TheBloke
/

Llama-2-7B-GPTQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

TheBloke commited on Jul 25, 2023

Commit

98ffa0d

•

1 Parent(s): b86778e

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -106,7 +106,7 @@ use_triton = False
 tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
 model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
-        model_basename=model_basename
         use_safetensors=True,
         trust_remote_code=True,
         device="cuda:0",

 tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
 model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
+        model_basename=model_basename,
         use_safetensors=True,
         trust_remote_code=True,
         device="cuda:0",