Update README.md
Browse files
README.md
CHANGED
@@ -1,23 +1,28 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
- text: "I love AutoTrain because "
|
7 |
-
license: other
|
8 |
-
---
|
9 |
|
10 |
-
|
|
|
|
|
|
|
|
|
|
|
11 |
|
12 |
-
|
|
|
13 |
|
14 |
-
|
|
|
|
|
15 |
|
16 |
```python
|
17 |
|
18 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
19 |
|
20 |
-
model_path = "
|
21 |
|
22 |
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
23 |
model = AutoModelForCausalLM.from_pretrained(
|
@@ -37,4 +42,24 @@ response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tok
|
|
37 |
|
38 |
# Model response: "Hello! How can I assist you today?"
|
39 |
print(response)
|
40 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
license: afl-3.0
|
3 |
+
|
4 |
+
language:
|
5 |
+
- yo
|
|
|
|
|
|
|
6 |
|
7 |
+
datasets:
|
8 |
+
- afriqa
|
9 |
+
- xlsum
|
10 |
+
- menyo20k_mt
|
11 |
+
- alpaca-gpt4
|
12 |
+
---
|
13 |
|
14 |
+
# Model Description
|
15 |
+
**mistral_7b_yo_instruct** is a **text generation** model in Yorùbá.
|
16 |
|
17 |
+
## Intended uses & limitations
|
18 |
+
#### How to use
|
19 |
+
You can use this model with Transformers.
|
20 |
|
21 |
```python
|
22 |
|
23 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
24 |
|
25 |
+
model_path = "seyabde/mistral_7b_yo_instruct"
|
26 |
|
27 |
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
28 |
model = AutoModelForCausalLM.from_pretrained(
|
|
|
42 |
|
43 |
# Model response: "Hello! How can I assist you today?"
|
44 |
print(response)
|
45 |
+
```
|
46 |
+
|
47 |
+
## Eval results
|
48 |
+
Coming soon
|
49 |
+
|
50 |
+
#### Limitations and bias
|
51 |
+
This model is limited by its training dataset of entity-annotated news articles from a specific span of time. This may not generalize well for all use cases in different domains.
|
52 |
+
|
53 |
+
## Training data
|
54 |
+
This model is fine-tuned on 60k+ instruction-following demonstrations built from an aggregation of datasets ([AfriQA](https://huggingface.co/datasets/masakhane/afriqa), [XLSum](https://huggingface.co/datasets/csebuetnlp/xlsum), [MENYO-20k](https://huggingface.co/datasets/menyo20k_mt)), and translations of [Alpaca-gpt4](https://huggingface.co/datasets/vicgalle/alpaca-gpt4)).
|
55 |
+
|
56 |
+
### BibTeX entry and citation info
|
57 |
+
```
|
58 |
+
@article{
|
59 |
+
title={},
|
60 |
+
author={},
|
61 |
+
journal={},
|
62 |
+
year={},
|
63 |
+
volume={}
|
64 |
+
}
|
65 |
+
```
|