Edit model card
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.

Github

Discord

Request more models

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

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."

base_model: lemon-mint/gemma-ko-1.1-2b-it pipeline_tag: text-generation

Gemma 2B Translation v0.150

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

Prompt Template

<bos><start_of_turn>user
Translate into Korean:Hamsters don't eat cats.<end_of_turn>
<start_of_turn>model
ํ–„์Šคํ„ฐ๋Š” ๊ณ ์–‘์ด๋ฅผ ๋จน์ง€ ์•Š์Šต๋‹ˆ๋‹ค.<eos>
<bos><start_of_turn>user
Translate into English:ํ–„์Šคํ„ฐ๋Š” ๊ณ ์–‘์ด๋ฅผ ๋จน์ง€ ์•Š์Šต๋‹ˆ๋‹ค.<end_of_turn>
<start_of_turn>model
Hamsters do not eat cats.<eos>

Model Description

Downloads last month
52
GGUF
Model size
2.51B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API
Unable to determine this model's library. Check the docs .