ritvik77 (Ritvik Gaur)

reacted to their post with 🚀 about 3 hours ago

Post

229

ritvik77/ContributionChartHuggingFace
It's Ready!

One feature Hugging Face could really benefit from is a contribution heatmap — a visual dashboard to track user engagement and contributions across models, datasets, and models over the year, similar to GitHub’s contribution graph. Guess what, Clem Delangue mentioned idea about using HF API reference for it and we made it for use.

If you are a Hugging Face user add this Space in your collection and it will give you all stats about your contributions and commits nearly same as GitHub. It's still a prototype and still working on it as a product feature.

2 replies

·

posted an update about 6 hours ago

Post

229

ritvik77/ContributionChartHuggingFace
It's Ready!

One feature Hugging Face could really benefit from is a contribution heatmap — a visual dashboard to track user engagement and contributions across models, datasets, and models over the year, similar to GitHub’s contribution graph. Guess what, Clem Delangue mentioned idea about using HF API reference for it and we made it for use.

If you are a Hugging Face user add this Space in your collection and it will give you all stats about your contributions and commits nearly same as GitHub. It's still a prototype and still working on it as a product feature.

2 replies

·

reacted to burtenshaw's post with ❤️ 7 days ago

Post

3373

The Hugging Face Agents Course now includes three major agent frameworks!

🔗 https://huggingface.co/agents-course

This includes LlamaIndex, LangChain, and our very own smolagents. We've worked to integrate the three frameworks in distinctive ways so that learners can reflect on when and where to use each.

This also means that you can follow the course if you're already familiar with one of these frameworks, and soak up some of the fundamental knowledge in earlier units.

Hopefully, this makes the agents course as open to as many people as possible.

3 replies

·

posted an update 9 days ago

Post

431

Someone remember the Wile E. Coyote from Looney Tunes Show? He did it again but now with fooling a Tesla! This shows the difference of LiDAR vs Camera.

Tesla Autopilot Fails Wile E. Coyote Test, Drives Itself Into Picture of a Road.
For Original Video: https://lnkd.in/g4Qi8fd4

replied to their post 9 days ago

Big Asset Firms and tech Giants will soon get a way to even put some price on open source for money.

reacted to their post with ❤️❤️ 9 days ago

Post

2501

Big companies are now training huge AI models with tons of data and billions of parameters, and the future seems to be about quantization—making those models smaller by turning big numbers into simpler ones, like going from 32-bit to 8-bit without reducing accuracy by +/- 0.01%. There should be some standard unit of measurement for the ratio of model size reduction to accuracy lost.

What do you all thing about this ?

4 replies

·

reacted to nicolay-r's post with 👍 10 days ago

Post

1566

📢 With the recent release of Gemma-3, If you interested to play with textual chain-of-though, the notebook below is a wrapper over the the model (native transformers inference API) for passing the predefined schema of promps in batching mode.
https://github.com/nicolay-r/nlp-thirdgate/blob/master/tutorials/llm_gemma_3.ipynb

Limitation: schema supports texts only (for now), while gemma-3 is a text+image to text.

Model: google/gemma-3-1b-it
Provider: https://github.com/nicolay-r/nlp-thirdgate/blob/master/llm/transformers_gemma3.py

1 reply

·

posted an update 10 days ago

Post

2501

Big companies are now training huge AI models with tons of data and billions of parameters, and the future seems to be about quantization—making those models smaller by turning big numbers into simpler ones, like going from 32-bit to 8-bit without reducing accuracy by +/- 0.01%. There should be some standard unit of measurement for the ratio of model size reduction to accuracy lost.

What do you all thing about this ?

