TheBloke
/

Llama-2-13B-chat-GPTQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Update README.md

#4

by elite7 - opened Jul 19, 2023

base: refs/heads/main

←

from: refs/pr/4

Discussion Files changed

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -112,7 +112,7 @@ 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",