Spaces:

vita-group
/

README

Running

jyhong836 commited on Sep 3, 2023

Commit

674f496

1 Parent(s): 12af674

Update README.md

Files changed (1) hide show

README.md CHANGED Viewed

@@ -63,7 +63,6 @@ model = AutoGPTQForCausalLM.from_quantized(
         # inject_fused_attention=False, # or
         disable_exllama=True,
         device_map='auto',
-        revision='2bit_128g',
     )
 tokenizer = AutoTokenizer.from_pretrained(tokenizer_path, trust_remote_code=True)
 input_ids = tokenizer('Hello! I am a VITA-compressed-LLM chatbot!', return_tensors='pt').input_ids.to('cuda')

         # inject_fused_attention=False, # or
         disable_exllama=True,
         device_map='auto',
     )
 tokenizer = AutoTokenizer.from_pretrained(tokenizer_path, trust_remote_code=True)
 input_ids = tokenizer('Hello! I am a VITA-compressed-LLM chatbot!', return_tensors='pt').input_ids.to('cuda')