Update README.md
Browse files
README.md
CHANGED
@@ -28,9 +28,9 @@ DeciLM 6B and its fine-tuned variant, [DeciLM 6B-Instruct](https://huggingface.c
|
|
28 |
A permissively licensed, text-to-image latent diffusion model generated by Deci's Neural Architecture Search technology.
|
29 |
DeciDiffusion generates Stable Diffusion-caliber images 3x faster.
|
30 |
|
31 |
-
## **[DeciCoder](https://huggingface.co/Deci/DeciCoder-1b):**
|
32 |
A permissively licensed 1.1 billion-parameter code generation model generated by Deci's Neural Architecture Search technology.
|
33 |
-
Equipped with a 2048-context window, DeciCoder delivers a 3.5x increase in throughput, improved accuracy on the HumanEval benchmark, and reduced memory usage compared to widely-used code generation LLMs such as SantaCoder.
|
34 |
|
35 |
## **[Infery-LLM](https://deci.ai/infery-llm-book-a-demo/):**
|
36 |
The most advanced inference SDK for LLM optimization and deployment, Infery-LLM includes unique features such as optimized kernels, continuous batching, advanced selective quantization, ultra-efficient beam search, parallel execution, and more.
|
@@ -45,12 +45,12 @@ capabilities and production-ready performance.
|
|
45 |
## **[SuperGradients](https://github.com/Deci-AI/super-gradients):**
|
46 |
An open-source library for training PyTorch-based computer vision
|
47 |
models. Developed by Deci's deep learning experts for the benefit of the
|
48 |
-
AI community
|
49 |
techniques and enables users to easily train or fine-tune SOTA computer vision models for
|
50 |
all main tasks with one training library.
|
51 |
|
52 |
## **[DataGradients](https://github.com/Deci-AI/data-gradients):**
|
53 |
-
DataGradients is an open-source Python-based library specifically
|
54 |
designed for computer vision dataset analysis. It automatically extracts
|
55 |
features from your datasets and combines them all into a single
|
56 |
user-friendly report.
|
@@ -61,7 +61,7 @@ Generative AI applications with highly accurate and efficient foundation
|
|
61 |
models. Utilize advanced tools to customize, optimize, and deploy deep learning models to
|
62 |
production.
|
63 |
|
64 |
-
Deci is powered by
|
65 |
Construction (AutoNAC™) technology. Deci's AutoNAC™ engine democratizes
|
66 |
the use of Neural Architecture Search for every organization and helps
|
67 |
teams quickly generate fast, accurate, and efficient deep learning
|
|
|
28 |
A permissively licensed, text-to-image latent diffusion model generated by Deci's Neural Architecture Search technology.
|
29 |
DeciDiffusion generates Stable Diffusion-caliber images 3x faster.
|
30 |
|
31 |
+
## **[DeciCoder 1B](https://huggingface.co/Deci/DeciCoder-1b):**
|
32 |
A permissively licensed 1.1 billion-parameter code generation model generated by Deci's Neural Architecture Search technology.
|
33 |
+
Equipped with a 2048-context window, DeciCoder 1B delivers a 3.5x increase in throughput, improved accuracy on the HumanEval benchmark, and reduced memory usage compared to widely-used code generation LLMs such as SantaCoder.
|
34 |
|
35 |
## **[Infery-LLM](https://deci.ai/infery-llm-book-a-demo/):**
|
36 |
The most advanced inference SDK for LLM optimization and deployment, Infery-LLM includes unique features such as optimized kernels, continuous batching, advanced selective quantization, ultra-efficient beam search, parallel execution, and more.
|
|
|
45 |
## **[SuperGradients](https://github.com/Deci-AI/super-gradients):**
|
46 |
An open-source library for training PyTorch-based computer vision
|
47 |
models. Developed by Deci's deep learning experts for the benefit of the
|
48 |
+
AI community, SuperGradients boosts performance with advanced
|
49 |
techniques and enables users to easily train or fine-tune SOTA computer vision models for
|
50 |
all main tasks with one training library.
|
51 |
|
52 |
## **[DataGradients](https://github.com/Deci-AI/data-gradients):**
|
53 |
+
DataGradients is an open-source, Python-based library specifically
|
54 |
designed for computer vision dataset analysis. It automatically extracts
|
55 |
features from your datasets and combines them all into a single
|
56 |
user-friendly report.
|
|
|
61 |
models. Utilize advanced tools to customize, optimize, and deploy deep learning models to
|
62 |
production.
|
63 |
|
64 |
+
Deci is powered by a groundbreaking Automated Neural Architecture
|
65 |
Construction (AutoNAC™) technology. Deci's AutoNAC™ engine democratizes
|
66 |
the use of Neural Architecture Search for every organization and helps
|
67 |
teams quickly generate fast, accurate, and efficient deep learning
|