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

imatrix : migrate to gpt_params (#7771)

Browse source 
* imatrix : migrate to gpt_params

ggml-ci

* imatrix : add --save-frequency cli arg

* common : fix --no-ppl
This commit is contained in:
Georgi Gerganov 2024-06-06 16:30:58 +03:00 • committed by GitHub
parent ad675e1c67
commit f83351f9a6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 213 additions and 215 deletions
Download patch file Download diff file Expand all files Collapse all files

11
examples/imatrix/README.md
View file

@ -6,16 +6,19 @@ More information is available here: https://github.com/ggerganov/llama.cpp/pull/
## 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]
./imatrix \
-m model.gguf -f some-text.txt [-o imatrix.dat] [--process-output] [--verbosity 1] \
[--no-ppl] [--chunk 123] [--output-frequency 10] [--save-frequency 0] \
[--in-file imatrix-prev-0.dat --in-file imatrix-prev-1.dat ...]
```
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.
* `--output-frequency` specifies how often the so far computed result is saved to disk. Default is 10 (i.e., every 10 chunks)
* `--save-frequency` specifies how often to save a copy of the imatrix in a separate file. Default is 0 (i.e., never)
* `--process-output` 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