Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-03 17:51:09 +01:00
Code Issues Packages Projects Releases Wiki Activity

convert-llama-7b-pth-to-gguf.py : add tensor data layout

Browse Source
This commit is contained in:
klosax 2023-08-15 19:55:13 +02:00 committed by GitHub
parent 66756c82af
commit 2ae0e985b3
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
convert-llama-7b-pth-to-gguf.py
View File

@ -96,6 +96,7 @@ 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)