diff options
| author | Laurent Mazare <laurent.mazare@gmail.com> | 2023-08-16 12:41:07 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-08-16 12:41:07 +0100 |
| commit | 3071134788334c972d9e356f53887d2b2ff026b7 (patch) | |
| tree | adbb58e3babee5d62fa6150bde4f9bb03770607c /candle-core/examples/cpu_benchmarks.rs | |
| parent | fec87e86f50da78656a0fb28fc254390435fb3fd (diff) | |
| download | candle-3071134788334c972d9e356f53887d2b2ff026b7.tar.gz candle-3071134788334c972d9e356f53887d2b2ff026b7.tar.bz2 candle-3071134788334c972d9e356f53887d2b2ff026b7.zip | |
Get the ggml based llama to generate some text. (#464)
* Add more stats to the ggml example.
* Build a quantized model from the file content.
* Move the tensor retrieval in the main crate.
* Start adding the forward pass.
* Add more to the forward pass of the quantized llama.
* Apply the attention layers.
* Add the sampling loop.
* Get the sampling loop to work.
* Minor tweak.
* Add a quantize/dequantize test.
* Bugfix.
* Add a comment + swap the order.
* Bugfixes.
Diffstat (limited to 'candle-core/examples/cpu_benchmarks.rs')
0 files changed, 0 insertions, 0 deletions