duyntnet
/

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

Text Generation

Model card Files Files and versions Community

duyntnet commited on May 1

Commit

9f408c3

•

1 Parent(s): 837c937

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ tags:
 Quantizations of https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
 Update (May 1, 2024): re-uploaded models after this merge: https://github.com/ggerganov/llama.cpp/pull/6920
-Models now work correctly (tried with 7777+3333 and 3333+777 both gave correct results)
 # From original readme

 Quantizations of https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
 Update (May 1, 2024): re-uploaded models after this merge: https://github.com/ggerganov/llama.cpp/pull/6920
+Models now work correctly (tried with 7777+3333 and 3333+777 using Q8_0, both gave correct results)
 # From original readme