Nick Senger cbaa0ad46f UniPC for diffusion sampling (#2684) ...

* feat: Add unipc multistep scheduler

* chore: Clippy and formatting

* chore: Update comments

* chore: Avoid unsafety in float ordering

* refactor: Update Scheduler::step mutability requirements

* fix: Corrector img2img

* chore: Update unipc ref link to latest diffusers release

* chore: Deduplicate float ordering

* fix: Panic when running with dev profile

2025-01-01 21:34:17 +01:00

..

based

Add Based LLM from Hazy Research. (#2411)

2024-08-12 21:21:19 +02:00

beit

onnx: fix pad, unsqueeze (#2317)

2024-07-23 23:10:57 +02:00

bert

bert attention mask (#1934)

2024-08-01 08:26:19 +02:00

bigcode

Adapt more examples to the updated safetensor api. (#947)

2023-09-23 21:26:03 +01:00

blip

onnx: fix pad, unsqueeze (#2317)

2024-07-23 23:10:57 +02:00

chatglm

Add the custom tokenizer. (#1686)

2024-02-09 17:36:50 +01:00

chinese_clip

feat: intergrate chinese clip and add example (#2555)

2024-10-10 15:18:55 +02:00

clip

Add the SigLIP model. (#2515)

2024-09-28 23:48:00 +02:00

codegeex4-9b

Update README.org (#2670)

2024-12-30 11:32:02 +01:00

colpali

Add ColPali (#2524)

2024-10-01 11:48:39 +02:00

convmixer

Move the image tensor to the appropriate device. (#1856)

2024-03-16 22:25:46 +01:00

convnext

Move the image tensor to the appropriate device. (#1856)

2024-03-16 22:25:46 +01:00

custom-ops

Cuda acceleration for quantized model. (#1754)

2024-02-25 18:11:47 +01:00

depth_anything_v2

make DepthAnythingV2 more reusable (#2675)

2024-12-21 12:06:03 +01:00

dinov2

Move the image tensor to the appropriate device. (#1856)

2024-03-16 22:25:46 +01:00

dinov2reg4

Add DINOv2Reg4 + PlantCLEF2024 (#2293)

2024-06-29 11:49:15 +02:00

distilbert

…

efficientnet

Move the image tensor to the appropriate device. (#1856)

2024-03-16 22:25:46 +01:00

efficientvit

Move the image tensor to the appropriate device. (#1856)

2024-03-16 22:25:46 +01:00

encodec

Make the RNN configs accessible from the models. (#2541)

2024-10-04 14:22:23 +02:00

eva2

onnx: fix pad, unsqueeze (#2317)

2024-07-23 23:10:57 +02:00

falcon

Use the new hub helper function. (#1484)

2023-12-26 09:44:30 +01:00

fastvit

FastViT fixes. (#2452)

2024-08-28 11:20:09 +02:00

flux

Streamline the glm4 example. (#2694)

2024-12-31 09:21:41 +01:00

gemma

Add support for gemma-2. (#2425)

2024-08-17 20:31:23 +02:00

glm4

Actually remove the default hf-hub cache path for glm. (#2696)

2024-12-31 11:00:44 +01:00

granite

Adding Granite 7b Instruct model example (#2487)

2024-09-21 11:52:01 +02:00

gte-qwen

Support embedding model gte-Qwen1.5-7B-instruct (#2190)

2024-05-16 21:34:10 +02:00

hiera

Add Hiera vision model. (#2382)

2024-08-01 11:59:22 +02:00

jina-bert

Fix cargo fmt. (#2383)

2024-08-01 14:19:41 +02:00

llama

Add the SmolLM2 models. (#2595)

2024-11-03 17:11:12 +01:00

llama2-c

Explicit caching in llama2.c.

2024-02-22 10:22:03 +01:00

llama_multiprocess

Apply rustfmt. (#2421)

2024-08-16 18:57:14 +02:00

llava

onnx: fix pad, unsqueeze (#2317)

2024-07-23 23:10:57 +02:00

mamba

Support alternative dtypes for mamba (#2036)

2024-04-10 18:10:01 +02:00

mamba-minimal

Lint fixes introduced with Rust 1.83 (#2646)

2024-11-28 23:00:21 +01:00

marian-mt

Fix the marian tokenizer importer. (#2426)

2024-08-17 20:58:40 +02:00

metavoice

Quantized version of the metavoice model. (#1824)

2024-03-09 11:06:04 +01:00

mimi

Make the RNN configs accessible from the models. (#2541)

2024-10-04 14:22:23 +02:00

mistral

Support for mistral-nemo. (#2396)

2024-08-04 19:52:40 +02:00

mixtral

Use BF16 on metal when possible. (#2378)

2024-08-01 10:48:58 +02:00

mnist-training

…

mobileclip

Remove some extra whitelines. (#2513)

