diff --git a/convert-llama-h5-to-gguf.py b/convert-llama-h5-to-gguf.py index 22405673f..fd3b9d55b 100644 --- a/convert-llama-h5-to-gguf.py +++ b/convert-llama-h5-to-gguf.py @@ -97,6 +97,7 @@ gguf_writer.add_architecture(llm_arch) gguf_writer.add_name(last_dir) gguf_writer.add_file_type("All tensors F32" if ftype == 0 else "Most tensors F16, some F32") gguf_writer.add_source_hf_repo(hf_repo) +gguf_writer.add_tensor_data_layout(llm_arch, "Meta AI original pth") gguf_writer.add_context_length(llm_arch, hparams["max_position_embeddings"]) gguf_writer.add_embedding_length(llm_arch, hparams["hidden_size"]) gguf_writer.add_block_count(llm_arch, block_count)