Update README.md
Browse files
README.md
CHANGED
|
@@ -17,6 +17,8 @@ Poro 2 70B SFT is a supervised fine-tuned model created from the Poro 2 70B Base
|
|
| 17 |
|
| 18 |
Poro 2 was created in a collaboration between [AMD Silo AI](https://www.amd.com/en/solutions/ai/silo-ai.html), the [TurkuNLP group](https://turkunlp.org/) of the University of Turku, and [High Performance Language Technologies](https://hplt-project.org/) (HPLT). Training was conducted on the [LUMI supercomputer](https://www.lumi-supercomputer.eu/), using compute resources generously provided by [CSC](https://csc.fi/) - IT Center for Science, Finland.
|
| 19 |
|
|
|
|
|
|
|
| 20 |
## Poro 2 Model Family
|
| 21 |
|
| 22 |
The Poro 2 model family includes both 8B and 70B models, and there are three different versions released of the Poro 2 models: a base model, a post-training SFT-only checkpoint, and the final instruct model which is the SFT model plus a round of DPO.
|
|
|
|
| 17 |
|
| 18 |
Poro 2 was created in a collaboration between [AMD Silo AI](https://www.amd.com/en/solutions/ai/silo-ai.html), the [TurkuNLP group](https://turkunlp.org/) of the University of Turku, and [High Performance Language Technologies](https://hplt-project.org/) (HPLT). Training was conducted on the [LUMI supercomputer](https://www.lumi-supercomputer.eu/), using compute resources generously provided by [CSC](https://csc.fi/) - IT Center for Science, Finland.
|
| 19 |
|
| 20 |
+
For more details on our training and data generation pipeline, check out our [Continued Pretraining Playbook](https://rocm.blogs.amd.com/artificial-intelligence/multilingual-continued-pretraining/README.html).
|
| 21 |
+
|
| 22 |
## Poro 2 Model Family
|
| 23 |
|
| 24 |
The Poro 2 model family includes both 8B and 70B models, and there are three different versions released of the Poro 2 models: a base model, a post-training SFT-only checkpoint, and the final instruct model which is the SFT model plus a round of DPO.
|