You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am now to LocalAI and am a novice at running LLMs locally.
I have just started trying out LocalAI. However, when I run the GPT-OSS-20B model using the llama.cpp backend, I get outputs that show the Harmony tags like <|channel|>analysis<|message|>.
For example, when I send this query: Hi, what's your name? I get the following response:
<|channel|>analysis<|message|>We need to respond: friendly, helpful. The user asks "Hi, what's your name?" We can say "I'm ChatGPT".<|end|><|start|>assistant<|channel|>final<|message|>Hi! I’m ChatGPT – your AI assistant. How can I help you today?
I am not sure what to do as this is not a problem for the other models.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
I am now to LocalAI and am a novice at running LLMs locally.
I have just started trying out LocalAI. However, when I run the GPT-OSS-20B model using the llama.cpp backend, I get outputs that show the Harmony tags like
<|channel|>analysis<|message|>
.For example, when I send this query:
Hi, what's your name?
I get the following response:I am not sure what to do as this is not a problem for the other models.
Any help or advice is much appreciated!
Beta Was this translation helpful? Give feedback.
All reactions