Update README.md
Browse files
README.md
CHANGED
|
@@ -78,6 +78,7 @@ The primary goal of this training was to demonstrate that with Spectrum CPT targ
|
|
| 78 |
This method has an even more pronounced effect on larger models. It is feasible to teach a model a new language by training just a quarter of the available layers.
|
| 79 |
|
| 80 |
The model has substantially improved German skills as demonstrated in RAG evaluations and numerous recognized benchmarks. In some English benchmarks, it even surpasses the Qwen2-1.5B-Instruct model.
|
|
|
|
| 81 |
**Spectrum CPT can efficiently teach a new language to a large language model (LLM) while preserving the majority of its previously acquired knowledge.**
|
| 82 |
|
| 83 |
Stay tuned for the next big models employing Spectrum CPT!
|
|
|
|
| 78 |
This method has an even more pronounced effect on larger models. It is feasible to teach a model a new language by training just a quarter of the available layers.
|
| 79 |
|
| 80 |
The model has substantially improved German skills as demonstrated in RAG evaluations and numerous recognized benchmarks. In some English benchmarks, it even surpasses the Qwen2-1.5B-Instruct model.
|
| 81 |
+
|
| 82 |
**Spectrum CPT can efficiently teach a new language to a large language model (LLM) while preserving the majority of its previously acquired knowledge.**
|
| 83 |
|
| 84 |
Stay tuned for the next big models employing Spectrum CPT!
|