Laurent Mazare 55bc3382cf Allow for different behavior between training and eval (#1213) ...

* Forward with training.

* Do not use dropout on vgg evaluation.

2023-10-29 07:53:09 +01:00

..

segment_anything

Add negative prompts to segment-anything. (#1000)

2023-09-30 06:17:42 +01:00

stable_diffusion

Remove some todos. (#1042)

2023-10-05 22:42:20 +01:00

whisper

Make the whisper model cloneable (#1200)

2023-10-27 16:59:19 +01:00

wuerstchen

Add flash-attn support. (#912)

2023-09-20 14:07:55 +01:00

bert.rs

Add the jina-bert embeddings model. (#1187)

2023-10-26 16:54:36 +01:00

bigcode.rs

Use softmax-last-dim where possible. (#1057)

2023-10-08 13:16:42 +01:00

blip_text.rs

[Wasm] BLIP Example (#1183)

2023-10-26 07:24:02 +01:00

blip.rs

[Wasm] BLIP Example (#1183)

2023-10-26 07:24:02 +01:00

convmixer.rs

Convmixer (#1073)

2023-10-11 18:24:32 +01:00

dinov2.rs

Move more models to candle-transformers (#796)

2023-09-10 10:20:18 +01:00

efficientnet.rs

Move more models to candle-transformers (#796)

2023-09-10 10:20:18 +01:00

falcon.rs

Move some models to candle-transformers so that it's easier to re-use. (#794)

2023-09-10 09:40:27 +01:00

jina_bert.rs

Fixes for jina-bert. (#1189)

2023-10-26 18:52:30 +01:00

llama2_c_weights.rs

Move the llama2-c model in transformers. (#1205)

2023-10-28 16:51:19 +01:00

llama2_c.rs

Infer the config for llama2-c. (#1208)

2023-10-28 19:00:39 +01:00

llama.rs

Move some models to candle-transformers so that it's easier to re-use. (#794)

2023-09-10 09:40:27 +01:00

mistral.rs

Make some model cloneable. (#1125)

2023-10-18 19:30:47 +01:00

mixformer.rs

Add support for the phi-hermes finetuned model. (#1192)

2023-10-27 05:57:08 +01:00

mod.rs

feat: implement VGG13, VGG16 and VGG19 (#1211)

2023-10-29 06:10:23 +00:00

mpt.rs

Make some model cloneable. (#1125)

2023-10-18 19:30:47 +01:00

persimmon.rs

Add the relu2 and relu6 activations. (#1201)

2023-10-27 20:51:16 +01:00

quantized_blip_text.rs

Add a quantized blip model. (#1155)

2023-10-22 20:33:25 +01:00

quantized_blip.rs

[Wasm] BLIP Example (#1183)

2023-10-26 07:24:02 +01:00

quantized_llama2_c.rs

Move the llama2-c model in transformers. (#1205)

2023-10-28 16:51:19 +01:00

quantized_llama.rs

Make some model cloneable. (#1125)

2023-10-18 19:30:47 +01:00

quantized_mistral.rs

More model cloning. (#1126)

2023-10-18 21:55:46 +01:00

quantized_mixformer.rs

More model cloning. (#1126)

2023-10-18 21:55:46 +01:00

quantized_mpt.rs

More model cloning. (#1126)

2023-10-18 21:55:46 +01:00

quantized_stable_lm.rs

Make more models cloneable. (#1203)

2023-10-28 07:43:08 +01:00

quantized_t5.rs

Make more models cloneable. (#1203)

2023-10-28 07:43:08 +01:00

resnet.rs

Support ResNet 50/101/152. (#1130)

2023-10-19 10:48:31 +01:00

stable_lm.rs

Tracing for StableLM and quantized StableLM. (#1068)

2023-10-10 08:09:25 +02:00

t5.rs

Make more models cloneable. (#1203)

2023-10-28 07:43:08 +01:00

vgg.rs

Allow for different behavior between training and eval (#1213)

2023-10-29 07:53:09 +01:00

vit.rs

Add some vision transformers models (#1132)

2023-10-19 22:24:18 +01:00

with_tracing.rs

Remove the unused pragma and properly apply the bias. (#1147)

2023-10-22 06:47:40 +01:00