root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-11-11 21:39:52 +00:00
Code Issues Actions 12 Packages Projects Releases Wiki Activity
29122d32ac
llama.cpp/examples/imatrix
History
Jared Van Bortel 1b67731e18
BERT tokenizer fixes (#6498) 
Key changes:
* BERT conversion: fix abuse of LlamaHfVocab, do not set BOS or EOS
* Nomic Embed conversion: pad vocab instead of slicing embedding tensor
* llama_tokenize: handle added special tokens like HF does
2024-04-09 13:44:08 -04:00
..
CMakeLists.txt Importance Matrix calculation (#4861) 2024-01-12 06:59:57 +01:00
imatrix.cpp BERT tokenizer fixes (#6498) 2024-04-09 13:44:08 -04:00
README.md cuda : rename build flag to LLAMA_CUDA (#6299) 2024-03-26 01:16:01 +01:00

README.md

llama.cpp/examples/imatrix

Compute an importance matrix for a model and given text dataset. Can be used during quantization to enchance the quality of the quantum models. More information is available here: https://github.com/ggerganov/llama.cpp/pull/4861

Usage

./imatrix -m <some_fp_model> -f <some_training_data> [-o <output_file>] [--verbosity <verbosity_level>]
        [-ofreq num_chunks] [-ow <0 or 1>] [other common params]

Here -m with a model name and -f with a file containing training data (such as e.g. wiki.train.raw) are mandatory. The parameters in square brackets are optional and have the following meaning:

  • -o (or --output-file) specifies the name of the file where the computed data will be stored. If missing imatrix.dat is used.
  • --verbosity specifies the verbosity level. If set to 0, no output other than the perplexity of the processed chunks will be generated. If set to 1, each time the results are saved a message is written to stderr. If >=2, a message is output each time data is collected for any tensor. Default verbosity level is 1.
  • -ofreq (or --output-frequency) specifies how often the so far computed result is saved to disk. Default is 10 (i.e., every 10 chunks)
  • -ow (or --output-weight) specifies if data will be collected for the output.weight tensor. My experience is that it is better to not utilize the importance matrix when quantizing output.weight, so this is set to false by default.

For faster computation, make sure to use GPU offloading via the -ngl argument

Example

LLAMA_CUDA=1 make -j

# generate importance matrix (imatrix.dat)
./imatrix -m ggml-model-f16.gguf -f train-data.txt -ngl 99

# use the imatrix to perform a Q4_K_M quantization
./quantize --imatrix imatrix.dat ggml-model-f16.gguf ./ggml-model-q4_k_m.gguf q4_k_m