RichardErkhov/lemon-mint_-_gemma-2b-translation-v0.150-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gemma-2b-translation-v0.150 - GGUF

• —Model creator: https://huggingface.co/lemon-mint/
• —Original model: https://huggingface.co/lemon-mint/gemma-2b-translation-v0.150/

Original model description: --- library_name: transformers language:

• —ko license: gemma tags:
• —gemma
• —pytorch
• —instruct
• —finetune
• —translation widget:
• —messages:
• —role: user content: "Translate into Korean:Hamsters don't eat cats."

basemodel: lemon-mint/gemma-ko-1.1-2b-it pipelinetag: text-generation ---

Gemma 2B Translation v0.150

• —Eval Loss: 0.93082
• —Train Loss: 0.81643
• —lr: 9e-05
• —optimizer: adamw
• —lrschedulertype: cosine

Prompt Template

<bos><start_of_turn>user
Translate into Korean:Hamsters don't eat cats.<end_of_turn>
<start_of_turn>model
햄스터는 고양이를 먹지 않습니다.<eos>

<bos><start_of_turn>user
Translate into English:햄스터는 고양이를 먹지 않습니다.<end_of_turn>
<start_of_turn>model
Hamsters do not eat cats.<eos>

Model Description

• —Developed by: lemon-mint
• —Model type: Gemma
• —Language(s) (NLP): English
• —License: gemma-terms-of-use
• —Finetuned from model: lemon-mint/gemma-ko-1.1-2b-it