Downloads · 30 days
21
5% of all-time downloads
tagalog-seallm-7b-v1
922-Narra/tagalog-seallm-7b-v1
tagalog-seallm-7b-v1 is a text generation model from 922-Narra. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Yet another archived test/toy model, fine-tuned on a synthetic Tagalog dataset partially produced by Mistral based on this dataset Base: SeaLLM
All-time downloads
457
Public
Parameters
7.4B
29.5 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin14.8 GB · 50%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- mistral
- Access
- Public
- Created
- Feb 11, 2024
- Updated
- Jan 31, 2025
- SHA
- b7d6dc7f
Try a prompt
Base models
Model card
From the Hugging Face model README
AKA Tagamistral-7b-v1:
- Yet another archived test/toy model, fine-tuned on a synthetic Tagalog dataset partially produced by Mistral based on this dataset
- Base: SeaLLM
- GGUF
USAGE
This is meant to be mainly a chat model.
Best results with "Human" and "Assistant" and prompt with Tagalog. Example:
"Ito ay isang chat log sa pagitan ng AI Assistant na nagta-Tagalog at isang Pilipino. Magsimula ng chat:\nHuman: Hello po?\nAssistant:"
HYPERPARAMS
- Trained for ~1 epoch
- rank: 32
- lora alpha: 32
- lora dropout: 0
- lr: 2e-4
- batch size: 2
- grad steps: 4
This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.
WARNINGS AND DISCLAIMERS
There is still a chance that the model may switch to English or Taglish.
It is possible that the Tagalog capability still comes mostly from the fine-tuned base more than the dataset.
Finally, this model is not guaranteed to output aligned or safe outputs nor is it meant for production use - use at your own risk!
- Task
- Text Generation
- Library
- transformers
- Type
- mistral
- License
- apache-2.0
- Languages
- en
- Created
- Feb 11, 2024
- Updated
- Jan 31, 2025