lemon-mint
/

Llama-3-Translation-8B-v0.180

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Edit model card

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

Downloads last month: 220

Safetensors

Model size

8.17B params

Tensor type

BF16

·

Inference Examples

Text Generation

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for lemon-mint/Llama-3-Translation-8B-v0.180

Base model

maywell/Llama-3-Ko-Luxia-Instruct

Finetuned

(3)

this model

Quantizations