131–135 of 135 posts
Open source AI is just a lost term. It has been co-opted. If the weights are released, it's open source. Not because that makes sense, not because it's right, but because that's the unfortunate marketting term that has stuck. The real open source models need a rebrand. Transparent models, perhaps?
Also: I simply asked to the 7B model "hi, who are u": Thought for 1 seconds Okay, the user is asking "Who are u?" with a casual tone ("u" instead of "you", exclamation mark). Let me break this down. First, I need to address the question itself. They want to know who I am as an AI assistant. My standard response is that I'm DeepSeek R1, designed to be helpful and handle reasoning step by step. But maybe they're not fa…
(I’m a researcher on the post-training team at Ai2.) Where did you try this? On the Ai2 playground?
I guess Ollama needs to update their version, maybe!
Earlier quoted context omitted.
Hmm. We think there is something wrong with the LM Studio integration. Thinking traces can be whacky, but not like this. We're looking into it.
The LM Studio team is on the case! Can you share settings you used to make that reply?
The logfile of the conversation:
https://drive.google.com/file/d/1xx0wFcYyCHMzA0kcZnZBmwfj3kF...
The json file of the conversation:
https://drive.google.com/file/d/1wZlAD5TM0YjwVjOQy3BaY_7QSkC...
Hope this help.
Earlier quoted context omitted.
Hard time? What value does adult videos description, views and comments add to small (7,32B) models?
It says it’s common crawl, I interpret it to mean this is a generic web scrape dataset, presumably they filter stuff out they don’t want before pretraining. You’d have to do do some ablation testing to know what value it adds