jmprcp commited on
Commit
3ba07fe
1 Parent(s): acd21e2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +32 -9
README.md CHANGED
@@ -4,23 +4,46 @@ language:
4
  - en
5
  - de
6
  - fr
 
7
  - pt
8
- - es
9
- - it
10
  - nl
11
  - ru
12
- - zh
13
  - ko
 
 
14
  metrics:
15
  - comet
16
- pipeline_tag: text-generation
17
  ---
18
- # Tower-Base-7B-v0.1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
 
20
- ## Model Architecture
21
 
22
- ## License
23
 
24
- ## Intended Uses
25
 
26
- ## Limitations
 
4
  - en
5
  - de
6
  - fr
7
+ - zh
8
  - pt
 
 
9
  - nl
10
  - ru
 
11
  - ko
12
+ - it
13
+ - es
14
  metrics:
15
  - comet
16
+ pipeline_tag: translation
17
  ---
18
+ # Model Card for TowerBase-7B-v0.1
19
+
20
+ ## Model Details
21
+
22
+ ### Model Description
23
+
24
+ TowerBase-7B is a language model that results from continuing the pretraining of Llama 2 on a mix of 20 billion tokens of monolingual data from non-English languages, and bilingual data. TowerBase-7B-v0.1 is the first model in the series.
25
+ The resulting model shows improved performance on the supported languages, while maintaining Llama's capabilities on English. It is particularly well-suited for fine-tuning on translation and related tasks: check out [TowerInstruct](https://huggingface.co/Unbabel/TowerInstruct-7B-v0.1)
26
+ We will release more details in the upcoming technical report.
27
+
28
+ - **Developed by:** Unbabel, Instituto Superior Técnico, CentraleSupélec University of Paris-Saclay
29
+ - **Model type:** A 7B parameter model built on top of Llama 2 by continuing pretraining on multilingual data.
30
+ - **Language(s) (NLP):** English, Portuguese, Spanish, French, German, Dutch, Italian, Korean, Chinese, Russian
31
+ - **License:** CC-BY-NC-4.0
32
+
33
+ ## Intended uses & limitations
34
+
35
+ The model is intended for research purposes in the 10 languages it supports.
36
+ The model is able to perform well on translation and related tasks (e.g., APE, GEC) on a few-shot regime.
37
+ It can also be fine-tuned to perform these tasks in a zero-shot fashion (see [TowerInstruct](https://huggingface.co/Unbabel/TowerInstruct-7B-v0.1), as well as other multilingual tasks.
38
+
39
+ ### Out-of-Scope Use
40
+
41
+ The model is not guaranteed to perform well for languages other than the 10 languages it supports.
42
 
43
+ ## Bias, Risks, and Limitations
44
 
45
+ TowerBase-v0.1 has not been aligned to human preferences, so the model may generate problematic outputs (e.g., hallucinations, harmful content, or false statements).
46
 
47
+ ## Citation
48
 
49
+ To be completed.