RichardErkhov/Samvardhan777_-_gemma-2b-mt-German-to-English-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gemma-2b-mt-German-to-English - GGUF

• Model creator: https://huggingface.co/Samvardhan777/
• Original model: https://huggingface.co/Samvardhan777/gemma-2b-mt-German-to-English/

Name	Quant method	Size
gemma-2b-mt-German-to-English.Q2_K.gguf	Q2_K	1.08GB
gemma-2b-mt-German-to-English.Q3_K_S.gguf	Q3_K_S	1.2GB
gemma-2b-mt-German-to-English.Q3_K.gguf	Q3_K	1.29GB
gemma-2b-mt-German-to-English.Q3_K_M.gguf	Q3_K_M	1.29GB
gemma-2b-mt-German-to-English.Q3_K_L.gguf	Q3_K_L	1.36GB
gemma-2b-mt-German-to-English.IQ4_XS.gguf	IQ4_XS	1.4GB
gemma-2b-mt-German-to-English.Q4_0.gguf	Q4_0	1.44GB
gemma-2b-mt-German-to-English.IQ4_NL.gguf	IQ4_NL	1.45GB
gemma-2b-mt-German-to-English.Q4_K_S.gguf	Q4_K_S	1.45GB
gemma-2b-mt-German-to-English.Q4_K.gguf	Q4_K	1.52GB
gemma-2b-mt-German-to-English.Q4_K_M.gguf	Q4_K_M	1.52GB
gemma-2b-mt-German-to-English.Q4_1.gguf	Q4_1	1.56GB
gemma-2b-mt-German-to-English.Q5_0.gguf	Q5_0	1.68GB
gemma-2b-mt-German-to-English.Q5_K_S.gguf	Q5_K_S	1.68GB
gemma-2b-mt-German-to-English.Q5_K.gguf	Q5_K	1.71GB
gemma-2b-mt-German-to-English.Q5_K_M.gguf	Q5_K_M	1.71GB
gemma-2b-mt-German-to-English.Q5_1.gguf	Q5_1	1.79GB
gemma-2b-mt-German-to-English.Q6_K.gguf	Q6_K	1.92GB
gemma-2b-mt-German-to-English.Q8_0.gguf	Q8_0	2.49GB

Original model description:

license: mit language: - de - en pipeline_tag: translation tags: - text-generation-inference

Description

Gemma 2B German to English v0.1 Alpha [Experimental Release]

This is a german instruction finetuned version of Google's Gemma 2B model. This is an experiment to see if Gemma can be Translate German to English by expanding vocabulary. While the responses may be rusty at times, it shows a lot of promise for a 2B parameter model.

---

Model description 🗄️:

Model type: A 2B parameter GPT-like model finetuned on 100,000 samples consisting of an equal proportion of English and German samples.

Language(s): Bilingual. English and German.

License: Google Gemma Terms of Use

Finetuned from model: Samvardhan777/gemma-2b-mt-German-to-English

Training Precision: bfloat16

Training Hardware: Free Google Colab

Dataset: kaitchup/opus-German-to-English