I'm using https://artificialanalysis.ai/ just because it puts everything in one place! It's not the best resource but these days I'm all about saving time.
@ThomasTheMaker if you make an issue on the repo, I'll look into it!
@ThomasTheMaker it's just the raw attention and transformer architecture in golang designed for serverless so performance will definitely be less than ggml and llama.cpp since it's not accelerated by GPU's but if you're into edge AI CPU only, this is the first, only and best way to compute attention.
Quantization can definitely be supported as it's just a math model!
This is a pretty big update for sure. The models have improved significantly which is great for everyone involved, especially the end user. Those datasets look very promising as well!
Sounds interesting, I’ll check it out!
This is a really interesting post. I’ve been looking at the DeepSeek models for sure. This shows a pretty nice improvement, would love to see some example changes!
Very cool
Sir, basically I want to create a generative AI university helpdesk chatbot, and for this, I have created datasets myself and also fine-tuned models, but I am not getting satisfactory results. Sir, if you have time, could you please check my datasets in my profile and help me understand how I can improve my dataset and work on it so that my task gets completed? I would be very grateful to you.
I would enhance your dataset to use multi turn conversations if you can at all for llama2 you could do something like this:
<s>[INST] Is the BS Physics program a part-time or full-time course? [/INST] The BS Physics program is a full-time undergraduate program that requires regular on-campus attendance. </s><s>[INST] How many units per semester? [/INST] A typical semester load consists of 15-18 units. </s>
hope this helps! Again, please reach out to me on discord here: takarajordan_82155
gimme an invite! :D
SmolTuners
you guys are amazing!
