Commit
•
561d5c3
1
Parent(s):
6f09d04
Update README.md
Browse files
README.md
CHANGED
|
@@ -5,11 +5,16 @@ tags:
|
|
| 5 |
- trl
|
| 6 |
- sft
|
| 7 |
- generated_from_trainer
|
|
|
|
| 8 |
datasets:
|
| 9 |
-
-
|
| 10 |
model-index:
|
| 11 |
- name: Llama-3-instruct-dansk
|
| 12 |
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
---
|
| 14 |
|
| 15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -18,7 +23,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/emillykkejensen/LLM-instruct/runs/v8wdcn55)
|
| 19 |
# Llama-3-instruct-dansk
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
- Loss: 0.9477
|
| 24 |
|
|
@@ -61,4 +66,4 @@ The following hyperparameters were used during training:
|
|
| 61 |
- Transformers 4.41.0.dev0
|
| 62 |
- Pytorch 2.2.0
|
| 63 |
- Datasets 2.19.0
|
| 64 |
-
- Tokenizers 0.19.1
|
|
|
|
| 5 |
- trl
|
| 6 |
- sft
|
| 7 |
- generated_from_trainer
|
| 8 |
+
- danish
|
| 9 |
datasets:
|
| 10 |
+
- kobprof/skolegpt-instruct
|
| 11 |
model-index:
|
| 12 |
- name: Llama-3-instruct-dansk
|
| 13 |
results: []
|
| 14 |
+
language:
|
| 15 |
+
- da
|
| 16 |
+
library_name: transformers
|
| 17 |
+
pipeline_tag: text-generation
|
| 18 |
---
|
| 19 |
|
| 20 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 23 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/emillykkejensen/LLM-instruct/runs/v8wdcn55)
|
| 24 |
# Llama-3-instruct-dansk
|
| 25 |
|
| 26 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the [kobprof/skolegpt-instruct](https://huggingface.co/datasets/kobprof/skolegpt-instruct) dataset.
|
| 27 |
It achieves the following results on the evaluation set:
|
| 28 |
- Loss: 0.9477
|
| 29 |
|
|
|
|
| 66 |
- Transformers 4.41.0.dev0
|
| 67 |
- Pytorch 2.2.0
|
| 68 |
- Datasets 2.19.0
|
| 69 |
+
- Tokenizers 0.19.1
|