jukofyork commited on
Commit
6ea406f
1 Parent(s): ade24e2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -99,9 +99,9 @@ python create_control_vectors.py --model_id ./Mistral-Large-Instruct-2407 --outp
99
  ```
100
 
101
  ```sh
102
- python create_control_vectors.py --model_id ./c4ai-command-r-plus --output_path Mistral-Large-Instruct-2407_alignment_ --system_prompt_file data/system_messages_alignment.json --prompt_file data/prompts.txt --num_prompt_sample 500 --regularisation_factor 1.0
103
- python create_control_vectors.py --model_id ./c4ai-command-r-plus --output_path Mistral-Large-Instruct-2407_alignment_ --system_prompt_file data/system_messages_alignment.json --prompt_file data/prompts.txt --num_prompt_sample 500 --regularisation_factor 0.5
104
- python create_control_vectors.py --model_id ./c4ai-command-r-plus --output_path Mistral-Large-Instruct-2407_alignment_ --system_prompt_file data/system_messages_alignment.json --prompt_file data/prompts.txt --num_prompt_sample 500 --regularisation_factor 0.0
105
  ```
106
 
107
  Please leave feedback if you find these useful and I will consider running the same on the other 9 models in the main [creative-writing-control-vectors-v2.1](https://huggingface.co/jukofyork/creative-writing-control-vectors-v2.1) repo.
 
99
  ```
100
 
101
  ```sh
102
+ python create_control_vectors.py --model_id ./c4ai-command-r-plus --output_path c4ai-command-r-plus_alignment_ --system_prompt_file data/system_messages_alignment.json --prompt_file data/prompts.txt --num_prompt_sample 500 --regularisation_factor 1.0
103
+ python create_control_vectors.py --model_id ./c4ai-command-r-plus --output_path c4ai-command-r-plus_alignment_ --system_prompt_file data/system_messages_alignment.json --prompt_file data/prompts.txt --num_prompt_sample 500 --regularisation_factor 0.5
104
+ python create_control_vectors.py --model_id ./c4ai-command-r-plus --output_path c4ai-command-r-plus_alignment_ --system_prompt_file data/system_messages_alignment.json --prompt_file data/prompts.txt --num_prompt_sample 500 --regularisation_factor 0.0
105
  ```
106
 
107
  Please leave feedback if you find these useful and I will consider running the same on the other 9 models in the main [creative-writing-control-vectors-v2.1](https://huggingface.co/jukofyork/creative-writing-control-vectors-v2.1) repo.