fietje-2b

Running on Zero

BramVanroy commited on Apr 29

Commit

5d7dfb6

•

1 Parent(s): f7fb349

Update app.py

Files changed (1) hide show

app.py CHANGED Viewed

@@ -15,7 +15,7 @@ MAX_MAX_NEW_TOKENS = 1536
 DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "8192"))
-model_id = "BramVanroy/fietje-2b-sft"
 model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")
 model = model.to("cuda" if torch.cuda.is_available() else "cpu")
 tokenizer = AutoTokenizer.from_pretrained(model_id)

 DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "8192"))
+model_id = "BramVanroy/fietje-2b-chat"
 model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")
 model = model.to("cuda" if torch.cuda.is_available() else "cpu")
 tokenizer = AutoTokenizer.from_pretrained(model_id)