diegobit
/

llama-3-8b-ita-4k-orpo-v3

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

diegobit commited on Jun 12

Commit

13e571a

•

1 Parent(s): 94d720b

Update README.md

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -61,6 +61,8 @@ dtype = None
 load_in_4bit = False
 ```
 ```
 r = 64
 lora_alpha = 64

 load_in_4bit = False
 ```
+- **PEFT parameters:**
 ```
 r = 64
 lora_alpha = 64