We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent d5bda98 commit b1e922bCopy full SHA for b1e922b
recipes/configs/generation.yaml
@@ -28,7 +28,7 @@ tokenizer:
28
path: /tmp/Llama-2-7b-hf/tokenizer.model
29
30
# Generation arguments; defaults taken from gpt-fast
31
-prompt: "Hello, my name is"
+prompt: "Tell me a joke?"
32
instruct_template: null
33
chat_format: null
34
max_new_tokens: 300
0 commit comments