Translation
PEFT
Safetensors
traintogpb commited on
Commit
f076c37
1 Parent(s): 9d8b9cd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -89,6 +89,7 @@ pipeline_tag: translation
89
  </한국어></target>
90
  </translation>
91
  ```
 
92
 
93
  ### Training
94
  - Trained with LoRA adapter
@@ -105,7 +106,7 @@ pipeline_tag: translation
105
 
106
  model = AutoModelForCausalLM.from_pretrained(
107
  model_name,
108
- max_length=4000,
109
  attn_implementation='flash_attention_2',
110
  torch_dtype=torch.bfloat16,
111
  )
 
89
  </한국어></target>
90
  </translation>
91
  ```
92
+ Model will generate the XML end tags.
93
 
94
  ### Training
95
  - Trained with LoRA adapter
 
106
 
107
  model = AutoModelForCausalLM.from_pretrained(
108
  model_name,
109
+ max_length=4096,
110
  attn_implementation='flash_attention_2',
111
  torch_dtype=torch.bfloat16,
112
  )