Language Models

LLM architectures, training, capabilities, and model comparisons

1.

Large Language Models WIP

Overview of LLM architectures, training, and capabilities

2.

Model Lists

Reference list of LLMs with parameter counts and release info

3.

Model Selection Guide WIP

How to choose the right LLM based on GPU constraints, task requirements, and architecture (MoE vs Dense)

4.

Meta-Prompting & Frameworks WIP

Frameworks for algorithmic prompt optimization instead of manual prompt engineering

5.

Open-Source Models: Coding & Action WIP

Salesforce xLAM/xGen/CodeGen, DeepSeek-Coder, and Qwen-2.5-Coder

6.

Open-Source Models: Reasoning & Alignment WIP

Orca 2, Phi-3, and Nemotron for reasoning, alignment, and RAG

7.

Function Gemma WIP

Google's open-weights LLM specifically tuned for function calling and on-device agents

8.

LLMs for Recommender Systems (LLMRec, RLMRec) WIP

Leveraging Large Language Models and Recursive Language Models for RecSys