RichardErkhov/lemon-mint_-_gemma-2b-translation-v0.103-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gemma-2b-translation-v0.103 - GGUF

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

Name	Quant method	Size
gemma-2b-translation-v0.103.Q2_K.gguf	Q2_K	1.08GB
gemma-2b-translation-v0.103.IQ3_XS.gguf	IQ3_XS	1.16GB
gemma-2b-translation-v0.103.IQ3_S.gguf	IQ3_S	1.2GB
gemma-2b-translation-v0.103.Q3_K_S.gguf	Q3_K_S	1.2GB
gemma-2b-translation-v0.103.IQ3_M.gguf	IQ3_M	1.22GB
gemma-2b-translation-v0.103.Q3_K.gguf	Q3_K	1.29GB
gemma-2b-translation-v0.103.Q3_K_M.gguf	Q3_K_M	1.29GB
gemma-2b-translation-v0.103.Q3_K_L.gguf	Q3_K_L	1.36GB
gemma-2b-translation-v0.103.IQ4_XS.gguf	IQ4_XS	1.4GB
gemma-2b-translation-v0.103.Q4_0.gguf	Q4_0	1.44GB
gemma-2b-translation-v0.103.IQ4_NL.gguf	IQ4_NL	1.45GB
gemma-2b-translation-v0.103.Q4_K_S.gguf	Q4_K_S	1.45GB
gemma-2b-translation-v0.103.Q4_K.gguf	Q4_K	1.52GB
gemma-2b-translation-v0.103.Q4_K_M.gguf	Q4_K_M	1.52GB
gemma-2b-translation-v0.103.Q4_1.gguf	Q4_1	1.56GB
gemma-2b-translation-v0.103.Q5_0.gguf	Q5_0	1.68GB
gemma-2b-translation-v0.103.Q5_K_S.gguf	Q5_K_S	1.68GB
gemma-2b-translation-v0.103.Q5_K.gguf	Q5_K	1.71GB
gemma-2b-translation-v0.103.Q5_K_M.gguf	Q5_K_M	1.71GB
gemma-2b-translation-v0.103.Q5_1.gguf	Q5_1	1.79GB
gemma-2b-translation-v0.103.Q6_K.gguf	Q6_K	1.92GB

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