RichardErkhov/vilm_-_vinallama-2.7b-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

vinallama-2.7b - GGUF

• Model creator: https://huggingface.co/vilm/
• Original model: https://huggingface.co/vilm/vinallama-2.7b/

Name	Quant method	Size
vinallama-2.7b.Q2_K.gguf	Q2_K	1.0GB
vinallama-2.7b.IQ3_XS.gguf	IQ3_XS	1.1GB
vinallama-2.7b.IQ3_S.gguf	IQ3_S	1.16GB
vinallama-2.7b.Q3_K_S.gguf	Q3_K_S	1.16GB
vinallama-2.7b.IQ3_M.gguf	IQ3_M	1.22GB
vinallama-2.7b.Q3_K.gguf	Q3_K	1.28GB
vinallama-2.7b.Q3_K_M.gguf	Q3_K_M	1.28GB
vinallama-2.7b.Q3_K_L.gguf	Q3_K_L	1.39GB
vinallama-2.7b.IQ4_XS.gguf	IQ4_XS	1.42GB
vinallama-2.7b.Q4_0.gguf	Q4_0	1.48GB
vinallama-2.7b.IQ4_NL.gguf	IQ4_NL	1.49GB
vinallama-2.7b.Q4_K_S.gguf	Q4_K_S	1.49GB
vinallama-2.7b.Q4_K.gguf	Q4_K	1.58GB
vinallama-2.7b.Q4_K_M.gguf	Q4_K_M	1.58GB
vinallama-2.7b.Q4_1.gguf	Q4_1	1.64GB
vinallama-2.7b.Q5_0.gguf	Q5_0	1.79GB
vinallama-2.7b.Q5_K_S.gguf	Q5_K_S	1.79GB
vinallama-2.7b.Q5_K.gguf	Q5_K	1.84GB
vinallama-2.7b.Q5_K_M.gguf	Q5_K_M	1.84GB
vinallama-2.7b.Q5_1.gguf	Q5_1	1.95GB
vinallama-2.7b.Q6_K.gguf	Q6_K	2.12GB
vinallama-2.7b.Q8_0.gguf	Q8_0	2.75GB

Original model description:

license: llama2 language: - vi

VinaLLaMA - State-of-the-art Vietnamese LLMs

Read our Paper