InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

  1. LLMs-from-scratch

    AI repositories

    Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

    Stale GitHub, rasbt 108.3k ★Custom licence (see repository)Updated 7 days ago

    git clone https://github.com/rasbt/LLMs-from-scratch.git
  2. llm-internals

    AI repositories

    Learn LLM internals step by step - from tokenization to attention to inference optimization.

    Indexed GitHub, amitshekhariitbhu 1,773 ★Apache-2.0Updated today

    git clone https://github.com/amitshekhariitbhu/llm-internals.git
  3. how-to-train-your-gpt

    Docs & tutorials

    Build a modern LLM from scratch. Every line commented. Explained like we are five.

    Stale GitHub, raiyanyahya 4,151 ★MITUpdated 21 days ago

    git clone https://github.com/raiyanyahya/how-to-train-your-gpt.git
  4. DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

    Indexed OpenRouter model list, deepseek Updated 11 months ago

    deepseek/deepseek-v3.2
  5. MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it...

    No longer listed OpenRouter model list, minimax Updated 17 months ago

    minimax/minimax-m1
  6. DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

    Indexed OpenRouter model list, deepseek Updated 13 months ago

    deepseek/deepseek-v3.2-exp
  7. The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...

    Indexed OpenRouter model list, qwen Updated 8 months ago

    qwen/qwen3.5-27b
  8. ERNIE-Light-DT-1.0 is based on open-source GLM models and includes research findings from Baidu Search's Lightning large model. It features Baidu Sparse Attention (BSA), a unique sparse attention mechanism developed by...

    Indexed OpenRouter model list, baidu Updated 6 days ago

    baidu/ernie-light-dt-1.0-intl
  9. The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...

    Indexed OpenRouter model list, qwen Updated 8 months ago

    qwen/qwen3.5-flash-02-23
  10. The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...

    Indexed OpenRouter model list, qwen Updated 8 months ago

    qwen/qwen3.5-35b-a3b
  11. The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...

    Indexed OpenRouter model list, qwen Updated 8 months ago

    qwen/qwen3.5-122b-a10b
  12. The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...

    Indexed OpenRouter model list, qwen Updated 9 months ago

    qwen/qwen3.5-397b-a17b
  13. The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...

    Indexed OpenRouter model list, qwen Updated 9 months ago

    qwen/qwen3.5-plus-02-15
  14. MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...

    Indexed OpenRouter model list, xiaomi Updated 56 days ago

    xiaomi/mimo-v2.6-flash

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.