Pritam Kumar Ravi

PritamcodesAGI

pritam5756

AI & ML interests

LLM for security , Computational Neuroscience.

Recent Activity

reacted to hesamation's post with ❤️ 14 days ago

this paper lists ways to make reasoning LLMs more efficient: > enforce token limits per reasoning step > route tasks to different models (small/large) > compress reasoning chains during SFT > reward based on reasoning length > parallel search at test-time and more... @Xiaoye08 @yaful @Warrieryes https://huggingface.co/papers/2503.21614

liked a model 14 days ago

manycore-research/SpatialLM-Llama-1B

liked a model 14 days ago

rasbt/llama-3.2-from-scratch

View all activity

Organizations

PritamcodesAGI's activity

reacted to hesamation's post with ❤️ 14 days ago

Post

1787

this paper lists ways to make reasoning LLMs more efficient:
> enforce token limits per reasoning step
> route tasks to different models (small/large)
> compress reasoning chains during SFT
> reward based on reasoning length
> parallel search at test-time
and more...
@Xiaoye08 @yaful @Warrieryes
A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond (2503.21614)

liked 2 models 14 days ago

manycore-research/SpatialLM-Llama-1B

Text Generation • Updated 25 days ago • 18.7k • 943

rasbt/llama-3.2-from-scratch

Updated 14 days ago • 252

liked a model 22 days ago

deepseek-ai/DeepSeek-V3-0324

Text Generation • Updated 20 days ago • 221k • • 2.6k

commented on LLM Inference on Edge: A Fun and Easy Guide to run LLMs via React Native on your Phone! 24 days ago

Hi can I convert VLMs into GGUF?

updated a model 24 days ago

PritamcodesAGI/SmolLM2-135M-Instruct-ONNX

Updated 24 days ago • 4

published a model 24 days ago

PritamcodesAGI/SmolLM2-135M-Instruct-ONNX

Updated 24 days ago • 4

liked a Space 24 days ago

Convert to ONNX

☯

Convert a Hugging Face model to ONNX format

updated a model 29 days ago

PritamcodesAGI/Magma-8B-4bit

Updated 29 days ago • 64

published a model 29 days ago

PritamcodesAGI/Magma-8B-4bit

Updated 29 days ago • 64

liked a model 29 days ago

microsoft/Magma-8B

Image-Text-to-Text • Updated 15 days ago • 5.29k • 354

reacted to burtenshaw's post with 🤗 about 1 month ago

Post

3802

I’m super excited to work with @mlabonne to build the first practical example in the reasoning course.

🔗

reasoning-course

Here's a quick walk through of the first drop of material that works toward the use case:

- a fundamental introduction to reinforcement learning. Answering questions like, ‘what is a reward?’ and ‘how do we create an environment for a language model?’

- Then it focuses on Deepseek R1 by walking through the paper and highlighting key aspects. This is an old school way to learn ML topics, but it always works.

- Next, it takes to you Transformers Reinforcement Learning and demonstrates potential reward functions you could use. This is cool because it uses Marimo notebooks to visualise the reward.

- Finally, Maxime walks us through a real training notebook that uses GRPO to reduce generation length. I’m really into this because it works and Maxime took the time to validate it share assets and logging from his own runs for you to compare with.

Maxime’s work and notebooks have been a major part of the open source community over the last few years. I, like everyone, have learnt so much from them.