You can deploy this model and start earning money today!

RichardErkhov/
mudler_-_Minerva-3B-Llama3-Instruct-v0.1-gguf

Name: mudler_-_Minerva-3B-Llama3-Instruct-v0.1-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Minerva-3B-Llama3-Instruct-v0.1 - GGUF

Name	Quant method	Size
Minerva-3B-Llama3-Instruct-v0.1.Q2_K.gguf	Q2_K	1.02GB
Minerva-3B-Llama3-Instruct-v0.1.IQ3_XS.gguf	IQ3_XS	1.14GB
Minerva-3B-Llama3-Instruct-v0.1.IQ3_S.gguf	IQ3_S	1.2GB
Minerva-3B-Llama3-Instruct-v0.1.Q3_K_S.gguf	Q3_K_S	1.19GB
Minerva-3B-Llama3-Instruct-v0.1.IQ3_M.gguf	IQ3_M	1.23GB
Minerva-3B-Llama3-Instruct-v0.1.Q3_K.gguf	Q3_K	1.32GB
Minerva-3B-Llama3-Instruct-v0.1.Q3_K_M.gguf	Q3_K_M	1.32GB
Minerva-3B-Llama3-Instruct-v0.1.Q3_K_L.gguf	Q3_K_L	1.43GB
Minerva-3B-Llama3-Instruct-v0.1.IQ4_XS.gguf	IQ4_XS	1.48GB
Minerva-3B-Llama3-Instruct-v0.1.Q4_0.gguf	Q4_0	1.54GB
Minerva-3B-Llama3-Instruct-v0.1.IQ4_NL.gguf	IQ4_NL	1.55GB
Minerva-3B-Llama3-Instruct-v0.1.Q4_K_S.gguf	Q4_K_S	1.55GB
Minerva-3B-Llama3-Instruct-v0.1.Q4_K.gguf	Q4_K	1.63GB
Minerva-3B-Llama3-Instruct-v0.1.Q4_K_M.gguf	Q4_K_M	1.63GB
Minerva-3B-Llama3-Instruct-v0.1.Q4_1.gguf	Q4_1	1.7GB
Minerva-3B-Llama3-Instruct-v0.1.Q5_0.gguf	Q5_0	1.86GB
Minerva-3B-Llama3-Instruct-v0.1.Q5_K_S.gguf	Q5_K_S	1.86GB
Minerva-3B-Llama3-Instruct-v0.1.Q5_K.gguf	Q5_K	1.91GB
Minerva-3B-Llama3-Instruct-v0.1.Q5_K_M.gguf	Q5_K_M	1.91GB
Minerva-3B-Llama3-Instruct-v0.1.Q5_1.gguf	Q5_1	2.03GB
Minerva-3B-Llama3-Instruct-v0.1.Q6_K.gguf	Q6_K	2.21GB
Minerva-3B-Llama3-Instruct-v0.1.Q8_0.gguf	Q8_0	2.87GB

Original model description:

This is a https://huggingface.co/sapienzanlp/Minerva-3B-base-v1.0 fine-tune with a Llama3 prompt and the camoscio dataset in the Italian language.

It is fine-tuned with the llama3 instructor prompt so it is suitable for chat.

Note: the EOS is </s>