diff options
| author | Santiago Medina <santiagm08@gmail.com> | 2024-04-01 10:37:54 -0700 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-04-01 19:37:54 +0200 |
| commit | ea0d8d3753b53a936c472c30ae5dc0d52bfa81fa (patch) | |
| tree | 5e2e6d0359b0424f66e24a687bd694f65299cee2 /candle-examples/examples/t5/main.rs | |
| parent | 308ea070edd4fa52bdbbee3eb9279325c7500556 (diff) | |
| download | candle-ea0d8d3753b53a936c472c30ae5dc0d52bfa81fa.tar.gz candle-ea0d8d3753b53a936c472c30ae5dc0d52bfa81fa.tar.bz2 candle-ea0d8d3753b53a936c472c30ae5dc0d52bfa81fa.zip | |
Quantized moondream implementation and BOS token (#1980)
* moondream implementation
* add moondream example
* change config default activation
* Add assets and integrate phi mixformer with example
* Make use of kv cache and fix seq_len bug; Clean up example code
* Add README link to example
* Remove pos_embed scaling; Remove assets; Add to README; Expand VisionConfig
* Delete image
* Use apply instead of forward
* Pass bos token at the beginning of tensor.
* Quantize moondream.
* Forward with image bos token.
* Clippy.
* Use q4_0 quantization.
* Add pointers for sequence and tokens; Remove seq_len conditional
Diffstat (limited to 'candle-examples/examples/t5/main.rs')
0 files changed, 0 insertions, 0 deletions