Huy227_-_gemma2_2b_vn-gguf

RichardErkhov/Huy227_-_gemma2_2b_vn-gguf

Huy227_-_gemma2_2b_vn-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

Downloads · 30 days

118

11% of all-time downloads

All-time downloads

1.1K

Public

Repo size

32.3 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf37.3 GB · 100%

At a glance

Access: Public
Created: Oct 3, 2024
Updated: Oct 3, 2024
SHA: f6284964

Model card

From the Hugging Face model README

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gemma2_2b_vn - GGUF

Model creator: https://huggingface.co/Huy227/
Original model: https://huggingface.co/Huy227/gemma2_2b_vn/

Name	Quant method	Size
gemma2_2b_vn.Q2_K.gguf	Q2_K	1.15GB
gemma2_2b_vn.IQ3_XS.gguf	IQ3_XS	1.22GB
gemma2_2b_vn.IQ3_S.gguf	IQ3_S	1.27GB
gemma2_2b_vn.Q3_K_S.gguf	Q3_K_S	1.27GB
gemma2_2b_vn.IQ3_M.gguf	IQ3_M	1.3GB
gemma2_2b_vn.Q3_K.gguf	Q3_K	1.36GB
gemma2_2b_vn.Q3_K_M.gguf	Q3_K_M	1.36GB
gemma2_2b_vn.Q3_K_L.gguf	Q3_K_L	1.44GB
gemma2_2b_vn.IQ4_XS.gguf	IQ4_XS	1.47GB
gemma2_2b_vn.Q4_0.gguf	Q4_0	1.52GB
gemma2_2b_vn.IQ4_NL.gguf	IQ4_NL	1.53GB
gemma2_2b_vn.Q4_K_S.gguf	Q4_K_S	1.53GB
gemma2_2b_vn.Q4_K.gguf	Q4_K	1.59GB
gemma2_2b_vn.Q4_K_M.gguf	Q4_K_M	1.59GB
gemma2_2b_vn.Q4_1.gguf	Q4_1	1.64GB
gemma2_2b_vn.Q5_0.gguf	Q5_0	1.75GB
gemma2_2b_vn.Q5_K_S.gguf	Q5_K_S	1.75GB
gemma2_2b_vn.Q5_K.gguf	Q5_K	1.79GB
gemma2_2b_vn.Q5_K_M.gguf	Q5_K_M	1.79GB
gemma2_2b_vn.Q5_1.gguf	Q5_1	1.87GB
gemma2_2b_vn.Q6_K.gguf	Q6_K	2.0GB
gemma2_2b_vn.Q8_0.gguf	Q8_0	2.59GB

Original model description:

library_name: transformers tags:

llama-factory language:
en
vi

Model Card for Model ID

Gemma-2-2b a lightweight version has Sota performance at the same size finetuned on Vietnamese dataset. Model focused mainly on vietnamese

Evaluation

Testing Data

Achieved 42.35 on VMLU test

Created: Oct 3, 2024
Updated: Oct 3, 2024