Category: LLM
All the articles with the category "LLM".
Projects
Education
BERT Fine-tuning
Improving a Japanese Text-Generation Model through Fine-Tuning BERT.
PythonPyTorchBERTTransformer
Personal
Build a GPT-like LLM from scratch
An attempt to build a GPT-style LLM from scratch with PyTorch. Covers the full architecture, pre-training loop, decoding strategies, and loading OpenAI GPT-2 weights.
PythonPyTorchTransformerGPT
DEV WIP
Personal
Build Large Reasoning Model (LRM) from scratch
Build a Large Reasoning Model from scratch and turn non-reasoning LLMs into reasoning LLMs.
PythonPyTorchLRMRLGRPOFine-TuningMLX
POST WIP
Personal
Mike 3.0: RAG Powered LLM Model for Chatbot Backend
RAG backend chatbot service built with FastAPI and pgvector. It features real-time document ingestion and LLM-powered responses.
RAGFastAPIPythonuvPostgreSQLpgvectorPytest+6
Personal
RAG vs LoRA: LLM Fine-Tuning Comparison for Mike 3.0
An experimental comparison between RAG and LoRA for building a personal portfolio chatbot.
LoRARAGMLXOllamaGemmaLangflowSupervised Fine-Tuning+4
PKM Notes
LLM
Absolute Positional Embedding
LLM
Aha Moment (Deep Seek R1)
#LRM
Deep Learning LLM
Attention Mechanism
LLM
Attention Scores
#Transformer
LLM
Attention Weights
#Transformer
LLM
Batch Size
LLM
BOS Token
LLM
Broadcasting (Tensor Operation)
#PyTorch
Paper LLM Prompt Engineering
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
LLM Prompt Engineering
Chain-of-Thought Prompting
LLM
Compiler Feedback Loop
#RL
LLM
Context Vector
#Transformer
LLM
Context Window
Paper LLM
DeepSeek-R1 - Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
#LRM
LLM
Emergent Behavior
LLM
EndOfText Token
LLM
DataLoader (PyTorch)
#PyTorch
LLM
Few-shot Learning
LLM
GGUF (GPT-Generated Unified Format)
LLM
Inference Time Compute Scaling
#LRM
LLM
Input Embeddings (Transformer)
#Transformer
LLM
Input-Target Pairs
LLM
LlamaEdge
LLM
LLM Distillation
LLM
Low-Rank Adaptation (LoRA)
#Fine-Tuning
LLM
Next Word Prediction
LLM
One-Hot Encoding
LLM
One-shot Learning
LLM
Parallel Computing (DataLoader)
LLM
Positional Embedding
LLM
Quantization (DeepSeek)
LLM
Quantized Low-Rank Adaptation (QLoRA)
#Fine-Tuning
LLM
Reasoning Model Blueprint (SFT + RL)
#LRM
LLM
Relative Positional Embedding
LLM
Scaled Dot-Product Attention
#Transformer
LLM
Sliding Window Technique
LLM
Stride (Sliding Window Technique)
LLM
System 1 Thinking
#LRM
LLM
System 2 Thinking
#LRM
LLM
Test Time Compute
#LRM
LLM
Token ID (LLM)
LLM
Tokenization
Deep Learning LLM
Transformer
LLM
Vector Embedding
LLM
Vocabulary (Tokenizer)
LLM
