Quant-Cartel
/

Questionable-MN-12B-iMat-GGUF

Inference Endpoints

Model card Files Files and versions Community

InferenceIllusionist commited on Jan 20

Commit

678d67f

·

verified ·

1 Parent(s): b5af733

Update README.md

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -34,14 +34,14 @@ PROUDLY PRESENTS
 ```
 # Mistral-Large-Instruct-2411-iMat-GGUF
-Quantized from bf16.
 Original model author: [rAIfle](https://huggingface.co/rAIfle/)
 * Importance Matrix calculated using [groups_merged.txt](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)
-*  92 chunks
-*  n_ctx=512
-*  iMat Calculation uses fp16 precision model weights
 Original model README [here](https://huggingface.co/rAIfle/Questionable-MN-bf16) and below.

 ```
 # Mistral-Large-Instruct-2411-iMat-GGUF
+Quantized from bf16 with love.
 Original model author: [rAIfle](https://huggingface.co/rAIfle/)
 * Importance Matrix calculated using [groups_merged.txt](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)
+* 92 chunks
+* n_ctx=512
+* iMat Calculation uses fp16 precision model weights
 Original model README [here](https://huggingface.co/rAIfle/Questionable-MN-bf16) and below.