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

py : update outdated copy-paste instructions [no ci] (#10667)

Browse source 
This commit updates the copy-paste instruction in
convert_hf_to_gguf_update.py to reflect that convert_hf_to_gguf.py
will have already been updated with the new get_vocab_base_pre()
function when this script completes.
This commit is contained in:
Daniel Bevenius 2024-12-05 08:47:55 +01:00 • committed by GitHub
parent f112d198cd
commit d405804be8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
convert_hf_to_gguf_update.py
View file

@ -17,7 +17,7 @@
#
# python3 convert_hf_to_gguf_update.py <huggingface_token>
#
# - Copy-paste the generated get_vocab_base_pre() function into convert_hf_to_gguf.py
# - The convert_hf_to_gguf.py script will have had its get_vocab_base_pre() function updated
# - Update llama.cpp with the new pre-tokenizer if necessary
#
# TODO: generate tokenizer tests for llama.cpp