jukofyork
/

Qwen3-Coder-Instruct-DRAFT-0.75B-GGUF

speculative-decoding

Model card Files Files and versions

jukofyork commited on 24 days ago

Commit

07e59a5

·

verified ·

1 Parent(s): a928d48

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -92,7 +92,7 @@ Patching 'torch_dtype' in 'Qwen3-Coder-Instruct-DRAFT-0.75B/config.json' based o
 Operation completed successfully (ignore any 'segmentation fault' that follows!!!)
 ```
-**NOTE**: Unlike my other draft models - no subsequent fine-tuning has been performed (due to the 99% "1 to 1" mapping...).
 ## 2. The context was extended using YaRN:

 Operation completed successfully (ignore any 'segmentation fault' that follows!!!)
 ```
+**NOTE**: No subsequent fine-tuning has been performed (due to the 99% "1 to 1" mapping...).
 ## 2. The context was extended using YaRN: