mesolitica
/

malaysian-llama2-13b-32k-instructions-AWQ

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

huseinzol05 commited on Nov 12, 2023

Commit

9dfc73c

•

1 Parent(s): 360c33f

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -32,7 +32,7 @@ def parse_llama_chat(messages):
     prompt = ''.join(texts).strip()
     return prompt
-tokenizer = AutoTokenizer.from_pretrained('mesolitica/malaysian-llama2-13b-32k-instructions-AWS')
 model = AutoModelForCausalLM.from_pretrained(
     'mesolitica/malaysian-llama2-13b-32k-instructions-AWQ',
     use_flash_attention_2 = True,

     prompt = ''.join(texts).strip()
     return prompt
+tokenizer = AutoTokenizer.from_pretrained('mesolitica/malaysian-llama2-13b-32k-instructions-AWQ')
 model = AutoModelForCausalLM.from_pretrained(
     'mesolitica/malaysian-llama2-13b-32k-instructions-AWQ',
     use_flash_attention_2 = True,