2024-09-28 14:41:28 +02:00

mobilenetv4

MobileCLIP models S1 and S2 (#2454)

2024-08-29 15:38:58 +02:00

mobileone

Move the image tensor to the appropriate device. (#1856)

2024-03-16 22:25:46 +01:00

moondream

onnx: fix pad, unsqueeze (#2317)

2024-07-23 23:10:57 +02:00

musicgen

Clippy fixes for 1.81.0. (#2461)

2024-09-05 23:46:55 +02:00

nvembed_v2

Add Nvembed v2 model (#2649)

2024-12-03 10:56:01 +01:00

olmo

Add Olmo models (#2127)

2024-04-26 11:02:51 +02:00

onnx

Update docs to reflect current usage of example (#1610)

2024-02-04 11:59:47 +01:00

paligemma

Add PaliGemma. (#2519)

2024-09-29 19:56:56 +02:00

parler-tts

Fix for parler-tts, do not add the last slice of padding tokens. (#2442)

2024-08-22 23:22:03 +02:00

phi

Enable BF16 on metal. (#2380)

2024-08-01 11:05:07 +02:00

pixtral

Pixtral polishing. (#2522)

2024-09-30 21:23:54 +02:00

quantized

Add the SmolLM2 models. (#2595)

2024-11-03 17:11:12 +01:00

quantized-phi

Simplify the KvCache api. (#2207)

2024-05-23 17:07:21 +02:00

quantized-qwen2-instruct

add quantized qwen2 (#2329)

2024-07-12 10:00:03 +02:00

quantized-t5

Move the tensor-tools binary in a separate crate. (#1969)

2024-03-30 15:49:37 +01:00

qwen

Support for the new Qwen2 models. (#2257)

2024-06-07 10:51:50 +01:00

recurrent-gemma

Add a quantized version of recurrent-gemma. (#2054)

2024-04-13 20:07:01 +02:00

reinforcement-learning

Remove some unused macros. (#2618)

2024-11-15 16:46:55 +01:00

replit-code

Quantized GGUF style (#1523)

2024-01-17 10:27:58 +01:00

repvgg

Move the image tensor to the appropriate device. (#1856)

2024-03-16 22:25:46 +01:00

resnet

Move the image tensor to the appropriate device. (#1856)

2024-03-16 22:25:46 +01:00

rwkv

Fix the model path for rwkv. (#1825)

2024-03-09 11:21:48 +01:00

segformer

Update the image crate + use the re-exported version. (#1893)

2024-03-21 10:56:41 +01:00

segment-anything

onnx: fix pad, unsqueeze (#2317)

2024-07-23 23:10:57 +02:00

siglip

Add the SigLIP model. (#2515)

2024-09-28 23:48:00 +02:00

silero-vad

Clippy fixes for 1.81.0. (#2461)

2024-09-05 23:46:55 +02:00

splade

Add BertForMaskedLM to support SPLADE Models (#2550)

2024-10-07 23:28:21 +02:00

stable-diffusion

UniPC for diffusion sampling (#2684)

2025-01-01 21:34:17 +01:00

stable-diffusion-3

Support Skip Layer Guidance (SLG) for Stable Diffusion 3.5 Medium (#2590)

2024-11-01 18:10:40 +01:00

stable-lm

Avoid copying the data on squeeze and unsqueeze. (#1884)

2024-03-20 13:04:36 +01:00

starcoder2

Add the StarCoder2 model. (#1779)

2024-02-28 21:02:41 +01:00

stella-en-v5

Adds support for stella_en_v5 embedding model -400M variant (#2608)

2024-11-29 09:01:08 +01:00

t5

Expose the t5 config fields + allow t5-large. (#1987)

2024-04-01 20:58:34 +02:00

trocr

onnx: fix pad, unsqueeze (#2317)

2024-07-23 23:10:57 +02:00

vgg

Move the image tensor to the appropriate device. (#1856)

2024-03-16 22:25:46 +01:00

vit

Move the image tensor to the appropriate device. (#1856)

2024-03-16 22:25:46 +01:00

whisper

Add required feature for whisper example in Readme (#2539)

2024-10-04 14:29:55 +02:00

whisper-microphone

Fix for whisper-microphone example failure if audio isn't chunk aligned (#2645)

2024-11-27 22:35:11 +01:00

wuerstchen

…

xlm-roberta

Added XLMRobertaModel for Reranking (#2686)

2024-12-30 11:16:57 +01:00

yi

Fix token generation in bilingual models (non-English outputs) (#1668)

2024-02-06 12:03:53 +01:00

yolo-v3

Clippy fixes for 1.81.0. (#2461)

2024-09-05 23:46:55 +02:00

yolo-v8

Clippy fixes for 1.81.0. (#2461)

2024-09-05 23:46:55 +02:00

onnx_basics.rs

…