README.md

---
language:
- ko
license: llama3
library_name: transformers
tags:
- pytorch
- instruct
- finetune
- translation
base_model: maywell/Llama-3-Ko-8B-Instruct
widget:
- messages:
  - role: user
    content: Translate into Korean:Hamsters don't eat cats.
pipeline_tag: text-generation
---


# Llama 3 Translation 8B v0.170

- Eval  Loss: `0.70520`
- Train Loss: `0.49367`
- lr: `9e-05`
- optimizer: adamw
- lr_scheduler_type: cosine

## Prompt Template

```
<|begin_of_text|><|start_header_id|>user<|end_header_id|>

Translate into Korean:Hamsters don't eat cats.<|eot_id|><|start_header_id|>assistant<|end_header_id|>

햄스터는 고양이를 먹지 않습니다.<|eot_id|><|end_of_text|>
```

```
<|begin_of_text|><|start_header_id|>user<|end_header_id|>

Translate into English:햄스터는 고양이를 먹지 않습니다.<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Hamsters do not eat cats.<|eot_id|><|end_of_text|>
```

## Model Description

- **Developed by:** `lemon-mint`
- **Model type:** Llama
- **Language(s) (NLP):** English
- **License:** [llama3](https://huggingface.co/meta-llama/Meta-Llama-3-8B/blob/main/LICENSE)
- **Finetuned from model:** [maywell/Llama-3-Ko-8B-Instruct](https://huggingface.co/maywell/Llama-3-Ko-8B-Instruct)