jgchaparro commited on
Commit
2efa5ed
·
verified ·
1 Parent(s): 16e1e06

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -14
README.md CHANGED
@@ -15,23 +15,13 @@ should probably proofread and complete it, then remove this comment. -->
15
  [<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/tsakonian_ai/mistral-andalusian/runs/mh4xznd3)
16
  # MistrAND-7B-v1
17
 
18
- MistrAND 7B v2 is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the [OASST2 dataset](https://huggingface.co/datasets/OpenAssistant/oasst2) converted to a [custom Andalusian Spanish orthography](https://jgchaparro.github.io/posts/Una-propuesta-ortogr%C3%A1fica-para-el-habla-andaluza/).
19
 
20
- This model is
21
- It achieves the following results on the evaluation set:
22
- - Loss: 0.6530
23
 
24
- ## Model description
25
 
26
- More information needed
27
-
28
- ## Intended uses & limitations
29
-
30
- More information needed
31
-
32
- ## Training and evaluation data
33
-
34
- More information needed
35
 
36
  ## Training procedure
37
 
 
15
  [<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/tsakonian_ai/mistral-andalusian/runs/mh4xznd3)
16
  # MistrAND-7B-v1
17
 
18
+ MistrAND 7B v1 is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the [OASST2 dataset](https://huggingface.co/datasets/OpenAssistant/oasst2) converted to a [custom Andalusian Spanish orthography](https://jgchaparro.github.io/posts/Una-propuesta-ortogr%C3%A1fica-para-el-habla-andaluza/).
19
 
20
+ This project is part of the Master's Degree Final Thesis titled `Conservational AI for endangered languages: a preservation strategy for Tsakonian Greek upon the Andalusian Spanish case`, aiming to preserve endangered languages by storing them in QLoRA adapters for unlimited use in the future.
 
 
21
 
22
+ ## Links
23
 
24
+ * [Model repository on GitHub](https://github.com/jgchaparro/MistrAND-7B-v1)
 
 
 
 
 
 
 
 
25
 
26
  ## Training procedure
27