feat: add hugging face candle

src/SUMMARY.md

@@ -62,4 +62,5 @@
 - [ML](ml/mod.md)
   - [Large Language Model](ml/large-language-model.md)
   - [Stable Diffusion](ml/stable-diffusion.md)
+  - [Hugging Face - Candle](ml/huggingface-candle.md)
 - [Bye](bye.md)

src/ml/huggingface-candle.md

@@ -0,0 +1,45 @@
+# Hugging Face - Candle
+
+> [https://github.com/huggingface/candle]()
+
+A minimalist ML framework for Rust with a focus on performance (including GPU support) and ease of use.
+
+### Examples
+
+These online demos run entirely in your browser:
+
+- [yolo](https://huggingface.co/spaces/lmz/candle-yolo): pose estimation and
+  object recognition.
+- [whisper](https://huggingface.co/spaces/lmz/candle-whisper): text to speech.
+- [LLaMA2](https://huggingface.co/spaces/lmz/candle-llama2): text generation.
+- [LLaMA and LLaMA-v2](https://github.com/huggingface/candle/blob/main/candle-examples/examples/llama/): general LLM.
+- [Falcon](https://github.com/huggingface/candle/blob/main/candle-examples/examples/falcon/): general LLM.
+- [StarCoder](https://github.com/huggingface/candle/blob/main/candle-examples/examples/bigcode/): LLM specialized to code
+  generation.
+- [Quantized LLaMA](https://github.com/huggingface/candle/blob/main/candle-examples/examples/quantized/): quantized version of
+  the LLaMA model using the same quantization techniques as
+  [llama.cpp](https://github.com/ggerganov/llama.cpp).
+
+<img src="https://github.com/huggingface/candle/raw/main/candle-examples/examples/quantized/assets/aoc.gif" width="600">
+
+- [Stable Diffusion](https://github.com/huggingface/candle/blob/main/candle-examples/examples/stable-diffusion/): text to
+  image generative model, support for the 1.5, 2.1, and SDXL 1.0 versions.
+
+<img src="https://github.com/huggingface/candle/raw/main/candle-examples/examples/stable-diffusion/assets/stable-diffusion-xl.jpg" width="200">
+
+- [yolo-v3](https://github.com/huggingface/candle/blob/main/candle-examples/examples/yolo-v3/) and
+  [yolo-v8](https://github.com/huggingface/candle/blob/main/candle-examples/examples/yolo-v8/): object detection and pose
+  estimation models.
+
+<img src="https://github.com/huggingface/candle/raw/main/candle-examples/examples/yolo-v8/assets/bike.od.jpg" width="200"><img src="https://github.com/huggingface/candle/raw/main/candle-examples/examples/yolo-v8/assets/bike.pose.jpg" width="200">
+
+- [segment-anything](https://github.com/huggingface/candle/blob/main/candle-examples/examples/segment-anything/): image
+  segmentation model with prompt.
+
+<img src="https://github.com/huggingface/candle/raw/main/candle-examples/examples/segment-anything/assets/sam_merged.jpg" width="200">
+
+- [Whisper](https://github.com/huggingface/candle/blob/main/candle-examples/examples/whisper/): speech recognition model.
+- [Bert](https://github.com/huggingface/candle/blob/main/candle-examples/examples/bert/): useful for sentence embeddings.
+- [DINOv2](https://github.com/huggingface/candle/blob/main/candle-examples/examples/dinov2/): computer vision model trained
+  using self-supervision (can be used for imagenet classification, depth
+  evaluation, segmentation).

src/ml/mod.md

@@ -10,3 +10,4 @@
 
 - [Large Language Model](large-language-model.md)
 - [Stable Diffusion](stable-diffusion.md)
+- [Hugging Face - Candle](huggingface-candle.md)