The Kaitchup – AI on a Budget

Home
Notes
AI Notebooks
Table of Contents
Tutorials
Models
Hardware for LLMs
Archive
About

Tutorials

Fine-tune Llama 3 70B on Your GPU with AQLM 2-bit
It's possible to fine-tune Llama 3 70B with only 24 GB of GPU RAM
 • 
Benjamin Marie
Fine-tune Tiny Chat Models with Apple OpenELM and ORPO
Can we make a good chat model with a 270M LLM?
 • 
Benjamin Marie
Run Llama 3 70B on Your GPU with ExLlamaV2
2.5 bits per weight, on average, is good enough
 • 
Benjamin Marie
Phi-3: Fine-tuning and Quantization on Your Computer
Larger and better than Phi-2
 • 
Benjamin Marie
17
Turn Llama 3 into an Embedding Model with LLM2Vec
RAG with Llama 3 for the generation and the retrieval
 • 
Benjamin Marie
13
Estimate the Memory Consumption of LLMs for Inference and Fine-tuning
A close look at the memory consumption of Command-R+, Mixtral-8x22B, and Llama 3 70B
 • 
Benjamin Marie
Fine-tune Llama 3 on Your Computer
With code to merge QLoRA adapters and quantize the model
 • 
Benjamin Marie
21
Neural Speed: Fast Inference on CPU for 4-bit Large Language Models
Up to 40x faster than llama.cpp?
 • 
Benjamin Marie
ORPO: Preference Optimization without the Supervised Fine-tuning (SFT) Step
A much cheaper alignment method but performing as well as DPO
 • 
Benjamin Marie
GaLore: Full Fine-tuning on Your GPU
And pre-training!
 • 
Benjamin Marie
9
A Guide on Hyperparameters and Training Arguments for Fine-tuning LLMs
Batch size, optimizers, learning rate schedulers, bfloat16, ...
 • 
Benjamin Marie
3
Marlin: Nearly Ideal Inference Speed for 4-bit Models with vLLM (1k+ tokens/sec)
Up to 4x times faster inference
 • 
Benjamin Marie
7
© 2024 The Kaitchup
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great culture