RichardErkhov
/

lemon-mint_-_gemma-2b-translation-v0.103-4bits

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co./docs/hub/model-cards#model-card-metadata)

Quantization made by Richard Erkhov.

Request more models

gemma-2b-translation-v0.103 - bnb 4bits

Model creator: https://huggingface.co./lemon-mint/
Original model: https://huggingface.co./lemon-mint/gemma-2b-translation-v0.103/

Original model description:

library_name: transformers language: - ko license: gemma tags: - gemma - pytorch - instruct - finetune - translation widget: - messages: - role: user content: "Hamsters don't eat cats." inference: parameters: max_new_tokens: 2048 base_model: beomi/gemma-ko-2b datasets: - traintogpb/aihub-flores-koen-integrated-sparta-30k pipeline_tag: text-generation

Gemma 2B Translation v0.103

Eval Loss: 1.34507
Train Loss: 1.40326
lr: 3e-05
optimizer: adamw
lr_scheduler_type: cosine

Prompt Template

<bos>### English

Hamsters don't eat cats.

### Korean

햄스터는 고양이를 먹지 않습니다.<eos>

Model Description

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

Downloads last month: 84

Safetensors

Model size

1.55B params

Tensor type

F32

·

FP16

·

U8

·

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.