cgus
/

NinjaMouse2-2.5B-v0.1-iMat-GGUF

Inference Endpoints

Model card Files Files and versions Community

cgus commited on May 9, 2024

Commit

64b06a1

·

verified ·

1 Parent(s): 14acbd5

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -29,7 +29,7 @@ Original model: [NinjaMouse2-2.5B-v0.1](https://huggingface.co/trollek/NinjaMous
 Model creator: [trollek](https://huggingface.co/trollek)
 ## Quantization notes
-This repo contains GGUF models made with llama.cpp b2700 with iMatrix calibration.
 I used calibration data from the default dataset of Exllamav2 project.
 All quants were made with the imatrix file.

 Model creator: [trollek](https://huggingface.co/trollek)
 ## Quantization notes
+This repo contains GGUF models made with llama.cpp b2822 with iMatrix calibration.
 I used calibration data from the default dataset of Exllamav2 project.
 All quants were made with the imatrix file.