tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-19 06:25:15 -04:00
Code Issues Packages Projects Releases Wiki Activity

imatrix : use GGUF by default (#14842)

Browse Source 
* imatrix : use GGUF by default

* imatrix : use GGUF regardless of the output filename

The legacy format can only be produced with --output-format dat
This commit is contained in:
compilade
2025-08-03 16:00:05 -04:00
committed by GitHub
parent 0a2f5496be
commit d31192b4ee
4 changed files with 23 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
tools/imatrix/README.md
View File

@@ -7,7 +7,7 @@ More information is available in <https://github.com/ggml-org/llama.cpp/pull/486
```
./llama-imatrix \
-m model.gguf -f some-text.txt [-o imatrix.gguf] [--no-ppl] \
-m model.gguf -f some-text.txt [-o imatrix.gguf] [--output-format {gguf,dat}] [--no-ppl] \
[--process-output] [--chunk 123] [--save-frequency 0] [--output-frequency 10] \
[--in-file imatrix-prev-0.gguf --in-file imatrix-prev-1.gguf ...] [--parse-special] \
[--show-statistics] [...]
@@ -20,6 +20,7 @@ The parameters in square brackets are optional and have the following meaning:
* `-lv | --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`.
* `-o | --output-file` specifies the name of the file where the computed data will be stored. If missing `imatrix.gguf` is used.
* `-ofreq | --output-frequency` specifies how often the so far computed result is saved to disk. Default is 10 (i.e., every 10 chunks)
* `--output-format` specifies the output format of the generated imatrix file. Either "gguf", or "dat" (the legacy format). Defaults to "gguf".
* `--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. Typically, it is better not to utilize the importance matrix when quantizing `output.weight`, so this is set to `false` by default.
* `--in-file` one or more existing imatrix files to load and combine. Useful for merging files from multiple runs/datasets.
@@ -45,14 +46,19 @@ Recent versions of `llama-imatrix` store data in GGUF format by default. For the
```bash
# generate and save the imatrix using legacy format
./llama-imatrix -m ggml-model-f16.gguf -f calibration-data.txt -o imatrix-legcy-format.dat -ngl 99
./llama-imatrix -m ggml-model-f16.gguf -f calibration-data.txt --output-format dat -o imatrix-legcy-format.dat -ngl 99
```
```bash
# covert legacy (binary) imatrix format to new (GGUF) format
# convert legacy (binary) imatrix format to new (GGUF) format
./llama-imatrix --in-file imatrix-legacy-format.dat -o imatrix-new-format.gguf
```
```bash
# convert new (GGUF) imatrix format to legacy (binary) format
./llama-imatrix --in-file imatrix-new-format.gguf --output-format dat -o imatrix-legacy-format.dat
```
```bash
# combine existing imatrices
./llama-imatrix --in-file imatrix-prev-0.gguf --in-file imatrix-prev-1.gguf -o imatrix-combined.gguf