Update README.md
Browse files
README.md
CHANGED
@@ -1,14 +1,20 @@
|
|
1 |
---
|
2 |
-
license:
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
base_model: nisten/shqiponja-15b-v1
|
7 |
model-index:
|
8 |
-
- name:
|
9 |
results: []
|
|
|
|
|
|
|
10 |
---
|
11 |
|
|
|
|
|
|
|
12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
should probably proofread and complete it, then remove this comment. -->
|
14 |
|
@@ -75,5 +81,4 @@ The following hyperparameters were used during training:
|
|
75 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
76 |
- lr_scheduler_type: cosine
|
77 |
- lr_scheduler_warmup_steps: 10
|
78 |
-
- num_epochs: 3
|
79 |
-
|
|
|
1 |
---
|
2 |
+
license: gpl-3.0
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
base_model: nisten/shqiponja-15b-v1
|
7 |
model-index:
|
8 |
+
- name: shqiponja-15
|
9 |
results: []
|
10 |
+
datasets:
|
11 |
+
- iamshnoo/alpaca-cleaned-albanian
|
12 |
+
- noxneural/lilium_albanicum_eng_alb
|
13 |
---
|
14 |
|
15 |
+
|
16 |
+
**15.6b 2expert MoE**
|
17 |
+
|
18 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
19 |
should probably proofread and complete it, then remove this comment. -->
|
20 |
|
|
|
81 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
82 |
- lr_scheduler_type: cosine
|
83 |
- lr_scheduler_warmup_steps: 10
|
84 |
+
- num_epochs: 3
|
|