mukel
/

Meta-Llama-3-8B-Instruct-GGUF

Inference Endpoints

Model card Files Files and versions Community

mukel commited on May 14

Commit

bea5997

•

1 Parent(s): 3778493

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -8,7 +8,7 @@ tags:
 - llama3.java
 ---
-## GGUF models for llama3.java
 Pure .gguf `Q4_0` and `Q8_0` quantizations of Llama 3 8B instruct, ready to consume by [llama3.java](https://github.com/mukel/llama3.java).
 In the wild, `Q8_0` quantizations are fine, but `Q4_0` quantizations are rarely pure e.g. the `output.weights` tensor is quantized with `Q6_K`, instead of `Q4_0`.

 - llama3.java
 ---
+# GGUF models for llama3.java
 Pure .gguf `Q4_0` and `Q8_0` quantizations of Llama 3 8B instruct, ready to consume by [llama3.java](https://github.com/mukel/llama3.java).
 In the wild, `Q8_0` quantizations are fine, but `Q4_0` quantizations are rarely pure e.g. the `output.weights` tensor is quantized with `Q6_K`, instead of `Q4_0`.