Naphula commited on
Commit
e2cf457
·
verified ·
1 Parent(s): bea1ba9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -19,6 +19,9 @@ Tools to enhance LLM quantizations and merging
19
  # [vocab_resizer.py](https://huggingface.co/spaces/Naphula/model_tools/blob/main/vocab_resizer.py)
20
  - Converts models with larger vocab_sizes to a standard size (default 131072 Mistral 24B) for use with mergekit. Note that `tokenizer.model` must be manually copied into the `/fixed/` folder.
21
 
 
 
 
22
  # [folder_content_combiner_anyfiles.py](https://huggingface.co/spaces/Naphula/model_tools/blob/main/folder_content_combiner_anyfiles.py)
23
  - Combines all files in the script's current directory into a single output file, sorted alphabetically.
24
 
 
19
  # [vocab_resizer.py](https://huggingface.co/spaces/Naphula/model_tools/blob/main/vocab_resizer.py)
20
  - Converts models with larger vocab_sizes to a standard size (default 131072 Mistral 24B) for use with mergekit. Note that `tokenizer.model` must be manually copied into the `/fixed/` folder.
21
 
22
+ # [lm_head_remover.py](https://huggingface.co/spaces/Naphula/model_tools/blob/main/lm_head_remover.py)
23
+ - This script will load a "fat" 18.9GB model (default Gemma 9B), force it to tie the weights (deduplicating the lm_head), and re-save it. This will drop the file size to ~17.2GB and make it compatible with the others.
24
+
25
  # [folder_content_combiner_anyfiles.py](https://huggingface.co/spaces/Naphula/model_tools/blob/main/folder_content_combiner_anyfiles.py)
26
  - Combines all files in the script's current directory into a single output file, sorted alphabetically.
27