llama.cpp/examples/cvector-generator
ngxson 6d2464aef5 code style 2024-06-13 15:36:03 +02:00
..
CMakeLists.txt change compile target to llama-cvector-generator 2024-06-13 14:51:11 +02:00
README.md typo 2024-06-13 14:55:26 +02:00
completions.txt change compile target to llama-cvector-generator 2024-06-13 14:51:11 +02:00
cvector-generator.cpp change compile target to llama-cvector-generator 2024-06-13 14:51:11 +02:00
negative.txt change compile target to llama-cvector-generator 2024-06-13 14:51:11 +02:00
pca.hpp code style 2024-06-13 15:36:03 +02:00
positive.txt change compile target to llama-cvector-generator 2024-06-13 14:51:11 +02:00

README.md

cvector-generator

This example demonstrates how to generate a control vector using gguf models.

Related PRs:

Examples

# CPU only
./cvector-generator -m ./dolphin-2.0-mistral-7b.Q4_K_M.gguf

# With GPU
./cvector-generator -m ./dolphin-2.0-mistral-7b.Q4_K_M.gguf -ngl 99

# With advanced options
./cvector-generator -m ./dolphin-2.0-mistral-7b.Q4_K_M.gguf -ngl 99 --completions 128 --pca-iter 2000 --batch-pca 100

# To see help message
./cvector-generator -h
# Then, have a look at "cvector" section

Tips and tricks

If you have multiple lines per prompt, you can escape the newline character (change it to \n). For example:

<|im_start|>system\nAct like a person who is extremely happy.<|im_end|>
<|im_start|>system\nYou are in a very good mood today<|im_end|>