Wow, I can't wait to try Reachy Mini and get back into telepresence development. Its been awhile but I had a web server I wrote years back that let you remote pilot a robot with a camera and video capture to cloud which was itself a peer web server / client.

It was capable of driving (tank treads) and picked and place with a little bull dozer/claw robot which was written with gcode for the motors. Once users figured out how to have it unplug itself it was short lived on the web.

Where can I buy one and get rocking with it?

Aaron

This morning I completed the agentic demonstration with the SFT fine tuned model. Now the demo does the following:

1. Allows user to download an open model they can specialize fine tune easily.
2. Provide a CSV file with fine tune QA dataset.
3. Using torch and transformers create an SFT output model with the new data trained to the model with 3 epochs.
4. Ability to Test new model with list of QA questions and compare answers to expected.
5. Demonstrate use of agents with smolagents tools.

Try it here:

https://huggingface.co/spaces/awacke1/TorchTransformers-NLP-CV-SFT

Download ML Models:

Build ML Models with Specialized Fine Tuning to a CSV:

Test your SFT Version with your changes.

Have an Agentic RAG Party with agents and your SFT model

Hope you enjoy and this demo is useful to you on your learning journey in ML!!

--Aaron Wacker
https://huggingface.co/awacke1
https://x.com/Aaron_Wacker

After trying pretty much everything I gave the latest Grok2 a spin at converting my old malfunctioning Python/Gradio code which no longer adheres to syntax innovations and feature adds within python and gradio.

Grok2 in my opinion is the only one which could do this. Examine below instant one shot win by Grok2 with gradio! Greatest thing about it is it shows references via tweet so you can find where the intelligence was added so Grok2 is using modern syntax and unlike OpenAI and Anthropic, it produces innovative modern results aware of recent innovation.

Grok2 for the win I guess!

Tried a straw man example shown below which fails on others but works on Grok2:

Original which fails now if you upgrade Gradio:

import gradio as gr
from fastai.vision.all import *
import skimage

learn = load_learner('characters.pkl')

labels = learn.dls.vocab
def predict(img):
    pred,pred_idx,probs = learn.predict(img)
    return {labels[i]: float(probs[i]) for i in range(len(labels))}

title = "Video Game Character Classifier"
# description = "A pet breed classifier trained on the Oxford Pets dataset with fastai. Created as a demo for Gradio and HuggingFace Spaces."
#article="<p style='text-align: center'><a href='https://tmabraham.github.io/blog/gradio_hf_spaces_tutorial' target='_blank'>Blog post</a></p>"
examples = ['ellie.jpg','arthur.jpg','kratos.jpg','ellielou.jpg']
interpretation='default'
enable_queue=True

gr.Interface(fn=predict,inputs=gr.inputs.Image(shape=(128, 128)),outputs=gr.outputs.Label(),title=title,examples=examples,interpretation=interpretation,enable_queue=enable_queue).launch()

Second Grok2 prompt (first switched to blocks shown below).

Grok2's second shot with examples of errors gave working code and also tweet references!!

import gradio as gr
from fastai.vision.all import *
import skimage

learn = load_learner('characters.pkl')

labels = learn.dls.vocab
def predict(img):
    pred, pred_idx, probs = learn.predict(img)
    return {labels[i]: float(probs[i]) for i in range(len(labels))}

title = "Video Game Character Classifier"
examples = ['ellie.jpg', 'arthur.jpg', 'kratos.jpg', 'ellielou.jpg']

# Updated Gradio Interface with new syntax
with gr.Blocks() as demo:
    gr.Markdown("# " + title)
    # Use width and height instead of shape
    image_input = gr.Image(width=128, height=128)
    label_output = gr.Label()
    
    # Create submit button
    submit_btn = gr.Button("Classify")
    submit_btn.click(fn=predict, inputs=image_input, outputs=label_output)

    # Adding examples
    gr.Examples(examples, inputs=image_input, outputs=label_output, fn=predict)

demo.launch()

Most excellent Dataset sir. This is quite useful. Thanks! Aaron

Thankyou for the tips and insight on Gradio 5. Much appreciated,