# AI techniques

- [Chain](https://aisuko.gitbook.io/wiki/ai-techniques/chain.md)
- [LangChain](https://aisuko.gitbook.io/wiki/ai-techniques/chain/langchain.md): lang-chain is a technique for adapting large language models (LLMs) to specific tasks.
- [Concepts](https://aisuko.gitbook.io/wiki/ai-techniques/chain/langchain/concepts.md)
- [Models](https://aisuko.gitbook.io/wiki/ai-techniques/chain/langchain/models.md)
- [Prompts](https://aisuko.gitbook.io/wiki/ai-techniques/chain/langchain/prompts.md)
- [Memory](https://aisuko.gitbook.io/wiki/ai-techniques/chain/langchain/memory.md)
- [Indexes](https://aisuko.gitbook.io/wiki/ai-techniques/chain/langchain/indexes.md)
- [framework](https://aisuko.gitbook.io/wiki/ai-techniques/framework.md)
- [pytorch](https://aisuko.gitbook.io/wiki/ai-techniques/framework/pytorch.md)
- [Time components](https://aisuko.gitbook.io/wiki/ai-techniques/framework/ml_training_components.md)
- [burn](https://aisuko.gitbook.io/wiki/ai-techniques/framework/burn.md)
- [Adaptation](https://aisuko.gitbook.io/wiki/ai-techniques/adaptation.md)
- [LoRA](https://aisuko.gitbook.io/wiki/ai-techniques/adaptation/lora.md): Low-Rank Adaptation of Large Language Models. It is a promising technique for adapting LLMs to specific tasks in a computationally efficient manner.
- [Matrix Factorization](https://aisuko.gitbook.io/wiki/ai-techniques/adaptation/lora/matrix-factorization.md)
- [SVD](https://aisuko.gitbook.io/wiki/ai-techniques/adaptation/lora/svd.md): Singular Value Decomposition(A mathematical technique)
- [Distillation of SVD](https://aisuko.gitbook.io/wiki/ai-techniques/adaptation/lora/svd/distillation-of-svd.md): A machine learning technique that uses SVD.
- [Eigenvalues of a covariance matrix](https://aisuko.gitbook.io/wiki/ai-techniques/adaptation/lora/svd/eigenvalues-of-a-covariance-matrix.md)
- [Eigenvalues](https://aisuko.gitbook.io/wiki/ai-techniques/adaptation/lora/svd/eigenvalues-of-a-covariance-matrix/eigenvalues.md)
- [Covariance Matrix](https://aisuko.gitbook.io/wiki/ai-techniques/adaptation/lora/svd/eigenvalues-of-a-covariance-matrix/covariance-matrix.md)
- [Checkpoint](https://aisuko.gitbook.io/wiki/ai-techniques/adaptation/lora/checkpoint.md)
- [PEFT](https://aisuko.gitbook.io/wiki/ai-techniques/adaptation/peft.md): State-of-the-art Parameter-Efficient Fine-Tuning methods
- [Training](https://aisuko.gitbook.io/wiki/ai-techniques/training.md)
- [Training with QLoRA](https://aisuko.gitbook.io/wiki/ai-techniques/training/training-with-qlora.md): Fine-tuning models on consumer hardware
- [Deep Speed](https://aisuko.gitbook.io/wiki/ai-techniques/training/deepspeed.md)
- [Stable Diffusion](https://aisuko.gitbook.io/wiki/ai-techniques/stable-diffusion.md)
- [Stable Diffusion model](https://aisuko.gitbook.io/wiki/ai-techniques/stable-diffusion/stable-diffusion-model.md)
- [Stable Diffusion v1 vs v2](https://aisuko.gitbook.io/wiki/ai-techniques/stable-diffusion/stable-diffusion-v1-vs-v2.md)
- [The important parameters for stunning AI image](https://aisuko.gitbook.io/wiki/ai-techniques/stable-diffusion/the-important-parameters-for-stunning-ai-image.md)
- [Diffusion in image](https://aisuko.gitbook.io/wiki/ai-techniques/stable-diffusion/diffusion-in-image.md): Diffusion processing in image
- [Classifier Free Guidance](https://aisuko.gitbook.io/wiki/ai-techniques/stable-diffusion/classifier-free-guidance.md)
