arise-sustech
/

llm4decompile-33b

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

arise-sustech commited on Mar 16

Commit

341b9ba

•

1 Parent(s): 64de7f6

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -67,7 +67,7 @@ Then use LLM4Decompile to translate the assembly instructions into C:
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
-model_path = 'arise-sustech/llm4decompile-33b'
 tokenizer = AutoTokenizer.from_pretrained(model_path)
 model = AutoModelForCausalLM.from_pretrained(model_path,torch_dtype=torch.bfloat16).cuda()

 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
+model_path = 'arise-sustech/llm4decompile-33b' #note: it may need multi-gpu support
 tokenizer = AutoTokenizer.from_pretrained(model_path)
 model = AutoModelForCausalLM.from_pretrained(model_path,torch_dtype=torch.bfloat16).cuda()