hpprc_-_gemma-2-2b-jpn-it-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
hpprc_-_gemma-2-2b-jpn-it-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

gemma-2-2b-jpn-it - GGUF

Model creator: https://huggingface.co/hpprc/
Original model: https://huggingface.co/hpprc/gemma-2-2b-jpn-it/

Name	Quant method	Size
gemma-2-2b-jpn-it.Q2_K.gguf	Q2_K	1.15GB
gemma-2-2b-jpn-it.IQ3_XS.gguf	IQ3_XS	1.22GB
gemma-2-2b-jpn-it.IQ3_S.gguf	IQ3_S	1.27GB
gemma-2-2b-jpn-it.Q3_K_S.gguf	Q3_K_S	1.27GB
gemma-2-2b-jpn-it.IQ3_M.gguf	IQ3_M	1.3GB
gemma-2-2b-jpn-it.Q3_K.gguf	Q3_K	1.36GB
gemma-2-2b-jpn-it.Q3_K_M.gguf	Q3_K_M	1.36GB
gemma-2-2b-jpn-it.Q3_K_L.gguf	Q3_K_L	1.44GB
gemma-2-2b-jpn-it.IQ4_XS.gguf	IQ4_XS	1.47GB
gemma-2-2b-jpn-it.Q4_0.gguf	Q4_0	1.52GB
gemma-2-2b-jpn-it.IQ4_NL.gguf	IQ4_NL	1.21GB
gemma-2-2b-jpn-it.Q4_K_S.gguf	Q4_K_S	1.53GB
gemma-2-2b-jpn-it.Q4_K.gguf	Q4_K	1.59GB
gemma-2-2b-jpn-it.Q4_K_M.gguf	Q4_K_M	1.59GB
gemma-2-2b-jpn-it.Q4_1.gguf	Q4_1	1.64GB
gemma-2-2b-jpn-it.Q5_0.gguf	Q5_0	1.75GB
gemma-2-2b-jpn-it.Q5_K_S.gguf	Q5_K_S	1.75GB
gemma-2-2b-jpn-it.Q5_K.gguf	Q5_K	1.79GB
gemma-2-2b-jpn-it.Q5_K_M.gguf	Q5_K_M	1.79GB
gemma-2-2b-jpn-it.Q5_1.gguf	Q5_1	1.87GB
gemma-2-2b-jpn-it.Q6_K.gguf	Q6_K	2.0GB
gemma-2-2b-jpn-it.Q8_0.gguf	Q8_0	2.59GB

Original model description:

library_name: transformers license: gemma base_model:

google/gemma-2-2b-jpn-it

オリジナルのgoogle/gemma-2-2b-jpn-itを用いてvLLMを使用する際に存在する問題を解消するため、設定ファイルに軽微な変更のみを加えたモデルです(追加訓練やマージなどモデルパラメータの操作はしていません)。

具体的な変更点: config.hidden_act = config.hidden_activation