- [Denoising strength](https://aisuko.gitbook.io/wiki/ai-techniques/stable-diffusion/denoising-strength.md)
- [Stable Diffusion workflow](https://aisuko.gitbook.io/wiki/ai-techniques/stable-diffusion/stable-diffusion-workflow.md)
- [LoRA(Stable Diffusion)](https://aisuko.gitbook.io/wiki/ai-techniques/stable-diffusion/lora-stable-diffusion.md)
- [Depth maps](https://aisuko.gitbook.io/wiki/ai-techniques/stable-diffusion/depth-maps.md): Depth to image
- [CLIP](https://aisuko.gitbook.io/wiki/ai-techniques/stable-diffusion/clip.md)
- [Embeddings](https://aisuko.gitbook.io/wiki/ai-techniques/stable-diffusion/embeddings.md): The textual inversion
- [VAE](https://aisuko.gitbook.io/wiki/ai-techniques/stable-diffusion/vae.md): VAE stands for variational autoencoder
- [Conditioning](https://aisuko.gitbook.io/wiki/ai-techniques/stable-diffusion/conditioning.md)
- [Diffusion sampling/samplers](https://aisuko.gitbook.io/wiki/ai-techniques/stable-diffusion/diffusion-sampling-samplers.md)
- [Prompt](https://aisuko.gitbook.io/wiki/ai-techniques/stable-diffusion/prompt.md)
- [ControlNet](https://aisuko.gitbook.io/wiki/ai-techniques/stable-diffusion/controlnet.md)
- [Settings Explained](https://aisuko.gitbook.io/wiki/ai-techniques/stable-diffusion/controlnet/settings-explained.md): Explaining the ControlNet settings
- [ControlNet with models](https://aisuko.gitbook.io/wiki/ai-techniques/stable-diffusion/controlnet/controlnet-with-models.md)
- [Large Language Model](https://aisuko.gitbook.io/wiki/ai-techniques/large-language-model.md): Large language model
- [SMID](https://aisuko.gitbook.io/wiki/ai-techniques/large-language-model/smid.md): Single Instruction Multiple Data
- [ARM NEON](https://aisuko.gitbook.io/wiki/ai-techniques/large-language-model/arm-neon.md)
- [Metal](https://aisuko.gitbook.io/wiki/ai-techniques/large-language-model/metal.md)
- [BLAS](https://aisuko.gitbook.io/wiki/ai-techniques/large-language-model/blas.md): Basic Linear Algebra Subprograms
- [ggml](https://aisuko.gitbook.io/wiki/ai-techniques/large-language-model/ggml.md): How to use quantization to democratize access to LLMs?
- [llama.cpp](https://aisuko.gitbook.io/wiki/ai-techniques/large-language-model/llama.cpp.md): Port of Facebook's LLaMA model in C/C++
- [Measuring model quality](https://aisuko.gitbook.io/wiki/ai-techniques/large-language-model/measuring-model-quality.md)
- [Type for NNC](https://aisuko.gitbook.io/wiki/ai-techniques/large-language-model/type-for-nnc.md): Type for neural network computations
- [Token](https://aisuko.gitbook.io/wiki/ai-techniques/large-language-model/token.md)
- [Doc Retrieval && QA with LLMs](https://aisuko.gitbook.io/wiki/ai-techniques/large-language-model/doc_retrieval_and_qa_llms.md): Generative AI - Document Retrieval and Question Answering with LLMs(Apply LLMs to the domain-specific data)
- [Hallucination(AI)](https://aisuko.gitbook.io/wiki/ai-techniques/large-language-model/hallucination.md)
- [diffusers](https://aisuko.gitbook.io/wiki/ai-techniques/diffusers.md): Hugging face diffusers and it allows one to customize the inage generation pipeline.
- [Deconstruct the Stable Diffusion pipeline](https://aisuko.gitbook.io/wiki/ai-techniques/diffusers/deconstruct_sd_pipeline.md)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://aisuko.gitbook.io/wiki/ai-techniques.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.