Skip to content
View binaryecheos's full-sized avatar
💭
I may be slow to respond.
💭
I may be slow to respond.
5 followers · 5 following

Achievements

Achievement: QuickdrawAchievement: YOLOAchievement: Pull Shark

Achievements

Achievement: QuickdrawAchievement: YOLOAchievement: Pull Shark

Highlights

Block or report binaryecheos

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
binaryecheos/README.md 
┌────────────────────────────────────┐
│  gourav                            │
│  cs / ai / ml                      │
└────────────────────────────────────┘


learning in public.  
building in private.

---

interests
---------
• small language models  
• capacity + constraints  
• reasoning in latent space  
• systems that don’t pretend to be magic  

---

currently
---------
• implementing papers  
• breaking models to see why they work  
• experimenting with efficient representations  

---

stack
-----
python · c++  
pytorch · tensorflow · sklearn  
mlflow · hf · langchain  
flask · docker · k8s  
linux  

---

presence
--------
x    → https://x.com/Gourav_sahu_  
web  → https://gouravsahu.space  

---

notes
-----
models fail quietly.  
assumptions don’t.

trying to write code  
that explains itself.

Pinned Loading

  1. oppimista-logs oppimista-logs Public

    This repo is where I keep experiments, math notes, model implementations and ML systems

    Jupyter Notebook

  2. dtc-route-rationalization dtc-route-rationalization Public

    Jupyter Notebook 1

  3. Price-Prediction-Model Price-Prediction-Model Public

    Python

  4. SLM-tinystories SLM-tinystories Public

    TinyStories-based small language model in a Jupyter notebook, training a tiny GPT-style Transformer on the synthetic TinyStories kids-story dataset to see how small you can go while still getting c…

    Jupyter Notebook