radm
/

Safetensors
qwen2
radm commited on
Commit
cc64ac9
·
verified ·
1 Parent(s): 5980fe8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -27,7 +27,9 @@ datasets:
27
 
28
  Improved quality on hard tasks by 25 percent relative to the base model Qwen2.5-32B-Instruct. Improved multilingual support.
29
 
30
- Fine-tuning on A100 in 4-bit with unsloth using SIMPO and internal dataset
 
 
31
 
32
  ### Eval results
33
 
 
27
 
28
  Improved quality on hard tasks by 25 percent relative to the base model Qwen2.5-32B-Instruct. Improved multilingual support.
29
 
30
+ Fine-tuning on A100 in 4-bit with unsloth using SIMPO and custom dataset
31
+
32
+ LoRA adapter: [radm/Qwen2.5-32B-simpo-LoRA](https://huggingface.co/radm/Qwen2.5-32B-simpo-LoRA)
33
 
34
  ### Eval results
35