steampunque
/

Ring-mini-2.0-MP-GGUF

Model card Files Files and versions

steampunque commited on Feb 18

Commit

4592246

·

verified ·

1 Parent(s): c767975

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -10,7 +10,7 @@ tags:
 - 6-bit
 ---
-## Llama.cpp hybrid layer quantization of Ring-mini-2.0 by inclusionAI
 Original model: https://huggingface.co/inclusionAI/Ring-mini-2.0
@@ -161,7 +161,7 @@ Evals for the model are available here:  https://huggingface.co/spaces/steampunq
 ## Download the file from below:
 | Link | Type | Size/e9 B | Notes |
 |------|------|-----------|-------|
-| [Ring-mini-2.0.Q6_K_H.gguf](https://huggingface.co/steampunque/Ring-mini-2.0-Hybrid-GGUF/resolve/main/Ring-mini-2.0.Q6_K_H.gguf) | Q6_K_H | 13.2e9 B | ~Q6_K size |
 A discussion thread about the hybrid layer quant approach can be found here on the llama.cpp git repository:

 - 6-bit
 ---
+## Mixed Precision GGUF layer quantization of Ring-mini-2.0 by inclusionAI
 Original model: https://huggingface.co/inclusionAI/Ring-mini-2.0
 ## Download the file from below:
 | Link | Type | Size/e9 B | Notes |
 |------|------|-----------|-------|
+| [Ring-mini-2.0.Q6_K_H.gguf](https://huggingface.co/steampunque/Ring-mini-2.0-MP-GGUF/resolve/main/Ring-mini-2.0.Q6_K_H.gguf) | Q6_K_H | 13.2e9 B | ~Q6_K size |
 A discussion thread about the hybrid layer quant approach can be found here on the llama.cpp git repository: