j88 meaning

Product description



　　metadata

　　Quantized using 115 rows of 8192 tokens from the default ExLlamav2-calibration dataset.

　　Branches:

　　--

　　8.0b8h -- 8.0bpw, 8bit lm_head

　　6.0b6h -- 6.0bpw, 6bit lm_head

　　5.0b6h -- 5.0bpw, 6bit lm_head

　　4.25b6h -- 4.25bpw, 6bit lm_head

　　4.0b6h -- 4.0bpw, 6bit lm_head

　　3.0b6h -- 3.0bpw, 6bit lm_head

　　2.25b6h -- 2.25bpw, 6bit lm_head

　　Original model link: knifeayumu/Behemoth-v1.1-Magnum-v4-123B

　　Original model README below.

　　Recipe based on MarsupialAI/Monstral-123B but uses TheDrummer/Behemoth-123B-v1.1 as the base.

　　This is a merge of pre-trained language models created using mergekit.

　　GGUF Quants:

　　GGUF (static): mradermacher/Behemoth-v1.1-Magnum-v4-123B-GGUF

　　GGUF (weighted/imatrix): mradermacher/Behemoth-v1.1-Magnum-v4-123B-i1-GGUF

　　Thank you mradermacher for honoring my request.

　　This model was merged using the SLERP merge method.

　　The following models were included in the merge:

　　anthracite-org/magnum-v4-123b

　　TheDrummer/Behemoth-123B-v1.1

　　The following YAML configuration was used to produce this model: