Nanobit commited on
Commit
8552218
1 Parent(s): de2a733

Improve Inference instruction

Browse files
Files changed (1) hide show
  1. README.md +9 -5
README.md CHANGED
@@ -317,12 +317,16 @@ accelerate launch scripts/finetune.py configs/your_config.yml
317
 
318
  ### Inference
319
 
320
- Add `--inference` flag to train command above
321
 
322
- If you are inferencing a pretrained LORA, pass
323
- ```bash
324
- --lora_model_dir ./completed-model
325
- ```
 
 
 
 
326
 
327
  ### Merge LORA to base
328
 
 
317
 
318
  ### Inference
319
 
320
+ Pass the appropriate flag to the train command:
321
 
322
+ - Pretrained LORA:
323
+ ```bash
324
+ --inference --lora_model_dir ./completed-model
325
+ ```
326
+ - Full weights finetune:
327
+ ```bash
328
+ --inference --base_model ./completed-model
329
+ ```
330
 
331
  ### Merge LORA to base
332