nisten
/

llama3-8b-instruct-32k-gguf

Inference Endpoints

Model card Files Files and versions Community

nisten commited on Apr 24

Commit

1d68898

•

1 Parent(s): b94ba72

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -7,7 +7,7 @@ base_model: meta-llama/Meta-Llama-3-8B-Instruct
 ### *THIS IS NOT A FINETUNE IT JUST WORKS GREAT VIA YARN SCALING*
-## imatrix custom edge-quants included and work great for 4, 3 and 2 bit versions
 > [!TIP]
 > You have to set context with ***-c 32000*** in llama.cpp to take advantage of this when you run it.

 ### *THIS IS NOT A FINETUNE IT JUST WORKS GREAT VIA YARN SCALING*
+## imatrix custom edge-quants tested ok at 4,3 & 2bit
 > [!TIP]
 > You have to set context with ***-c 32000*** in llama.cpp to take advantage of this when you run it.