mirror of
https://github.com/jart/cosmopolitan.git
synced 2025-02-07 15:03:34 +00:00
282dd8e7b7
make -j8 o//third_party/radpajama/radpajama.com
make -j8 o//third_party/radpajama/radpajama-chat.com
This change gets the radpajama.mk config working. This package depends
on THIRD_PARTY_GGML but it's configured to call ggjt_v1(), so that the
library will provide the old quantizers. The ggml_quantize_chunk() API
will now dispatch to older quantizers based on the configured version.
22 lines
No EOL
524 B
Bash
22 lines
No EOL
524 B
Bash
// clang-format off
|
|
#!/bin/bash
|
|
|
|
# cd to scripts dir
|
|
cd `dirname $0`
|
|
|
|
# download model to models dir
|
|
echo "Downloading model"
|
|
python ./convert_gptneox_to_ggml.py togethercomputer/RedPajama-INCITE-Base-3B-v1 ../models/pythia
|
|
|
|
# remove temp cache dir
|
|
echo "Removing temp cache dir"
|
|
rm -r ../models/pythia-cache
|
|
|
|
# quantize model
|
|
echo "Quantizing model (q4_0)"
|
|
cd ../../..
|
|
python ./examples/redpajama/scripts/quantize-gptneox.py ./examples/redpajama/models/pythia/ggml-RedPajama-INCITE-Base-3B-v1-f16.bin
|
|
|
|
|
|
# done!
|
|
echo "Done." |