Downloads · 30 days
20
22% of all-time downloads
humob-task2_dataset-ds-in07-out01-len01
avsolatorio/humob-task2_dataset-ds-in07-out01-len01
humob-task2_dataset-ds-in07-out01-len01 is a text generation model from avsolatorio. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
The version of the model until revision=7a9877f8576882b453d9e1f40a693d1a1810af0e is fine-tuned from avsolatorio/humob-task1dataset-ds-in07-out01-len01:revision=3a0d2288ea2da91dff1a4ddeb6a111b43504098e
All-time downloads
93
Public
Repo size
17.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt461 MB · 50%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- mit
- Model type
- gpt2
- Access
- Public
- Created
- Aug 13, 2023
- Updated
- Aug 16, 2023
- SHA
- 56b3a5ae
Try a prompt
Model card
From the Hugging Face model README
The version of the model until revision=7a9877f8576882b453d9e1f40a693d1a1810af0e is fine-tuned from avsolatorio/humob-task1_dataset-ds-in07-out01-len01:revision=3a0d2288ea2da91dff1a4ddeb6a111b43504098e
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
# Use the base model based on the specific version
# trained on the task1_dataset
model = AutoModelForCausalLM.from_pretrained(
"avsolatorio/humob-task1_dataset-ds-in07-out01-len01",
revision="3a0d2288ea2da91dff1a4ddeb6a111b43504098e",
)
# model = model.to(device)
Note that we use a custom tokenizer. Refer to commit version aedad132deb8eef2085b04c083d6844b0f071b35 in the https://github.com/avsolatorio/humob-challenge-2023 repository for the implementation. The raw dataset was also processed and split into the train, valid, and test sets using the Data Generation.ipynb notebook under the same commit version.
- Task
- Text Generation
- Library
- transformers
- Type
- gpt2
- License
- mit
- Created
- Aug 13, 2023
- Updated
- Aug 16, 2023