You can deploy this model and start earning money today!

RichardErkhov/
Changgil_-_K2S3-Mistral-7bx2-48layers_v1.2-gguf

Name: Changgil_-_K2S3-Mistral-7bx2-48layers_v1.2-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

K2S3-Mistral-7bx2-48layers_v1.2 - GGUF

Model creator: https://huggingface.co/Changgil/
Original model: https://huggingface.co/Changgil/K2S3-Mistral-7bx2-48layers_v1.2/

Name	Quant method	Size
K2S3-Mistral-7bx2-48layers_v1.2.Q2_K.gguf	Q2_K	3.8GB
K2S3-Mistral-7bx2-48layers_v1.2.IQ3_XS.gguf	IQ3_XS	4.22GB
K2S3-Mistral-7bx2-48layers_v1.2.IQ3_S.gguf	IQ3_S	4.45GB
K2S3-Mistral-7bx2-48layers_v1.2.Q3_K_S.gguf	Q3_K_S	4.42GB
K2S3-Mistral-7bx2-48layers_v1.2.IQ3_M.gguf	IQ3_M	4.59GB
K2S3-Mistral-7bx2-48layers_v1.2.Q3_K.gguf	Q3_K	4.92GB
K2S3-Mistral-7bx2-48layers_v1.2.Q3_K_M.gguf	Q3_K_M	4.92GB
K2S3-Mistral-7bx2-48layers_v1.2.Q3_K_L.gguf	Q3_K_L	5.34GB
K2S3-Mistral-7bx2-48layers_v1.2.IQ4_XS.gguf	IQ4_XS	5.51GB
K2S3-Mistral-7bx2-48layers_v1.2.Q4_0.gguf	Q4_0	5.74GB
K2S3-Mistral-7bx2-48layers_v1.2.IQ4_NL.gguf	IQ4_NL	5.8GB
K2S3-Mistral-7bx2-48layers_v1.2.Q4_K_S.gguf	Q4_K_S	5.78GB
K2S3-Mistral-7bx2-48layers_v1.2.Q4_K.gguf	Q4_K	6.1GB
K2S3-Mistral-7bx2-48layers_v1.2.Q4_K_M.gguf	Q4_K_M	6.1GB
K2S3-Mistral-7bx2-48layers_v1.2.Q4_1.gguf	Q4_1	6.36GB
K2S3-Mistral-7bx2-48layers_v1.2.Q5_0.gguf	Q5_0	6.98GB
K2S3-Mistral-7bx2-48layers_v1.2.Q5_K_S.gguf	Q5_K_S	6.98GB
K2S3-Mistral-7bx2-48layers_v1.2.Q5_K.gguf	Q5_K	7.17GB
K2S3-Mistral-7bx2-48layers_v1.2.Q5_K_M.gguf	Q5_K_M	7.17GB
K2S3-Mistral-7bx2-48layers_v1.2.Q5_1.gguf	Q5_1	7.6GB
K2S3-Mistral-7bx2-48layers_v1.2.Q6_K.gguf	Q6_K	8.3GB
K2S3-Mistral-7bx2-48layers_v1.2.Q8_0.gguf	Q8_0	10.75GB

Original model description:

license: cc-by-nc-4.0 language:

dtype: bfloat16 merge_method: passthrough slices:

sources:
- layer_range: [0, 24] model: model: path: Changgil/K2S3-Mistral-7b-v1.2
sources:
- layer_range: [8, 32] model: model: path: Changgil/K2S3-Mistral-7b-v1.2