TheStageAI
/

Elastic-Qwen2.5-7B-Instruct

Text Generation

Model card Files Files and versions

Update README.md

#2

by hypothetical - opened Apr 27

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -81,7 +81,7 @@ chat_prompt = tokenizer.apply_chat_template(
 inputs = tokenizer(chat_prompt, return_tensors="pt")
 inputs.to(device)
-with torch.inference_mode:
     generate_ids = model.generate(**inputs, max_length=500)
 input_len = inputs['input_ids'].shape[1]

 inputs = tokenizer(chat_prompt, return_tensors="pt")
 inputs.to(device)
+with torch.inference_mode():
     generate_ids = model.generate(**inputs, max_length=500)
 input_len = inputs['input_ids'].shape[1]