Quantization made by Richard Erkhov.

vinallama-7b-chat - GGUF

Model creator: https://huggingface.co/vilm/
Original model: https://huggingface.co/vilm/vinallama-7b-chat/

Name	Quant method	Size
vinallama-7b-chat.Q2_K.gguf	Q2_K	2.42GB
vinallama-7b-chat.IQ3_XS.gguf	IQ3_XS	2.67GB
vinallama-7b-chat.IQ3_S.gguf	IQ3_S	2.81GB
vinallama-7b-chat.Q3_K_S.gguf	Q3_K_S	2.81GB
vinallama-7b-chat.IQ3_M.gguf	IQ3_M	2.97GB
vinallama-7b-chat.Q3_K.gguf	Q3_K	3.14GB
vinallama-7b-chat.Q3_K_M.gguf	Q3_K_M	3.14GB
vinallama-7b-chat.Q3_K_L.gguf	Q3_K_L	3.42GB
vinallama-7b-chat.IQ4_XS.gguf	IQ4_XS	3.47GB
vinallama-7b-chat.Q4_0.gguf	Q4_0	3.64GB
vinallama-7b-chat.IQ4_NL.gguf	IQ4_NL	3.66GB
vinallama-7b-chat.Q4_K_S.gguf	Q4_K_S	3.67GB
vinallama-7b-chat.Q4_K.gguf	Q4_K	3.88GB
vinallama-7b-chat.Q4_K_M.gguf	Q4_K_M	3.88GB
vinallama-7b-chat.Q4_1.gguf	Q4_1	4.03GB
vinallama-7b-chat.Q5_0.gguf	Q5_0	4.41GB
vinallama-7b-chat.Q5_K_S.gguf	Q5_K_S	4.41GB
vinallama-7b-chat.Q5_K.gguf	Q5_K	4.54GB
vinallama-7b-chat.Q5_K_M.gguf	Q5_K_M	4.54GB
vinallama-7b-chat.Q5_1.gguf	Q5_1	4.8GB
vinallama-7b-chat.Q6_K.gguf	Q6_K	5.24GB
vinallama-7b-chat.Q8_0.gguf	Q8_0	6.79GB

Original model description:

language: - vi license: llama2

VinaLLaMA - State-of-the-art Vietnamese LLMs

Read our Paper

Prompt Format (ChatML):

<|im_start|>system
Bạn là một trợ lí AI hữu ích. Hãy trả lời người dùng một cách chính xác.
<|im_end|>
<|im_start|>user
Hello world!<|im_end|>
<|im_start|>assistant