From 9360f58d3b9dab8660189da4c9f1cabe46a38ade Mon Sep 17 00:00:00 2001 From: "mingjiang.li" Date: Thu, 20 Feb 2025 17:55:15 +0800 Subject: [PATCH] move clip ixformer to multimodal/ Signed-off-by: mingjiang.li --- README.md | 19 ++++++++++--------- .../clip/ixformer/README.md | 2 +- .../clip/ixformer/ci/prepare.sh | 0 .../clip/ixformer/inference.py | 0 4 files changed, 11 insertions(+), 10 deletions(-) rename models/{cv/classification => multimodal/vision_language_understanding}/clip/ixformer/README.md (98%) rename models/{cv/classification => multimodal/vision_language_understanding}/clip/ixformer/ci/prepare.sh (100%) rename models/{cv/classification => multimodal/vision_language_understanding}/clip/ixformer/inference.py (100%) diff --git a/README.md b/README.md index d8156156..836018da 100644 --- a/README.md +++ b/README.md @@ -18,7 +18,7 @@ DeepSparkInference将按季度进行版本更新，后续会逐步丰富模型 |------------------------|-------|-----------------------------------------------------------------------|-----------------------------------------------------------------------| | AlexNet | FP16 | [✅](models/cv/classification/alexnet/igie/README.md#fp16) | [✅](models/cv/classification/alexnet/ixrt/README.md#fp16) | | | INT8 | [✅](models/cv/classification/alexnet/igie/README.md#int8) | [✅](models/cv/classification/alexnet/ixrt/README.md#int8) | -| CLIP | FP16 | [✅](models/cv/classification/clip/igie/README.md#fp16) | [✅](models/cv/classification/clip/ixformer/README.md#fp16) | +| CLIP | FP16 | [✅](models/cv/classification/clip/igie/README.md#fp16) | | | Conformer-B | FP16 | [✅](models/cv/classification/conformer_base/igie/README.md#fp16) | | | ConvNeXt-Base | FP16 | [✅](models/cv/classification/convnext_base/igie/README.md#fp16) | [✅](models/cv/classification/convnext_base/ixrt/README.md#fp16) | | ConvNext-S | FP16 | [✅](models/cv/classification/convnext_s/igie/README.md#fp16) | | @@ -209,14 +209,15 @@ DeepSparkInference将按季度进行版本更新，后续会逐步丰富模型 ## Multimodal -| Model | vLLM | -|---------------------|-----------------------------------------------------------------------------------------| -| Chameleon-7B | [✅](models/multimodal/vision_language_understanding/chameleon_7b/vllm/README.md) | -| Fuyu-8B | [✅](models/multimodal/vision_language_understanding/fuyu_8b/vllm/README.md) | -| InternVL2-4B | [✅](models/multimodal/vision_language_understanding/intern_vl/vllm/README.md) | -| LLaVA | [✅](models/multimodal/vision_language_understanding/llava/vllm/README.md) | -| LLaVA-Next-Video-7B | [✅](models/multimodal/vision_language_understanding/llava_next_video_7b/vllm/README.md) | -| MiniCPM V2 | [✅](models/multimodal/vision_language_understanding/minicpm_v_2/vllm/README.md) | +| Model | vLLM | IxFormer | +|---------------------|-----------------------------------------------------------------------------------------|------------------------------------------------------------------------------| +| Chameleon-7B | [✅](models/multimodal/vision_language_understanding/chameleon_7b/vllm/README.md) | | +| CLIP | | [✅](models/multimodal/vision_language_understanding/clip/ixformer/README.md) | +| Fuyu-8B | [✅](models/multimodal/vision_language_understanding/fuyu_8b/vllm/README.md) | | +| InternVL2-4B | [✅](models/multimodal/vision_language_understanding/intern_vl/vllm/README.md) | | +| LLaVA | [✅](models/multimodal/vision_language_understanding/llava/vllm/README.md) | | +| LLaVA-Next-Video-7B | [✅](models/multimodal/vision_language_understanding/llava_next_video_7b/vllm/README.md) | | +| MiniCPM V2 | [✅](models/multimodal/vision_language_understanding/minicpm_v_2/vllm/README.md) | | ## NLP diff --git a/models/cv/classification/clip/ixformer/README.md b/models/multimodal/vision_language_understanding/clip/ixformer/README.md similarity index 98% rename from models/cv/classification/clip/ixformer/README.md rename to models/multimodal/vision_language_understanding/clip/ixformer/README.md index 587b1cc2..b180a045 100644 --- a/models/cv/classification/clip/ixformer/README.md +++ b/models/multimodal/vision_language_understanding/clip/ixformer/README.md @@ -1,4 +1,4 @@ -# CLIP +# CLIP (IxFormer) ## Description diff --git a/models/cv/classification/clip/ixformer/ci/prepare.sh b/models/multimodal/vision_language_understanding/clip/ixformer/ci/prepare.sh similarity index 100% rename from models/cv/classification/clip/ixformer/ci/prepare.sh rename to models/multimodal/vision_language_understanding/clip/ixformer/ci/prepare.sh diff --git a/models/cv/classification/clip/ixformer/inference.py b/models/multimodal/vision_language_understanding/clip/ixformer/inference.py similarity index 100% rename from models/cv/classification/clip/ixformer/inference.py rename to models/multimodal/vision_language_understanding/clip/ixformer/inference.py -- Gitee