Mercedes BENZ: Small LM for In-Vehicle Function Calling

Поділитися
Вставка
  • Опубліковано 24 січ 2025

КОМЕНТАРІ • 14

  • @code4AI
    @code4AI  16 днів тому

    With the automatic audio dubbing from UA-cam /Google you hear a synthetic voice in your regional language.
    To hear my original voice in English, switch to "Default" or "English" in the settings. Thank you.

  • @coldlyanalytical1351
    @coldlyanalytical1351 17 днів тому +8

    Anecdote: I was once working on an oil-rig single board computer .. which was simply too weak for what it needed to do.
    After about 4 weeks and a major software rewrite it was ALMOST usable but not quite ... I had run out of road.
    By chance, one of the hardware techies came by and saw my despair. He told me to wait a moment and then returned with a replacement processor chip which was maybe 5x faster than the original. Problem solved! Apparently he was an official beta tester of Motorola CPUs!
    Moral of the story : we may need to optimise today - but hardware and software will get better and faster tomorrow!

  • @coldlyanalytical1351
    @coldlyanalytical1351 17 днів тому +6

    Re: the need for all this compression work : I used to work for BMW Research, and I found most engineers aim for small, fast code. This is an ingrained habit which is probably not really needed : Nvidia is about to produce a $3000 retail powerful AI processor box which can do what a car needs without needing tiny models. In quantity Mercedes could possibly get a smaller version in quantity for maybe $2000. This is not a huge sum, especially for fancy cars.

  • @shaneoseasnain9730
    @shaneoseasnain9730 17 днів тому +2

    It feels like gene editing. Interesting video

  • @coldlyanalytical1351
    @coldlyanalytical1351 17 днів тому +1

    Excellent - I have been waiting for this video for months!
    Everyone is aiming for HUGE models ... but tiny models will have great opportunities too!
    I have tried machine control LLMs where I get the LLM to emit and process special strings success as [1,5] which are picked up or emitted by a C wrapper to interface with I/O. That said, cars might need medium size rather than tiny models. The tiny models will be need for toasters and cookers.

  • @andikunar7183
    @andikunar7183 17 днів тому +1

    Very cool video, thanks!!! A few thoughts (I'm not an automotive expert at all, but have a tiny bit of embedded background): Q4_0 can be accelerated nicely on current arm CPUs (llama.cpp was able to accelerate PP 2-3x and also TG a bit by using special arm CPU-instructions for GEMM/GEMV operations), a GPU/NPU helps not much for SLM inference as TG/token-generation is mainly limited by RAM-bandwidth. A current NVIDIA Jetson Orin Nano 4GB embedded module (50GB/s memory-bandwidth, with its 64-bit bus) would be a platform with approx. the performance constraints mentioned for SLM token-generation in this paper. To me, it does NOT seem like old/cheap hardware. It's GPUs could be usd for other tasks like e.g. vision. Probably the SLM runs on hardware dedicated to "dashboard" centric features - a Jetson Orin Nano would already be a VERY luxurious processor for this.
    Servus aus Wien

  • @wwkk4964
    @wwkk4964 17 днів тому

    Thabks for sharing!

  • @Tuscani2005GT
    @Tuscani2005GT 17 днів тому

    Great video! Can you the link to paper(s) in the description for these types of videos please?

  • @fdavis1555
    @fdavis1555 17 днів тому

    Interesting concept!

  • @irbsurfer1585
    @irbsurfer1585 17 днів тому

    Tiny LMs? Yes please!

  • @ozne_2358
    @ozne_2358 17 днів тому

    From a Lossless (~1.5:1) Compression Algorithm for Llama2 7B Weights to Variable Precision, Variable Range, Compressed Numeric Data Types for CNNs and LLMs on vixra (re-arrange the letters)

  • @Pure_Science_and_Technology
    @Pure_Science_and_Technology 17 днів тому

    They should just train a model from scratch. They have the money to do it and it’s so domain specific. I’m not sure what the hell they’re doing.

    • @HarshVerma-k9z
      @HarshVerma-k9z 15 днів тому

      Yeah, this is weird but this was a good experiment tbh.

  • @spirobel2.0
    @spirobel2.0 10 днів тому

    its just sad. german bean counter culture at the big autos. meanwhile look at what tesla and the chinese are doing.