add 13B model link
Browse files
README.md
CHANGED
|
@@ -168,6 +168,8 @@ We benchmarked our model on the following tasks: [BoolQ](https://huggingface.co/
|
|
| 168 |
| LoRA LLaMA 7B | 63.9 | 51.3 | 48.9 | 31.4 | 8bit | 0.65 seconds |
|
| 169 |
| LoRA LLaMA 13B | 70 | 63.93 | 51.6 | 50.4 | 8bit | 1.2 seconds |
|
| 170 |
|
|
|
|
|
|
|
| 171 |
Overall our LoRA model is less performant than the original model from Meta, if we compare the results from the [original paper](https://arxiv.org/pdf/2302.13971.pdf).
|
| 172 |
|
| 173 |
The performance degradation is due to the fact we load the model in 8bit and we use the adapters from the LoRA training.
|
|
|
|
| 168 |
| LoRA LLaMA 7B | 63.9 | 51.3 | 48.9 | 31.4 | 8bit | 0.65 seconds |
|
| 169 |
| LoRA LLaMA 13B | 70 | 63.93 | 51.6 | 50.4 | 8bit | 1.2 seconds |
|
| 170 |
|
| 171 |
+
__Link to the 13B model:__ [wordcab/llama-natural-instructions-13b](https://huggingface.co/wordcab/llama-natural-instructions-13b)
|
| 172 |
+
|
| 173 |
Overall our LoRA model is less performant than the original model from Meta, if we compare the results from the [original paper](https://arxiv.org/pdf/2302.13971.pdf).
|
| 174 |
|
| 175 |
The performance degradation is due to the fact we load the model in 8bit and we use the adapters from the LoRA training.
|