Update README.md
Browse files
README.md
CHANGED
@@ -7,17 +7,9 @@ sdk: static
|
|
7 |
pinned: false
|
8 |
license: apache-2.0
|
9 |
---
|
10 |
-
## About Us
|
11 |
|
12 |
-
Deci
|
13 |
-
development barriers and attain production-grade performance and
|
14 |
-
efficient inference faster.
|
15 |
|
16 |
-
If you have questions, please feel free to contact us through our [website](https://deci.ai/contact/?utm_campaign=repos&utm_source=hugging-face&utm_medium=org-card),
|
17 |
-
reach out to us on [Twitter](https://twitter.com/deci_ai),
|
18 |
-
or join our Deep
|
19 |
-
Learning Daily [Discord
|
20 |
-
community](https://discord.com/invite/p9ecgRhDR8/).
|
21 |
|
22 |
## **[DeciLM-7B](https://huggingface.co/Deci/DeciLM-7B):**
|
23 |
A 7.04 billion-parameter decoder-only text generation model, licensed under Apache 2.0. DeciLM-7B is not only the most accurate 7B base model to date, but it also currently outpaces all models in its class with a throughput that is up to 4.4x that of Mistral-7B's. DeciLM-7B’s architecture is the result of Deci's Neural Architecture Search technology. The model was fine-tuned using LoRA on the SlimOrca dataset, creating [DeciLM-7B-instruct](https://huggingface.co/Deci/DeciLM-7B-instruct).
|
|
|
7 |
pinned: false
|
8 |
license: apache-2.0
|
9 |
---
|
|
|
10 |
|
11 |
+
## Deci was acquired by Nvidia Corporation of Santa Clara, CA. in May 2024.
|
|
|
|
|
12 |
|
|
|
|
|
|
|
|
|
|
|
13 |
|
14 |
## **[DeciLM-7B](https://huggingface.co/Deci/DeciLM-7B):**
|
15 |
A 7.04 billion-parameter decoder-only text generation model, licensed under Apache 2.0. DeciLM-7B is not only the most accurate 7B base model to date, but it also currently outpaces all models in its class with a throughput that is up to 4.4x that of Mistral-7B's. DeciLM-7B’s architecture is the result of Deci's Neural Architecture Search technology. The model was fine-tuned using LoRA on the SlimOrca dataset, creating [DeciLM-7B-instruct](https://huggingface.co/Deci/DeciLM-7B-instruct).
|