: model: add prevision on RoPE

Browse source
This commit is contained in:
Pierrick HYMBERT 2024-04-09 16:34:55 +02:00
parent 90c67719bf
commit 4be9750d49
1 changed files with 1 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
docs/HOWTO-add-model.md
View file

@ -95,6 +95,7 @@ The model params and tensors layout must be defined in `llama.cpp`:
2. Define the tensors layout in `LLM_TENSOR_NAMES` 2. Define the tensors layout in `LLM_TENSOR_NAMES`
3. Add any non standard metadata in `llm_load_hparams` 3. Add any non standard metadata in `llm_load_hparams`
4. Create the tensors for inference in `llm_load_tensors` 4. Create the tensors for inference in `llm_load_tensors`
5. If the model has a RoPE operation, add the rope type in `llama_rope_type`
NOTE: The dimensions in `ggml` are typically in the reverse order of the `pytorch` dimensions. NOTE: The dimensions in `ggml` are typically in the reverse order of the `pytorch` dimensions.