Update README.md
Browse files
README.md
CHANGED
|
@@ -11,6 +11,8 @@ license: apache-2.0
|
|
| 11 |
|
| 12 |
DCLM-1B is a 1.4 billion parameter language model trained on the DCLM-Baseline dataset, which was curated as part of the DataComp for Language Models (DCLM) benchmark. This model is designed to showcase the effectiveness of systematic data curation techniques for improving language model performance.
|
| 13 |
|
|
|
|
|
|
|
| 14 |
## Evaluation
|
| 15 |
|
| 16 |
We evaluate DCLM-1B using the [llm-foundry](https://github.com/mosaicml/llm-foundry) eval suite, and compare to recently released small models on key benchmarks.
|
|
|
|
| 11 |
|
| 12 |
DCLM-1B is a 1.4 billion parameter language model trained on the DCLM-Baseline dataset, which was curated as part of the DataComp for Language Models (DCLM) benchmark. This model is designed to showcase the effectiveness of systematic data curation techniques for improving language model performance.
|
| 13 |
|
| 14 |
+
The instruction tuned version of this model is available here: https://huggingface.co/TRI-ML/DCLM-1B-IT
|
| 15 |
+
|
| 16 |
## Evaluation
|
| 17 |
|
| 18 |
We evaluate DCLM-1B using the [llm-foundry](https://github.com/mosaicml/llm-foundry) eval suite, and compare to recently released small models on key benchmarks.
|