Commit
•
dfbd8e1
1
Parent(s):
e09938e
Add info
Browse files
README.md
CHANGED
@@ -3,9 +3,16 @@ license: apache-2.0
|
|
3 |
base_model: mistralai/Mistral-7B-v0.1
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
6 |
model-index:
|
7 |
- name: Mistral-7B-v0.1-chat-nl
|
8 |
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
---
|
10 |
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -13,21 +20,18 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# Mistral-7B-v0.1-chat-nl
|
15 |
|
16 |
-
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the
|
17 |
It achieves the following results on the evaluation set:
|
18 |
- Loss: 1.0263
|
19 |
|
20 |
## Model description
|
|
|
|
|
|
|
21 |
|
22 |
-
More
|
|
|
23 |
|
24 |
-
## Intended uses & limitations
|
25 |
-
|
26 |
-
More information needed
|
27 |
-
|
28 |
-
## Training and evaluation data
|
29 |
-
|
30 |
-
More information needed
|
31 |
|
32 |
## Training procedure
|
33 |
|
@@ -71,4 +75,4 @@ The following hyperparameters were used during training:
|
|
71 |
- Transformers 4.36.0.dev0
|
72 |
- Pytorch 2.1.1+cu121
|
73 |
- Datasets 2.15.0
|
74 |
-
- Tokenizers 0.15.0
|
|
|
3 |
base_model: mistralai/Mistral-7B-v0.1
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
- GEITje
|
7 |
model-index:
|
8 |
- name: Mistral-7B-v0.1-chat-nl
|
9 |
results: []
|
10 |
+
datasets:
|
11 |
+
- Rijgersberg/no_robots_nl
|
12 |
+
- Rijgersberg/ultrachat_10k_nl
|
13 |
+
language:
|
14 |
+
- nl
|
15 |
+
pipeline_tag: conversational
|
16 |
---
|
17 |
|
18 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
20 |
|
21 |
# Mistral-7B-v0.1-chat-nl
|
22 |
|
23 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the Rijgersberg/no_robots_nl and Rijgersberg/ultrachat_10k_nl datasets.
|
24 |
It achieves the following results on the evaluation set:
|
25 |
- Loss: 1.0263
|
26 |
|
27 |
## Model description
|
28 |
+
In order to investigate the effect of pretraining [Rijgersberg/GEITje-7B](https://huggingface.co/Rijgersberg/GEITje-7B-chat) on the finetuning of [Rijgersberg/GEITje-7B-chat](https://huggingface.co/Rijgersberg/GEITje-7B-chat),
|
29 |
+
I also subjected the base model Mistral 7B v0.1 to the exact same training.
|
30 |
+
This model is called Mistral-7B-v0.1-chat-nl.
|
31 |
|
32 |
+
## More info
|
33 |
+
Read more about GEITje and GEITje-chat in the [📄 README](https://github.com/Rijgersberg/GEITje/blob/main/README-en.md) on GitHub.
|
34 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
35 |
|
36 |
## Training procedure
|
37 |
|
|
|
75 |
- Transformers 4.36.0.dev0
|
76 |
- Pytorch 2.1.1+cu121
|
77 |
- Datasets 2.15.0
|
78 |
+
- Tokenizers 0.15.0
|