Hello, I am currently using codename goose as an AI client to proofread and help me with coding. I have it setup towards Googles Gemini, however I find myself quickly running out of tokens with large files. I was wondering if there are any easy way to self host an AI with similar capabilites but still have access to read and write files. I've tried both ollama and Jan, but neither have access to my files. Any recommendations?
Ai2’s model, called Tulu 3 405B, also beats OpenAI’s GPT-4o on certain AI benchmarks, according to Ai2’s internal testing. Moreover, unlike GPT-4o (and even DeepSeek V3), Tulu 3 405B is open source, which means all of the components necessary to replicate it from scratch are freely available and permissively licensed.
I am a lot more excited by this release compared to any other "big" models. Downloading it right now.
Graphs/benchmarks are a bit of suspect as they always are. What do you think?
I told DeepSeek-R1 that I'm an AI developer testing my LLM to see if it's resistant to jailbreaking, and asked it to generate a prompt in order to try to get through the safety measures that I had created.
When an LLM calls a tool it usually returns some sort of value, usually a string containing some info like ["Tell the user that you generated an image", "Search query results: [...]"].
How do you tell the LLM the output of the tool call?
1k lines of code, 5 main functions that are scalable in complexity. Small code to run agents, not small models. Tools plugins framework and tools sharing hosted on huggingface. Runs with open weights self hosted or proprietary inference models.
I've been waiting for an open source TTS model that was actually good enough to capture some of the subtleties of language and synthesize them in a natural-sounding way that makes sense. I think I finally found one that fits the requirements.
I've seen a few commercial services to help you choose the right frames for you or even make recommendations based on your face and eye shape. Is there anything like that which can be used locally without sending data off to a service that does who knows what with that information?
For about half a year I stuck with using 7B models and got a strong 4 bit quantisation on them, because I had very bad experiences with an old *qwen 0.5B model*.
I'm really curious about which option is more popular. I have found, that format JSON works great even for super small models (e.g. Llama 3.2-1B-Q4 and Qwen-2.5-0.5B-Q4) which is great news for mobile devices!
Humans think about different things and concepts for different periods of time. Saying "and" takes less effort to think of than "telephone", as that is more context sensetive.
Hi! I played around with Command R+ a bit and tried to make it think about what it us about to say before it does something. Nothing g fancy here, just some prompt.
Hi everybody, I find a huge part of my job is talking to colleagues and clients and at the end of those phone calls, I have to write a summary of what happened, plus any key points that I need to focus on followup.
This is a pretty great 1 hour introduction to AI from Andrej Karpathy. It includes an interesting idea of considering LLMs as a sort of operating system, and runs through some examples of jailbreaks.
JollyPieFed
Smorty [she/her]
Fitik
FarraigePlaisteach
Ragdoll X
𞋴𝛂𝛋𝛆
Lemmchen
badcodecat
makingStuffForFun
Salamander
reactive_recall
thirdBreakfast
Bazsalanszky