Add files using upload-large-folder tool

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 Qwen3-Coder-REAP-25B-A3B-MXFP4_MOE.gguf filter=lfs diff=lfs merge=lfs -text
 Qwen3-Coder-REAP-25B-A3B-i1-MXFP4_MOE.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-Coder-REAP-25B-A3B-i1-codetiny-exp-MXFP4_MOE.gguf filter=lfs diff=lfs merge=lfs -text

Qwen3-Coder-REAP-25B-A3B-i1-codetiny-exp-MXFP4_MOE.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20816fbcb1a9e8f4e21ea13bbfa5a26c195cfc94912f7fef64938dee1d05803b
+size 14064517696

README.md

@@ -5,6 +5,15 @@ base_model:
 ---
 This is a MXFP4_MOE quantization of the model Qwen3-Coder-REAP-25B-A3B
 
-Also added an imatrix version.
+Added an imatrix version, based on the imatrix from bartowski.
+
+I also created my own imatrix version, that is the one marked as codetiny-exp.
+This is considered experimental.
+What I did, is that I took a very specific imatrix data, that is *ONLY* for coding and not for general knowledge.
+It's the [code_tiny](https://huggingface.co/datasets/eaddario/imatrix-calibration/blob/main/code_tiny.parquet) dataset from [eaddario/imatrix-calibration](https://huggingface.co/datasets/eaddario/imatrix-calibration)
+I thought that would be better suited, as this a coding specific model.
+But further tests must be done.
+Please provide feedback.
+I'll maybe even train it on larger datasets if feedback is positive.
 
 Original model: https://huggingface.co/cerebras/Qwen3-Coder-REAP-25B-A3B