Shekswess/tiny-reasoning-language-model
Code repository dedicated to experimenting and research with tiny reasoning language model
This project offers an open pipeline for training small language models to perform step-by-step reasoning. It takes carefully curated datasets, fine-tunes a base model, and then aligns its reasoning style using preference data. The output is a smaller, more efficient language model capable of demonstrating a clear thought process, intended for researchers and machine learning engineers exploring model efficiency and reasoning capabilities.
Use this if you are a machine learning researcher or engineer interested in how smaller language models can be taught to perform complex, multi-step reasoning.
Not ideal if you need a ready-to-use language model for everyday applications, as this is a research prototype with limited capabilities and hallucination tendencies.
Stars
49
Forks
4
Language
Python
License
—
Category
Last pushed
Nov 24, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Shekswess/tiny-reasoning-language-model"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
galilai-group/stable-pretraining
Reliable, minimal and scalable library for pretraining foundation and world models
CognitiveAISystems/MAPF-GPT
[AAAI-2025] This repository contains MAPF-GPT, a deep learning-based model for solving MAPF...
UKPLab/gpl
Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled...
larslorch/avici
Amortized Inference for Causal Structure Learning, NeurIPS 2022
svdrecbd/mhc-mlx
MLX + Metal implementation of mHC: Manifold-Constrained Hyper-Connections by DeepSeek-AI.