Hugging Face's logo

Nekochu
/
Llama-3.1-8B-french-DPO

PEFT
Safetensors
French
English
llama
llama-factory
lora
Model card Files
xet
Community
2
Nekochu commited on
Commit
ff89c7a
·
verified ·
1 Parent(s): 87a4790

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -15,8 +15,7 @@ language:
15
  - I've kept LoRA `QLoRA_french_sft` so it can be applied to any LLaMA-3.1-8B fine-tuned model. It may affect performance.
16
 
17
  <details>
18
- <summary>This training can be replicated using [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory).
19
- </summary>
20
 
21
  Stage A: **P**re **T**raining, Raw text
22
  ```
 
15
  - I've kept LoRA `QLoRA_french_sft` so it can be applied to any LLaMA-3.1-8B fine-tuned model. It may affect performance.
16
 
17
  <details>
18
+ <summary>This training can be replicated using LLaMA-Factory. </summary>
 
19
 
20
  Stage A: **P**re **T**raining, Raw text
21
  ```