Skip to content
#

thinking-llm

Star

Here is 1 public repository matching this topic...

AarambhDevHub / aarambh-ai

Sponsor
Star 16

🦀 Decoder-only LLM built from scratch in pure Rust using Candle — no Python, no PyTorch. Thinking engine, INT4/GGUF quantization, LoRA/QLoRA fine-tuning, GRPO alignment, and self-learning loop. Scales: Tiny (25M) to Large (1.3B).

nlp rust machine-learning reinforcement-learning deep-learning tokenizer transformer lora quantization candle from-scratch self-learning inference-engine llm safetensors large-language-model gguf decoder-only grpo thinking-llm
  • Updated Jul 10, 2026
  • Rust

Improve this page

Add a description, image, and links to the thinking-llm topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the thinking-llm topic, visit your repo's landing page and select "manage topics."

Learn more