4 replies

·

reacted to burtenshaw's post with 👍 16 days ago

Post

1911

Here’s a notebook to make Gemma reason with GRPO & TRL. I made this whilst prepping the next unit of the reasoning course:

In this notebooks I combine together google’s model with some community tooling

- First, I load the model from the Hugging Face hub with transformers’s latest release for Gemma 3
- I use PEFT and bitsandbytes to get it running on Colab
- Then, I took Will Browns processing and reward functions to make reasoning chains from GSM8k
- Finally, I used TRL’s GRPOTrainer to train the model

Next step is to bring Unsloth AI in, then ship it in the reasoning course. Links to notebook below.

https://colab.research.google.com/drive/1Vkl69ytCS3bvOtV9_stRETMthlQXR4wX?usp=sharing

4 replies

·

replied to their post 17 days ago

Hey @nicolay-r this is still in dev phase, also I am trying to super quantize some 70B+ parameter LLM with active layering then tune again on Medical Data and benchmarks and get approved with some doctors and organizations. This way the log GPU can also handle it and making it accessable to everyone.

posted an update 18 days ago

Post

1526

Try it out: ritvik77/Medical_Doctor_AI_LoRA-Mistral-7B-Instruct_FullModel

🩺 Medical Diagnosis AI Model - Powered by Mistral-7B & LoRA 🚀
🔹 Model Overview:
Base Model: Mistral-7B (7.7 billion parameters)
Fine-Tuning Method: LoRA (Low-Rank Adaptation)
Quantization: bnb_4bit (reduces memory footprint while retaining performance)
🔹 Parameter Details:
Original Mistral-7B Parameters: 7.7 billion
LoRA Fine-Tuned Parameters: 4.48% of total model parameters (340 million) Final Merged Model Size (bnb_4bit Quantized): ~4.5GB

This can help you in making a AI agent for healthcare, if you need to finetune it for JSON function/tool calling format you can use some medical function calling dataset to again fine fine tine on it.

3 replies

·

reacted to tomaarsen's post with ❤️ 18 days ago

Post

6582

An assembly of 18 European companies, labs, and universities have banded together to launch 🇪🇺 EuroBERT! It's a state-of-the-art multilingual encoder for 15 European languages, designed to be finetuned for retrieval, classification, etc.

🇪🇺 15 Languages: English, French, German, Spanish, Chinese, Italian, Russian, Polish, Portuguese, Japanese, Vietnamese, Dutch, Arabic, Turkish, Hindi
3️⃣ 3 model sizes: 210M, 610M, and 2.1B parameters - very very useful sizes in my opinion
➡️ Sequence length of 8192 tokens! Nice to see these higher sequence lengths for encoders becoming more common.
⚙️ Architecture based on Llama, but with bi-directional (non-causal) attention to turn it into an encoder. Flash Attention 2 is supported.
🔥 A new Pareto frontier (stronger *and* smaller) for multilingual encoder models
📊 Evaluated against mDeBERTa, mGTE, XLM-RoBERTa for Retrieval, Classification, and Regression (after finetuning for each task separately): EuroBERT punches way above its weight.
📝 Detailed paper with all details, incl. data: FineWeb for English and CulturaX for multilingual data, The Stack v2 and Proof-Pile-2 for code.

Check out the release blogpost here: https://huggingface.co/blog/EuroBERT/release
* EuroBERT/EuroBERT-210m
* EuroBERT/EuroBERT-610m
* EuroBERT/EuroBERT-2.1B

The next step is for researchers to build upon the 3 EuroBERT base models and publish strong retrieval, zero-shot classification, etc. models for all to use. I'm very much looking forward to it!

1 reply

·

posted an update 23 days ago

Post

402

Hey Community,

ritvik77/FineTune_LoRA__AgentToolCall_Mistral-7B_Transformer

Fine-tuned Mistral-7B-Instruct-v0.3 with LoRA on Salesforce Function Dataset (~60K samples) for AI finance Agent, deployed full scale LLM model (14.5GB) via Hugging Face python transformers library and LoRA (PEFT, 715MB) for scalability.

Please let me know any improvements it requires, your ideas and feedback are always welcomed as I am still new to this and still learning.

replied to burtenshaw's post about 1 month ago

Hey Ben, I really loved the precise pin-pointed knowledge I got from the course.

Ritvik Gaur PRO

AI & ML interests

Recent Activity

Organizations

ritvik77's activity