RichardErkhov/typeof_-_mistral-60m-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

mistral-60m - GGUF

• Model creator: https://huggingface.co/typeof/
• Original model: https://huggingface.co/typeof/mistral-60m/

Name	Quant method	Size
mistral-60m.Q2_K.gguf	Q2_K	0.03GB
mistral-60m.IQ3_XS.gguf	IQ3_XS	0.03GB
mistral-60m.IQ3_S.gguf	IQ3_S	0.03GB
mistral-60m.Q3_K_S.gguf	Q3_K_S	0.03GB
mistral-60m.IQ3_M.gguf	IQ3_M	0.03GB
mistral-60m.Q3_K.gguf	Q3_K	0.03GB
mistral-60m.Q3_K_M.gguf	Q3_K_M	0.03GB
mistral-60m.Q3_K_L.gguf	Q3_K_L	0.03GB
mistral-60m.IQ4_XS.gguf	IQ4_XS	0.04GB
mistral-60m.Q4_0.gguf	Q4_0	0.04GB
mistral-60m.IQ4_NL.gguf	IQ4_NL	0.04GB
mistral-60m.Q4_K_S.gguf	Q4_K_S	0.04GB
mistral-60m.Q4_K.gguf	Q4_K	0.04GB
mistral-60m.Q4_K_M.gguf	Q4_K_M	0.04GB
mistral-60m.Q4_1.gguf	Q4_1	0.04GB
mistral-60m.Q5_0.gguf	Q5_0	0.04GB
mistral-60m.Q5_K_S.gguf	Q5_K_S	0.04GB
mistral-60m.Q5_K.gguf	Q5_K	0.04GB
mistral-60m.Q5_K_M.gguf	Q5_K_M	0.04GB
mistral-60m.Q5_1.gguf	Q5_1	0.04GB
mistral-60m.Q6_K.gguf	Q6_K	0.05GB
mistral-60m.Q8_0.gguf	Q8_0	0.06GB

Original model description:

language: - en

A mini (randomly initialized) mistral.

Training

Trained on slimorca with chatml format.