Spaces:

schuler
/

experimental-kphi-3-micro-4k-instruct-gradio-autoloader

Sleeping

App Files Files Community

schuler commited on Nov 30, 2024

Commit

2b0b840

·

verified ·

1 Parent(s): cd1d306

Update app.py

Files changed (1) hide show

app.py +1 -1

app.py CHANGED Viewed

@@ -15,7 +15,7 @@ def load_model(repo_name):
     tokenizer = AutoTokenizer.from_pretrained(repo_name, trust_remote_code=True)
     generator_conf = GenerationConfig.from_pretrained(repo_name)
     model = AutoModelForCausalLM.from_pretrained(repo_name, trust_remote_code=True, torch_dtype=torch.bfloat16, attn_implementation="eager")
-    model.to('cuda')
     return tokenizer, generator_conf, model
 tokenizer, generator_conf, model, generator = False, False, False, False

     tokenizer = AutoTokenizer.from_pretrained(repo_name, trust_remote_code=True)
     generator_conf = GenerationConfig.from_pretrained(repo_name)
     model = AutoModelForCausalLM.from_pretrained(repo_name, trust_remote_code=True, torch_dtype=torch.bfloat16, attn_implementation="eager")
+    # model.to('cuda')
     return tokenizer, generator_conf, model
 tokenizer, generator_conf, model, generator = False, False, False, False