nvidia
/

Llama-3_1-Nemotron-Ultra-253B-v1

Text Generation

Model card Files Files and versions

Update README.md

#15

by f14 - opened Nov 3

base: refs/heads/main

←

from: refs/pr/15

Discussion Files changed

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -154,7 +154,7 @@ Example of reasoning off:
 import torch
 import transformers
-model_id = "nvidia/Llama-3_1-Nemotron-ULtra-253B-v1"
 model_kwargs = {"torch_dtype": torch.bfloat16, "trust_remote_code": True, "device_map": "auto"}
 tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)
 tokenizer.pad_token_id = tokenizer.eos_token_id

 import torch
 import transformers
+model_id = "nvidia/Llama-3_1-Nemotron-Ultra-253B-v1"
 model_kwargs = {"torch_dtype": torch.bfloat16, "trust_remote_code": True, "device_map": "auto"}
 tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)
 tokenizer.pad_token_id = tokenizer.eos_token_id