最少使用 3090 即可训练自己的比特大脑（miniLLM）🧠（进行中）. Train your own BitBrain(A mini LLM) with just an RTX 3090 minimum.
-
Updated
May 4, 2026 - Python
#
mini-llm
Here are 10 public repositories matching this topic...
Personal hub of LM implementations, NLP experiments, and inference workflows 🛠️
-
Updated
Jul 2, 2026 - Python
Building a complete LLM from scratch. No libraries. No shortcuts. Just NumPy, math, and first principles.
python nlp machine-learning natural-language-processing deep-learning neural-network numpy transformers embeddings artificial-intelligence language-model attention-mechanism from-scratch tokenization self-attention ai-engineering llm generative-ai mini-llm llm-from-scratch
-
Updated
Jul 12, 2026 - Python
GDN+SWA+GQA Hybrid Mini-LLM Trained on Bangla, English & Translation Corpus.
-
Updated
Jul 25, 2026 - Jupyter Notebook
Budget Buddy is a finance chatbot built using Chainlit and the LLaMA language model. It analyzes PDF documents, such as bank statements and budget reports, to provide personalized financial advice and insights. The chatbot is integrated with Hugging Face for model management, offering an interactive way to manage personal finances.
chatbot torch embeddings accelerate llama pypdf pdf-parse sentence-transformers huggingface-transformers langchain huggingface-hub vector-store ctransformers chainlit bitsandbytes mini-llm faiss-vector-database faiss-cpu langchain-community
-
Updated
Dec 10, 2024 - Python
Python-Based Mini LLM: This code implements a simple rule-based Mini LLM that simulates the OpenAI Chat Completion API. It validates the input messages, generates responses using predefined rules, limits the response length with `max_tokens`, counts prompt and completion tokens, and returns a structured JSON response. A custom `APIError` is raised
-
Updated
Aug 5, 2026 - Python
A chrome extension developed to help you fill forms with AI, imagine not having to fill job applications by yourself - yes it does it.
-
Updated
Oct 31, 2023 - Python
Framework-agnostic IR architecture for tiny code LLMs (38M params, Transformer Decoder, RoPE, SwiGLU, GQA) | 框架无关 IR 架构的微型代码语言模型
python nlp training machine-learning ai deep-learning inference pytorch transformer code-generation framework-agnostic language-model rope onnx gqa llm gguf mini-llm swiglu ir-architecture
-
Updated
Jul 24, 2026 - Python
An educational GPT-style Transformer Language Model built from scratch in Python and PyTorch featuring custom tokenization, embeddings, positional encoding, causal masked self-attention, multi-head attention, autoregressive text generation, checkpointing, and temperature/top-k sampling.
python nlp machine-learning natural-language-processing deep-learning pytorch artificial-intelligence transformer educational attention gpt language-model from-scratch educational-project self-attention self-attention-implementation llm mini-llm
-
Updated
Jul 25, 2026 - TypeScript
Improve this page
Add a description, image, and links to the mini-llm topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the mini-llm topic, visit your repo's landing page and select "manage topics."