Hugging Face's logo
Asankhaya Sharma's picture
🔄 In a Training Loop
85 141 350

Asankhaya Sharma

codelion
hugging-science
xynic's profile picture Levi-Z's profile picture VigneshBaskaran's profile picture
·
http://asankhaya.github.io/

AI & ML interests

Creator of OptiLLM, OpenEvolve, Adaptive Classifier, and Ellora. Pioneering a new category in AI infrastructure: inference-time compute for LLMs.

Recent Activity

reacted to theirpost with 🤗 about 13 hours ago
SPROG-9M — a 9.37M parameter model trained from scratch to solve GSM8K-style math without using an LLM at inference. The model, https://huggingface.co/codelion/sprog-9m, predicts symbolic programs over number slots, then a deterministic executor does the arithmetic. With a simple verifier, it reaches ~11.8% on GSM8K test. We also released the dataset: https://huggingface.co/datasets/codelion/gsm8k-synth, 117K validated synthetic GSM8K-style problems. Tiny model, no pretraining, no LLM at inference, runs on a laptop.
reacted to theirpost with 👀 about 13 hours ago
SPROG-9M — a 9.37M parameter model trained from scratch to solve GSM8K-style math without using an LLM at inference. The model, https://huggingface.co/codelion/sprog-9m, predicts symbolic programs over number slots, then a deterministic executor does the arithmetic. With a simple verifier, it reaches ~11.8% on GSM8K test. We also released the dataset: https://huggingface.co/datasets/codelion/gsm8k-synth, 117K validated synthetic GSM8K-style problems. Tiny model, no pretraining, no LLM at inference, runs on a laptop.
reacted to theirpost with 🚀 about 13 hours ago
SPROG-9M — a 9.37M parameter model trained from scratch to solve GSM8K-style math without using an LLM at inference. The model, https://huggingface.co/codelion/sprog-9m, predicts symbolic programs over number slots, then a deterministic executor does the arithmetic. With a simple verifier, it reaches ~11.8% on GSM8K test. We also released the dataset: https://huggingface.co/datasets/codelion/gsm8k-synth, 117K validated synthetic GSM8K-style problems. Tiny model, no pretraining, no LLM at inference, runs on a laptop.
View all activity

Organizations

meraGPT's profile picture Lambda Security's profile picture National University of Singapore's profile picture Patched's profile picture ZeroGPU Explorers's profile picture MLX Community's profile picture Social Post Explorers's profile picture Hugging Face Discord Community's profile picture Dria's profile picture Adaptive Classifier's profile picture Reasoning datasets competition 's profile picture Cerebras Hugging Face Hackathon's profile picture LeRobot Worldwide Hackathon's profile picture Hugging Face Context Course's profile picture Agents-MCP-Hackathon's profile picture Hugging Science's profile picture MCP-1st-Birthday's profile picture Algorithmic SuperIntelligence Labs's profile picture Unsloth Jobs Explorers's profile picture Humanity's Last Hackathon's profile picture Build Small Hackathon's profile picture Gemma Challenge's profile picture