RedHatAI
/

Llama-2-7b-chat-quantized.w8a16

Text Generation

text-generation-inference

8-bit precision

Model card Files Files and versions

alexmarques commited on Jul 15, 2024

Commit

69cb000

·

verified ·

1 Parent(s): 131f2ba

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -121,7 +121,7 @@ import random
 model_id = "meta-llama/Llama-2-7b-chat-hf"
 num_samples = 256
-max_seq_len = 8192
 tokenizer = AutoTokenizer.from_pretrained(model_id)

 model_id = "meta-llama/Llama-2-7b-chat-hf"
 num_samples = 256
+max_seq_len = 4096
 tokenizer = AutoTokenizer.from_pretrained(model_id)