Update README.md
Browse files
README.md
CHANGED
|
@@ -139,10 +139,14 @@ To reduce toxic content, the pretrained version of thiis model was trained with
|
|
| 139 |
|
| 140 |
### Finetuning
|
| 141 |
|
| 142 |
-
Training was conducted on RTX 4080 using Unsloth framework https://github.com/unslothai/unsloth
|
| 143 |
Training script is available in this repo.
|
| 144 |
|
| 145 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 146 |
|
| 147 |
[llama-7b-finnish-instruct-v0.1](https://huggingface.co/Finnish-NLP/llama-7b-finnish-instruct-v0.1):
|
| 148 |
|
|
|
|
| 139 |
|
| 140 |
### Finetuning
|
| 141 |
|
| 142 |
+
Training was conducted on RTX 4080 using Unsloth framework https://github.com/unslothai/unsloth \
|
| 143 |
Training script is available in this repo.
|
| 144 |
|
| 145 |
|
| 146 |
+
## Evaluation results
|
| 147 |
+
|
| 148 |
+
This model was evaluated using [FIN-bench by TurkuNLP](https://github.com/TurkuNLP/FIN-bench) with zero-shot setting, but \
|
| 149 |
+
the evaluation script had some problems running succesfully, so the results reported below should perhaps be viewed with some caution.
|
| 150 |
|
| 151 |
[llama-7b-finnish-instruct-v0.1](https://huggingface.co/Finnish-NLP/llama-7b-finnish-instruct-v0.1):
|
| 152 |
|