nicholasKluge
commited on
Commit
•
3f02a48
1
Parent(s):
121149e
Upload README.md
Browse files
README.md
CHANGED
@@ -38,7 +38,8 @@ inference:
|
|
38 |
|
39 |
`Aira-Instruct-PT-124M` is a instruction-tuned GPT-style model based on [GPT-2](https://huggingface.co/pierreguillou/gpt2-small-portuguese). The model was trained with a dataset composed of `prompt`, `completions`, generated via the [Self-Instruct](https://github.com/yizhongw/self-instruct) framework. `Aira-Instruct-PT-124M` instruction-tuning was achieved via conditional text generation.
|
40 |
|
41 |
-
The dataset used to train this model combines
|
|
|
42 |
|
43 |
Check our gradio-demo in [Spaces](https://huggingface.co/spaces/nicholasKluge/Aira-Demo).
|
44 |
|
@@ -100,7 +101,6 @@ responses = aira.generate(**inputs,
|
|
100 |
print(f"Question: 👤 {question}\n")
|
101 |
|
102 |
for i, response in enumerate(responses):
|
103 |
-
# print only the response and remove the question
|
104 |
print(f'Response {i+1}: 🤖 {tokenizer.decode(response, skip_special_tokens=True).replace(question, "")}')
|
105 |
```
|
106 |
|
@@ -137,4 +137,4 @@ The model will output something like:
|
|
137 |
|
138 |
## License
|
139 |
|
140 |
-
The `Aira-Instruct-PT-124M` is licensed under the Apache License, Version 2.0. See the [LICENSE](LICENSE) file for more details.
|
|
|
38 |
|
39 |
`Aira-Instruct-PT-124M` is a instruction-tuned GPT-style model based on [GPT-2](https://huggingface.co/pierreguillou/gpt2-small-portuguese). The model was trained with a dataset composed of `prompt`, `completions`, generated via the [Self-Instruct](https://github.com/yizhongw/self-instruct) framework. `Aira-Instruct-PT-124M` instruction-tuning was achieved via conditional text generation.
|
40 |
|
41 |
+
The dataset used to train this model combines the following sources of data: the [`synthetic-instruct-gptj-pairwise`](https://huggingface.co/datasets/Dahoas/synthetic-instruct-gptj-pairwise) dataset, the [`databricks_dolly_15k`](https://huggingface.co/datasets/HuggingFaceH4/databricks_dolly_15k) dataset, the [`instruction-dataset`](https://huggingface.co/datasets/HuggingFaceH4/instruction-dataset) dataset, and a subset of [Aira's](https://github.com/Nkluge-correa/Aira-EXPERT) fine-tuning dataset, focused on Q&A related to Ethics, AI, AI safety, and other related topics. The dataset is available in both Portuguese and English.
|
42 |
+
|
43 |
|
44 |
Check our gradio-demo in [Spaces](https://huggingface.co/spaces/nicholasKluge/Aira-Demo).
|
45 |
|
|
|
101 |
print(f"Question: 👤 {question}\n")
|
102 |
|
103 |
for i, response in enumerate(responses):
|
|
|
104 |
print(f'Response {i+1}: 🤖 {tokenizer.decode(response, skip_special_tokens=True).replace(question, "")}')
|
105 |
```
|
106 |
|
|
|
137 |
|
138 |
## License
|
139 |
|
140 |
+
The `Aira-Instruct-PT-124M` is licensed under the Apache License, Version 2.0. See the [LICENSE](LICENSE) file for more details.
|