Thanks for your work on sharing this information. Much easier to watch your content than keep my ear to the ground all day trying to keep up. Much appreciated, sir.
@danielmz992 ай бұрын
Thanks for the great content. A video going through the fine-tuning process on this one would be amazing. I am not sure how this could scale to a video implementation (probably passing a frame each time).
@coolmcdude2 ай бұрын
I also would love a video/notebook for a Florence 2 fine tune
@shangonghoweАй бұрын
Another video which I appreciate a lot! thank you for sharing. I would also like it if you could do another going through the fine-tuning process :)
@IsxaaqAcademy2 ай бұрын
It's also good at OCR for hand written documents
@jeremybristol43742 ай бұрын
I'm enthusiastic about these smaller models. Thanks for covering this!
@IanScrivener2 ай бұрын
Thanks Sam!! Please keep up the great work...
@mukkeshmckenzie73862 ай бұрын
Vqa tutorial would be nice!
@richardobiri2642Ай бұрын
Thanks a lot for this I wish you could consider the continuing process for identifying authentic and fake certificates 🙏🙏🙏
@aa-xn5hc2 ай бұрын
Great, yes, fine tune would be very interesting.
@jefframpe50752 ай бұрын
Thanks, Sam! I always appreciate your videos. I would love your take on how Florence-2 compare with Apple's 4M-21.
@RishabhMathur06Ай бұрын
@samwitteveenai please make a fine-tuning video about VLMs such as: Llava, Florence-2 and if possible try to use Ollama so that we can make the inference on local device.
@GiovaniFerreiraS2 ай бұрын
I'd love seeing a fine tuning video, specially if it's not question answering, just so it's a different use case from the documentation. Maybe with a quick intro talking about what are possible scenarios where fine tune would be specially helpful.
@samwitteveenai2 ай бұрын
Noted!
@marcoscipioni132Ай бұрын
Yes, I'm trying to use it for table extraction out of scanned pdfs with little success so far. Would love to see how you implement that.
@unclecode2 ай бұрын
This is what people should call "small", anything below 1B! Thanks for your video. By the way, I played around with the quantized version, the result is unbelievably good! I shared a post on Twitter and mentioned you and shared the Colab. Take a look at it. I tried 8 bits and 4 bits. It's odd how 4 bits is almost the same as the base model!
@samwitteveenai2 ай бұрын
I saw you tweet and retweeted it, very cool stuff. I will check it out. just been knee deep in Gemma stuff for last few days
@unclecode2 ай бұрын
@@samwitteveenai Thanks, and yes, it's Gemma2's turn. Waiting for your KZfaq notification about the Gemma video!
@micbab-vg2mu2 ай бұрын
Thank you - it looks interesting:)
@ariramkilowan80512 ай бұрын
I think fine-tuning for OCR would be a good demo. OCR in the real world with images of documents is much harder than OCR on electronic documents so would be cool to see how a small model like this does as an alternative to Claude/GPT4.
@MH-ke2wi2 ай бұрын
I tried the OCR and OCR with region on images converted (no scanned) from PDF pages. Nothing fancy, standard text with some titles, sections, lists... it is absolutely unusable. When it detects something, it usually got it right, but it could only see around 25% of the text.
@ariramkilowan80512 ай бұрын
@MH-ke2wi yeah also been struggling to get decent results with OCR
@DodomiaolegemiАй бұрын
Thank you so much!!
@ranu93762 ай бұрын
I've tried this model, describing the image is great. I've also tried the docvqa, but giving only one word answers and not getting even simplest questions right. i had hoped to do some classification and compare with other models.
@ALEXPREMIUMGAME2 ай бұрын
awesome, thanks
@mshonle2 ай бұрын
I wonder how much performance would be affected when something so distilled then gets quantized? Also, it seems amazing that it can handle segmentation for an unspecified set size! With Phi3 Vision you would need to provide a token to represent, say, each giraffe you want to identify.
@samwitteveenai2 ай бұрын
quantization is a good question! I would expect it to suffer more than a big model. Might give it a test tomorrow.
@srk57022 ай бұрын
We request you to do fune tuning on object detection. Because, all llms are useful generating text oupit only. Thanks in advance
@sohitshivhare15412 ай бұрын
Thanks for the information this is great. Can i fine tune it for certain specific images like few short learning. Can you put a tutorial for the same it will be great full.
@ShravanKumar1472 ай бұрын
what would you pick for fine-tuning ? Any specific application ideas?
@toadlguy2 ай бұрын
Would be interested on how much memory is required to run these models. they seem pretty small even unquantized. Maybe I will try it later on my 8GB M1 Mini. One thing I am curious about: at 3:38 , the description for the image is wrong in ways that seem odd. The title is described as being on top with the "20 Years of ..." underneath and Ron's tie is described as red and hair blonde. I wonder if this is just vagaries of the model (placement data would be strange) or over reliance on training data. Or a straight up mistake in 'creating' the paper (which would probably be the most disturbing😉).
@SaiManojPrakhya-mp4oe2 ай бұрын
It would be great if you can show a finetuning example!
@yassinebouchouchaАй бұрын
When will you release a demo on to fine-tune such model ?
@tonyrungeetech2 ай бұрын
Hi Sam. Thank you for the videos. I've been playing around with some of the smaller vision models and trying to implement batched inferencing with little success. If you were trying to accomplish running multiple VQA style questions against the same image quickly, how would you go about that goal? Is batching even in the right direction I should be looking?
@pandian153728 күн бұрын
Is it possible to train ocr task prompt for custom dataset and if we train Florence-2 for ocr task the will it affect performance of the model?
@AbhishekKotecha2 ай бұрын
Hi Sam, thanks for the video. What do you think about how does it compare with Phi3-V? My take is that this is more raw and better for fine tuning, do you also think so?
@Walczyk2 ай бұрын
this is completely better and more advanced than phi 3 v crap image detection