Hugging Face's logo

Seance Table
non-profit
https://turn.pw
Activity Feed

AI & ML interests

None defined yet.
Quazim0t0 
posted an update 4 days ago
view post
Post
240
Used YoloV8n/YoloV11n Onnx + FastVLM to provide real time object detection and annotation. Works well with videos that do not have a lot of changes. In the space I used a stock security camera footage. It annotates using FastVLM while doing Object Detection using YoloV8n. The first version of this used only the FastVLM to annotate to draw the boxes then I realized that I could just be using Yolov8n. Really excited to see the future applications of ONNX models!

See the difference!
Quazim0t0/FastVLM-YoloV8n-v2
Quazim0t0/FastVLM-YoloV11n
Quazim0t0 
posted an update 6 days ago
view post
Post
1852
I loved the idea of the Boxing by sergiopaniego/vlm_object_understanding
And webml-community/fastvlm-webgpu


So I tried to combine the two idea, unfortunately I can’t seem to get it consistent and I only worked on the File Upload side. You may have to change the prompt a bit to suite the video you upload but it seems to semi work. If anyone knows a better way to fix this, I really wanted to use this for a project but I can’t seem to figure it out.

Quazim0t0/FastVLMBoxes
I used videos from here and uploaded them to try it out.

https://pixabay.com/videos/search/branch+birds/
Quazim0t0 
posted an update 4 months ago
view post
Post
1203
Thank you to the Open LLM Leaderboard's team for offering it to the community for as long as they did. I only recently joined HF, and it provided a lot of incentive and information to make better models.

Always will remember getting to #112 :D

Anyone have a solid way to test my models privately? Please let me know!

  • 1 reply
·
Quazim0t0 
posted an update 4 months ago
view post
Post
649
Update to the Imagine side-project.
Just uploaded the 16Bit & Q4

Samples: (Used a base Microsoft Phi4 model)
*You may experience bugs with either the model or the Open WebUI function*
Open WebUI function: https://openwebui.com/f/quaz93/imagine_phi
https://huggingface.co/Quazim0t0/Imagine-v0.5-16bit - Haven't tested
https://huggingface.co/Quazim0t0/ImagineTest-v0.5-GGUF - Tested (Pictures)

Dataset: https://huggingface.co/datasets/Quazim0t0/Amanita-Imagine
Small Dataset of 500+ entries, still working on it here and there when I can.
Pictures use the Open Web UI function I provided.
  • 1 reply
·
Quazim0t0 
posted an update 5 months ago
view post
Post
2242
Debugging Tags:
Imagine, Associated Thoughts, Dialectical Analysis, Backwards Induction, Metacognition, and Normal Thought Processes such as <think> or <begin_of_thought>

Edit: Uploaded new images w/ a Open WebUI function to organize the tags.
Open WebUI Function: https://openwebui.com/f/quaz93/imagine_phi

This Phi-4 model is part of a test project that I called Micro-Dose. My goal was to use a small dataset to activate reasoning and other cognitive processes without relying on a large dataset.

I found that this was possible with a tiny dataset of just 90 rows, specifically designed as math problems. In the initial iterations, the dataset only activated reasoning when a math-related question was asked. I then made a few changes to the dataset’s structure, including the order of information and the naming of tags. You can see the sample results in the pictures. Not really anything special, just thought I'd share.

Tweaked the dataset a bit:
https://huggingface.co/Quazim0t0/Imagine-Phi-v0.2-GGUF
https://huggingface.co/datasets/Quazim0t0/MicroDoseV0.2


First image shows the new tags, second shows the regular thought process and the third is the model in combination with web searches
 
  • 2 replies
·
Quazim0t0 
posted an update 5 months ago
view post
Post
2440
My first attempt at using SmolAgents:
https://huggingface.co/spaces/Quazim0t0/CSVAgent

The video attached was an example for this space.

Based on ZennyKenny's SqlAgent:
ZennyKenny/sqlAgent

You can upload a CSV file and it will automatically populate the table, then you can ask questions about the data.

Grab a sample CSV file here: https://github.com/datablist/sample-csv-files

The questions that can be asked may be limited.

_______________________
Second: https://huggingface.co/spaces/Quazim0t0/TXTAgent
Created an Agent that converts a .txt file into a CSV file, then you can ask about the data and also download the CSV file that was generated.

_______________________
Third: https://huggingface.co/spaces/Quazim0t0/ReportAgent
Upload Multiple TXT/DOC files to then generate a report from those files.

_______________________
Lastly: https://huggingface.co/spaces/Quazim0t0/qResearch
A Research tool that uses DuckDuckGo for Web Searches, Wikipedia and tries to refine the answers in MLA Format.
Quazim0t0 
published a Space 6 months ago