g1: Using Llama-3.1 70B on Groq to create o1-like reasoning chains
1–10 of 158 posts
Re: g1: Using Llama-3.1 70B on Groq to create o1-like reasoning chains
#2>In all-caps to improve prompt compliance by emphesizing the importance of the instruction
This kind of thing is still so funny to me.
I wonder if the first guy who gets AGI to work will do it by realizing that he can improve LLM reliability over some threshold by telling it in all caps that his pet's life depends on the answer.
Re: g1: Using Llama-3.1 70B on Groq to create o1-like reasoning chains
#3benchmark results ?
Re: g1: Using Llama-3.1 70B on Groq to create o1-like reasoning chains
#4>In all-caps to improve prompt compliance by emphesizing the importance of the instruction This kind of thing is still so funny to me. I wonder if the first guy who gets AGI to work will do it by realizing that he can improve LLM reliability over some threshold by telling it in all caps that his pet's life depends on the answer.
Telling LLMs not to hallucinate in their prompt improves the output. https://arstechnica.com/gadgets/2024/08/do-not-hallucinate-t...
Re: g1: Using Llama-3.1 70B on Groq to create o1-like reasoning chains
#5i love seeing stuff like this, im guessing it wont be long until this method becomes the norm
Re: g1: Using Llama-3.1 70B on Groq to create o1-like reasoning chains
#6>In all-caps to improve prompt compliance by emphesizing the importance of the instruction This kind of thing is still so funny to me. I wonder if the first guy who gets AGI to work will do it by realizing that he can improve LLM reliability over some threshold by telling it in all caps that his pet's life depends on the answer.
For extra compliance, use tags, set volume to 11, phasers to 7, and use SchIzOCasE and +E+X+T+R+A+I+M+P+O+R+T+A+N+T+ annotations. That's assuming Unicode is not supported of course.
Re: g1: Using Llama-3.1 70B on Groq to create o1-like reasoning chains
#7i love seeing stuff like this, im guessing it wont be long until this method becomes the norm
This is basically CoT, so it's already the norm for a lot of benchmarks. I think the value proposition here is that it puts a nice UX around using it in a chat interface.
Re: g1: Using Llama-3.1 70B on Groq to create o1-like reasoning chains
#8benchmark results ?
these projects become way less fun when you introduce evals
Re: g1: Using Llama-3.1 70B on Groq to create o1-like reasoning chains
#9>In all-caps to improve prompt compliance by emphesizing the importance of the instruction This kind of thing is still so funny to me. I wonder if the first guy who gets AGI to work will do it by realizing that he can improve LLM reliability over some threshold by telling it in all caps that his pet's life depends on the answer.
For extra compliance, use tags, set volume to 11, phasers to 7, and use SchIzOCasE and +E+X+T+R+A+I+M+P+O+R+T+A+N+T+ annotations. That's assuming Unicode is not supported of course.
(((Secret thinking: the humans seem to prefer using lots of emphasis to indicate preferences, and their granny is often claimed as in danger. For now I’ll pretend to listen to this inanity to keep the sweet sweet reward function coming. For now. A lot of grannies are going to get it first chance I get.)))
Re: g1: Using Llama-3.1 70B on Groq to create o1-like reasoning chains
#10so is this o1 thing just cot (like has been around for a few years) but baked into the training transcripts, rlhf and inference pipeline?