TheBloke
/

Yarn-Llama-2-13B-128K-GPTQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Update README.md

#2

by misokatsuoden - opened Sep 18, 2023

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -165,7 +165,8 @@ model_name_or_path = "TheBloke/Yarn-Llama-2-13B-128K-GPTQ"
 model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
                                              torch_dtype=torch.float16,
                                              device_map="auto",
-                                             revision="main")
 tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)

 model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
                                              torch_dtype=torch.float16,
                                              device_map="auto",
+                                             revision="main",
+                                             trust_remote_code=True)
 tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)