Downloads · 30 days
13
2% of all-time downloads
Llama-3-Translation-8B-v0.180
lemon-mint/Llama-3-Translation-8B-v0.180
Llama-3-Translation-8B-v0.180 is a text generation model from lemon-mint. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as llama3.
- Eval Loss: 0.69922 - Train Loss: 0.65752 - lr: 8e-05 - optimizer: adamw - lrschedulertype: cosine
All-time downloads
822
Public
Parameters
8.2B
16.3 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors16.3 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- llama3
- Model type
- llama
- Access
- Public
- Created
- May 7, 2024
- Updated
- May 7, 2024
- SHA
- 672ed875
Base models
Model card
From the Hugging Face model README
Llama 3 Translation 8B v0.180
- Eval Loss:
0.69922 - Train Loss:
0.65752 - lr:
8e-05 - optimizer: adamw
- lr_scheduler_type: cosine
Prompt Template
<|begin_of_text|><|im_start|>user
Translate into Korean:Hamsters don't eat cats.<|im_end|>
<|im_start|>assistant
햄스터는 고양이를 먹지 않습니다.<|im_end|><|end_of_text|>
<|begin_of_text|><|im_start|>user
Translate into English:햄스터는 고양이를 먹지 않습니다.<|im_end|>
<|im_start|>assistant
Hamsters do not eat cats.<|im_end|><|end_of_text|>
Model Description
- Developed by:
lemon-mint - Model type: Llama
- Language(s) (NLP): English
- License: llama3
- Finetuned from model: maywell/Llama-3-Ko-Luxia-Instruct
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- llama3
- Languages
- ko
- Created
- May 7, 2024
- Updated
- May 7, 2024