Downloads · 30 days
13
12% of all-time downloads
tinyllama-en_ja-translation-v3
NilanE/tinyllama-en_ja-translation-v3
tinyllama-en_ja-translation-v3 is a text generation model from NilanE. 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.
Trained for 2 epochs on NilanE/ParallelFiction-JaEn-100k using QLoRA. CPO tune is in-progress.
All-time downloads
105
Public
Parameters
1.1B
2.2 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors2.2 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- llama
- Access
- Public
- Created
- Apr 24, 2024
- Updated
- Jun 30, 2024
- SHA
- 6f8e6ef2
Try a prompt
Base models
Model card
From the Hugging Face model README
Trained for 2 epochs on NilanE/ParallelFiction-Ja_En-100k using QLoRA. CPO tune is in-progress.
Input should be 500-1000 tokens long. Make sure to set 'do_sample = False' if using HF transformers for inference, or otherwise set temperature to 0 for deterministic outputs.
Prompt format:
Translate this from Japanese to English:
### JAPANESE:
{source_text}
### ENGLISH:
Footnote:
This is an independantly-developed project. If anyone is interested in sponsoring further research please contact [email protected]. Questions about model usage can be asked in the disscussion tab.
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- apache-2.0
- Languages
- en, ja
- Created
- Apr 24, 2024
- Updated
- Jun 30, 2024