lemon-mint
/

Llama-3-Translation-8B-v0.170

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

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
Finetuned from model: maywell/Llama-3-Ko-8B-Instruct

Downloads last month: 4

Safetensors

Model size

8.03B params

Tensor type

BF16

·

Inference Providers NEW

Text Generation

This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for lemon-mint/Llama-3-Translation-8B-v0.170

Base model

maywell/Llama-3-Ko-8B-Instruct

Finetuned

(5)

this model